diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 2b484b1d9d0494426099ca5447b62ae0d3df7259..054e57a2434f1e6dbe683593b407e2436026b93d 100644 --- a/analysis/current/analysis-report-hybrid.json +++ b/analysis/current/analysis-report-hybrid.json @@ -1,8 +1,8 @@ { "schema_version": "1.0", "repo": "huggingface/transformers", - "snapshot_id": "20260504T180032Z", - "generated_at": "2026-05-04T18:07:11Z", + "snapshot_id": "20260505T000047Z", + "generated_at": "2026-05-05T00:04:56Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1148,6 +1148,204 @@ } ] }, + { + "cluster_id": "cluster-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, { "cluster_id": "cluster-43240-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", @@ -1422,76 +1620,6 @@ } ] }, - { - "cluster_id": "cluster-43824-3", - "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", - "status": "open", - "confidence": 0.75, - "canonical_issue_number": 43824, - "canonical_pr_number": 43836, - "issue_numbers": [ - 43824 - ], - "pr_numbers": [ - 43836, - 43842 - ], - "evidence_types": [ - "closing_reference", - "shared_issue_target" - ], - "pr_comparisons": [ - { - "left_pr_number": 43836, - "right_pr_number": 43842, - "code_similarity": 0.332, - "size_similarity": 0.088, - "file_overlap": 1.0, - "area_overlap": 0.033, - "patch_similarity": 0.017, - "shared_filenames": [ - "src/transformers/cli/serve.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/cli/serve.py", - "left_ranges": [ - [ - 11, - 18 - ], - [ - 359, - 429 - ], - [ - 584, - 590 - ], - [ - 1892, - 1910 - ], - [ - 1917, - 1923 - ] - ], - "right_ranges": [ - [ - 54, - 61 - ], - [ - 587, - 593 - ] - ] - } - ] - } - ] - }, { "cluster_id": "cluster-45081-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", @@ -1989,6 +2117,16 @@ "target_issue_number": 43240, "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." }, + { + "cluster_id": "cluster-43656-4", + "canonical_pr_number": 43656, + "duplicate_pr_numbers": [ + 43836, + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43656-4 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target, soft_similarity evidence." + }, { "cluster_id": "cluster-43698-3", "canonical_pr_number": 43779, @@ -1998,15 +2136,6 @@ "target_issue_number": 43698, "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." }, - { - "cluster_id": "cluster-43824-3", - "canonical_pr_number": 43836, - "duplicate_pr_numbers": [ - 43842 - ], - "target_issue_number": 43824, - "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." - }, { "cluster_id": "cluster-43979-11", "canonical_pr_number": 44007, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index a19e07ac5829d751817ee147b454578dce2a4d05..9a0ef737745819e48fc493aca0d022755725d70d 100644 --- a/analysis/current/analysis-report-hybrid.llm-reviews.json +++ b/analysis/current/analysis-report-hybrid.llm-reviews.json @@ -1,8 +1,8 @@ { "schema_version": "1.0", "repo": "huggingface/transformers", - "snapshot_id": "20260504T180032Z", - "generated_at": "2026-05-04T18:07:11Z", + "snapshot_id": "20260505T000047Z", + "generated_at": "2026-05-05T00:04:56Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -84,8 +84,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -723,8 +723,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -2057,8 +2057,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -2414,8 +2414,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -4682,8 +4682,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -7495,8 +7495,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -8098,8 +8098,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -8687,8 +8687,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -8991,8 +8991,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -9608,8 +9608,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -9927,8 +9927,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -10245,8 +10245,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -10564,8 +10564,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -11204,8 +11204,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -11538,8 +11538,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -11850,8 +11850,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -12196,8 +12196,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -12508,8 +12508,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -12855,8 +12855,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -13202,8 +13202,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -13552,8 +13552,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -13934,8 +13934,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -14317,8 +14317,8 @@ "review_unit_count": 44, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-384", "nodes": [ @@ -15811,8 +15811,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45762-2", "nodes": [ @@ -15874,8 +15874,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45764-2", "nodes": [ @@ -15980,12 +15980,12 @@ "pull_request:44827|pull_request:45770", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "f5a5321f2063277d5cc28284c41d76acb3289e12a4c3570b129b79515b6d5e1d", + "prepared_review_unit_hash": "9326002ff67b9751f2c06facb98e4abe8010b6dc7f8185dc2f78a5cc6d62875b", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 22, - "serialized_chars": 36417, + "serialized_chars": 36419, "estimated_input_tokens": 9105, "estimated_eval_tokens": 18466 }, @@ -15993,7 +15993,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 22, - "serialized_chars": 36417, + "serialized_chars": 36419, "estimated_input_tokens": 9105, "estimated_eval_tokens": 18466 }, @@ -16002,150 +16002,156 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Mostly a heterogeneous cluster of unrelated PRs: new model additions, tokenizer/processor improvements, a couple of small model/test fixes, and two closely related loss-utils PRs. Only 43251 and 43254 look like the same underlying change; the rest should stay separate.", - "confidence": 0.94, + "summary": "Only one soft edge looks like a true duplicate: the two `fixed_cross_entropy` PRs both implement the same kwargs/label_smoothing/weight pass-through on the same function and target the same issue. The rest are unrelated model additions, refactors, or test/documentation changes in different code paths.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR for the whole cluster: the items span unrelated features and fixes. The only clear duplicate subtopic is the fixed_cross_entropy kwargs work.", + "canonical_pr_reason": "PR #43251 is the better canonical representative: it has the explicit issue link, broader/clearer wording of the same `cross_entropy` fix, and the same code path as #43254.", "best_issue_reason": null, - "best_pr_reason": "43251 is the strongest representative of the only true duplicate subtopic: it has the explicit issue link and the core loss-utils fix with broader kwargs support.", + "best_pr_reason": "PR #43251 is the best global representative because it is the clearest, issue-linked version of the shared `fixed_cross_entropy` fix; the only other true duplicate (#43254) is a near-identical variant.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "VideoPrism model scaffolding is unrelated to an executorch dynamic-shape test." + "reason": "Unrelated PRs: VideoPrism model addition vs ExecuTorch dynamic-shape test coverage." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Mistral tokenizer helper methods are unrelated to adding the MobileLLM model." + "reason": "Different changes: Mistral tokenizer method additions vs adding a new MobileLLM model." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer API additions and executorch export tests are different changes." + "reason": "Tokenizer API fix vs ExecuTorch export test; no shared underlying bug." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness is unrelated to a new model implementation." + "reason": "Processor robustness refactor is unrelated to MobileLLM model implementation." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss-function kwargs support is unrelated to MobileLLM model addition." + "reason": "`fixed_cross_entropy` kwargs bugfix is unrelated to adding MobileLLM." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Same file overlap is incidental; one change is loss kwargs, the other is Mistral4 test/model wiring." + "reason": "Different code paths: loss utility fix vs Mistral4 test/integration changes." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch dynamic-shape testing and Mistral4 test fixes are not the same bug/change." + "reason": "ExecuTorch dynamic-shape test and Mistral4 test fixes are not the same underlying change." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Executorch export testing is unrelated to adding MobileLLM." + "reason": "ExecuTorch export test vs MobileLLM model addition; no duplicate bug/change." }, { "left": "pull_request:43823", "right": "pull_request:45770", "accept": false, - "reason": "New MobileLLM model work is unrelated to AutoModel text_config unwrapping." + "reason": "New MobileLLM model vs AutoModel `text_config` unwrap logic; different functionality." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "MobileLLM model addition and config resolution order fixes are different changes." + "reason": "MobileLLM model addition is unrelated to `cls.config` resolution order fix." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "Adding MobileLLM is unrelated to Falcon output-interface refactoring." + "reason": "New model implementation vs Falcon output-collection refactor; distinct changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:44827", + "accept": false, + "reason": "MobileLLM model addition and Mistral4 test fix do not address the same bug." }, { "left": "pull_request:43995", "right": "pull_request:45770", "accept": false, - "reason": "Falcon output collection refactor and AutoModel config unwrapping are separate code paths." + "reason": "Falcon refactor and AutoModel `text_config` unwrap are different code paths." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon model refactoring and the model-creation skill are unrelated." + "reason": "Falcon model refactor is unrelated to the model-creation skill PR." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactoring and Mistral4 test fixes do not target the same underlying problem." + "reason": "Falcon output interface refactor vs Mistral4 test fix; no shared concrete fix." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test fixes and the layrnorm->layernorm rename are different issues." + "reason": "Mistral4 test/integration work is unrelated to the `layrnorm` spelling correction across CLIP-like models." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 tests and cls.config resolution-order changes are unrelated." + "reason": "Mistral4 test fixes and `cls.config` resolution order are separate issues." }, { "left": "pull_request:43823", "right": "pull_request:44827", "accept": false, - "reason": "MobileLLM model addition and Mistral4 test fixes are unrelated." + "reason": "MobileLLM model addition and Mistral4 test fix are different changes." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 test fixes and the model-creation skill are not the same change." + "reason": "Mistral4 test fixes are unrelated to the model-creation skill/meta PR." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "MobileLLM model code and a repository skill file are unrelated." + "reason": "New model implementation vs meta skill/doc PR; not the same underlying change." }, { "left": "pull_request:45655", "right": "pull_request:45770", "accept": false, - "reason": "Both touch config handling, but they fix different problems in different code paths." + "reason": "Both touch config handling, but one fixes `cls.config` resolution order while the other unwraps `text_config`; not the same concrete bug." }, { "left": "pull_request:44827", "right": "pull_request:45770", "accept": false, - "reason": "Mistral4 tests and AutoModel text_config unwrapping are not the same bug." + "reason": "Mistral4 test fixes are unrelated to AutoModel `text_config` unwrapping." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "These are effectively the same fixed_cross_entropy change in the same file: both forward supported kwargs into nn.functional.cross_entropy." + "reason": "Both PRs fix the same `fixed_cross_entropy` API gap in `src/transformers/loss/loss_utils.py` by passing supported kwargs (`weight`, `label_smoothing`) through to `nn.functional.cross_entropy`." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The cluster is indeed mostly heterogeneous, and the only clearly mergeable duplicate pair is 43251/43254: both touch the same loss_utils fixed_cross_entropy path, target the same issue, and implement the same kwargs-forwarding fix." + "feedback": "The analyst output is well grounded in the packet and stays conservative on the soft edges. The only accepted duplicate pair, PR #43251 and #43254, is supported by the shared file, same function, and shared issue target 43240. The other verdicts are consistently limited to unrelated model additions, refactors, or tests, with no overstatement of duplicate evidence." }, "evaluator_used": true, "retried": false, @@ -16172,12 +16178,12 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "820fa66f13a7ab3757ca398d3953b20090c184808d9e470474452903480402bf", + "prepared_review_unit_hash": "745c6dc5e0c79b23001ad329081e4a080b55a68f260b4138da889ead134beb79", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7225, + "serialized_chars": 7226, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -16185,7 +16191,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7225, + "serialized_chars": 7226, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -16194,18 +16200,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two PRs in the same model family, but they are not duplicates: one implements core VibeVoice, the other adds a separate realtime variant with additional tokenizer/feature-extraction work. The shared filenames mainly reflect common model plumbing, not the same fix/change.", + "summary": "Two VibeVoice PRs overlap on the base model/docs/auto-registration scaffolding, but they target different deliverables: a full VibeVoice implementation vs. a later VibeVoice Realtime extension. They are related, not duplicates.", "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the base VibeVoice implementation and is the broader, more central change set; #42781 builds on the same model family but targets a different realtime variant, so it should not be treated as the same PR.", + "canonical_pr_reason": "PR 40546 is the broader foundational VibeVoice implementation and is the better representative of the base feature work. PR 42781 is a separate realtime follow-up with additional tokenizer/generation changes, not the same change set.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the best representative of the cluster because it is the main non-draft implementation of VibeVoice and appears more complete and foundational than the draft realtime follow-up.", + "best_pr_reason": "PR 40546 is the stronger cluster representative because it is the original, more complete implementation and is not marked draft. PR 42781 appears to be a distinct extension rather than a duplicate of the base VibeVoice PR.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Both touch VibeVoice infrastructure, but #40546 implements the base model while #42781 adds realtime-specific functionality and acoustic tokenizer support. They do not appear to fix the same concrete code-path problem and would not plausibly be merged into one PR." + "reason": "Both touch VibeVoice infrastructure, but 42781 adds realtime-specific components and extra generation/tokenizer work; it is a follow-up feature, not the same concrete fix/change as 40546." } ] }, @@ -16235,7 +16241,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "63199f0441f4d33bae2a9d9f4d141cf0107bfce8ac621dec0db991550bd520cc", + "prepared_review_unit_hash": "71de2fd1b4c153e5fc1784e73f43a94f41e6a55f77db4c96906f17dc3915fb61", "component_budget": { "node_count": 2, "item_count": 2, @@ -16257,18 +16263,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two unrelated pull requests: one adds TimesFM covariate forecasting, the other adds DINOv3 image classification support. They touch different models, code paths, and feature areas, so this cluster is not a duplicate set.", + "summary": "These are two unrelated pull requests: one adds TimesFM covariate forecasting support, the other adds DINOv3 image-classification support. They share only a broad \u201cmodel feature addition\u201d similarity, not the same code path or fix.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #41224 is the better canonical PR because it is a narrower, concrete feature addition with a single model family and a clear end-user capability.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR #41224 is the best representative PR for the cluster only in the weak sense that it is more self-contained; however, the cluster does not contain a true duplicate pair.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different model families and different functionality: TimesFM forecasting with covariates versus DINOv3 image classification. They do not fix the same bug or implement the same change, and would not plausibly be merged into one PR." + "reason": "Reject: they modify different models, different files, and different functionality. TimesFM covariate forecasting and DINOv3 classification support are separate feature additions, not the same underlying change or bug fix." } ] }, @@ -16361,7 +16367,7 @@ "soft_pairs": [ "pull_request:41797|pull_request:45186" ], - "prepared_review_unit_hash": "9408cc9e2e75042cdd71b9ff60503e32d75bef22c3ef2c604f5b3acc4c90938c", + "prepared_review_unit_hash": "aa039cd1adc9376a7cb012028955f19db45c1e3361eeb05bd6d5a40a65b87cc8", "component_budget": { "node_count": 2, "item_count": 2, @@ -16383,18 +16389,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are not duplicates: they add different model integrations (DeepSeekOCR vs Isaac) and only overlap on shared auto-registration/docs plumbing.", + "summary": "These are not duplicates: one PR adds DeepSeek OCR, the other adds Isaac. They share framework scaffolding for new model integrations, but the actual model code, docs, tests, and behavior are for different underlying models and code paths.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: 41797 introduces DeepSeekOCR, while 45186 introduces Isaac; the overlap is only in shared model-registration infrastructure.", + "canonical_pr_reason": "No canonical PR: the two pull requests implement different model additions (DeepSeek OCR vs Isaac), not the same fix/change.", "best_issue_reason": null, - "best_pr_reason": "Neither PR is a good global duplicate representative because they solve different integration tasks; if forced to pick one, 45186 is slightly more self-contained, but it should not replace 41797.", + "best_pr_reason": "Neither PR is a global best duplicate candidate because they are unrelated model-integration PRs rather than alternate solutions to the same problem.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different models and different added files; shared registry/docs changes are incidental and do not indicate the same underlying change." + "reason": "Shared boilerplate for model registration/docs is incidental; the PRs add different models with different configs, processors, modeling code, and tests, so they do not fix the same underlying bug/change." } ] }, @@ -16424,12 +16430,12 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "833b3bb5774ffcdc5d622d65b0773fbf47a1860314247be4efbcc1126149b0f5", + "prepared_review_unit_hash": "1b52a3839903aacf2d143dbf9bc7cc626d09c592886d9dc7a23c7e49cace8e78", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, + "serialized_chars": 5935, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -16437,7 +16443,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, + "serialized_chars": 5935, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -16446,18 +16452,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two workflow-maintenance PRs that overlap in CI files but target different action upgrades; they are related, not duplicates.", - "confidence": 0.89, + "summary": "These are related only at a broad maintenance level: both update GitHub Actions versions, but they target different action families and different upgrade goals. They should not be deduplicated.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 has the clearest single objective: upgrading GitHub Actions to Node 24-compatible versions across workflows.", + "canonical_pr_reason": "PR 42975 is the broader and more specific workflow-maintenance change: it explicitly targets Node 24 compatibility and updates many GitHub Actions usages across workflows.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the best representative because its purpose is explicit and cohesive, whereas PR 42976 is a more generic latest-version bump with different action targets.", + "best_pr_reason": "PR 42975 is the best representative of the cluster because it covers the main GitHub Actions compatibility upgrade theme more comprehensively than PR 42976, which is a separate action-version bump focused on docker/build-push-action and a few related workflows.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "They both touch GitHub Actions workflows, but one is a Node 24 compatibility sweep and the other is a separate latest-version update for build/docker actions; they are not the same underlying change and would not naturally merge into one PR." + "reason": "Both PRs update workflow action versions, but they change different actions and solve different upgrade needs. PR 42975 is about Node 24 compatibility for multiple actions; PR 42976 is about bumping docker/build-push-action and similar workflow dependencies. They are not the same concrete fix and would not plausibly be merged into one PR." } ] }, @@ -16496,76 +16502,76 @@ "pull_request:43451|pull_request:45490", "pull_request:45490|pull_request:45630" ], - "prepared_review_unit_hash": "19627c2b09276ef4bc366f7cd0c34090dff12c87fa5100f4f99b1e5a7eb717ee", + "prepared_review_unit_hash": "82bc1568491a1571e6796e975027e0581ccf49ebd7fc949a99843cca377e319b", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 7, - "serialized_chars": 17616, - "estimated_input_tokens": 4404, - "estimated_eval_tokens": 9064 + "serialized_chars": 17617, + "estimated_input_tokens": 4405, + "estimated_eval_tokens": 9066 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 7, - "serialized_chars": 17616, - "estimated_input_tokens": 4404, - "estimated_eval_tokens": 9064 + "serialized_chars": 17617, + "estimated_input_tokens": 4405, + "estimated_eval_tokens": 9066 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All candidate links are false positives: these PRs add different models (ViT NEPA, Molmo, Molmo2, CTSM, Kimi2_6) and do not fix the same underlying bug or change.", - "confidence": 0.98, + "summary": "All five items are separate model-addition pull requests for different models (ViT NEPA, Molmo, Molmo2, CTSM, Kimi2_6). They share only boilerplate integration files and docs patterns, not the same underlying change or code path.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the cluster contains separate model-addition PRs for different architectures and code paths, so they are not duplicates.", + "canonical_pr_reason": "If one PR must represent the cluster, 43451 (Molmo2) is the most complete standalone integration, with the broadest implementation surface (modeling, processing, docs, tests, and auto-mapping updates).", "best_issue_reason": null, - "best_pr_reason": "No best PR for deduping purposes; each PR is a distinct model introduction with its own files, tests, and implementation.", + "best_pr_reason": "43451 is the strongest representative for triage because it is the most substantive single integration; the others are distinct model ports and should not be collapsed into it.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model additions: ViT NEPA vs Molmo. Shared docs/auto-registry changes are broad integration work, not the same concrete change." + "reason": "Different models and different change goals: ViT NEPA vs Molmo. Shared auto/docs wiring is boilerplate, not the same bug or feature." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model additions: ViT NEPA vs Molmo2. They touch similar registry/docs files but implement separate architectures and code paths." + "reason": "Different model integrations (ViT NEPA vs Molmo2). They touch some of the same framework files, but the concrete code paths and artifacts are unrelated." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "Different model additions: ViT NEPA vs CTSM. No indication they fix the same bug or could be merged into one PR." + "reason": "ViT NEPA and CTSM are distinct model additions with no evidence of a shared underlying fix or mergeable single change." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related by name but are distinct model implementations with different files, tests, and interfaces." + "reason": "Molmo and Molmo2 are separate model ports. Similar filenames only reflect shared registration/docs scaffolding, not duplicate work." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo vs CTSM are unrelated model additions; overlap is only in shared registry/docs plumbing." + "reason": "Molmo and CTSM are unrelated integrations; they do not fix the same concrete problem or overlap beyond generic framework registration." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 vs CTSM are separate model additions and do not appear to address the same concrete code-path problem." + "reason": "Molmo2 and CTSM are different model additions with distinct implementations and tests, so they should not be merged as duplicates." }, { "left": "pull_request:45490", "right": "pull_request:45630", "accept": false, - "reason": "CTSM vs Kimi2_6 are different model additions. Despite both being time-series-oriented integrations, they are not the same underlying change." + "reason": "CTSM and Kimi2_6 are separate model additions; shared auto/modeling file edits are broad subsystem overlap, not the same code-path change." } ] }, @@ -16603,7 +16609,7 @@ "pull_request:43665|pull_request:45749", "pull_request:44815|pull_request:45747" ], - "prepared_review_unit_hash": "44d360cfe1a7980c2747786ec2c25c723d634346919ce6f373a5a2b1cc9bb4e0", + "prepared_review_unit_hash": "94fc491d0cc10075d0bbae640e0eb4346224bae0e8255efe481e77302e21284b", "component_budget": { "node_count": 5, "item_count": 5, @@ -16625,48 +16631,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are mostly unrelated: one substantive FP8 dequantization fix, two test-focused patches on different models, one title-only placeholder for batch size, and one docstring typo fix. No pair looks like the same underlying bug/change, so I rejected all soft edges.", - "confidence": 0.89, + "summary": "These PRs are not duplicates: they span unrelated areas (Whisper decoding/tests, CLIP/ViT test edits, FP8 dequant/model-loading, continuous batching docs, and an unrelated split-batch-size fix). The only substantive code change is the FP8/dequant PR; the others look like test-only or cosmetic changes, or lack enough evidence to connect them to the same bug/change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44815 is the strongest canonical PR because it contains a real code-path fix across model loading and FP8 quantization logic, with supporting test/model changes.", + "canonical_pr_reason": "PR 44815 is the strongest representative because it makes the only clearly substantive production-code changes across multiple source files and includes a real bug-fix theme (FP8/dequant/model loading), unlike the others which are test-only, cosmetic, or too underspecified.", "best_issue_reason": null, - "best_pr_reason": "PR 44815 is the best overall representative of the cluster since it is substantive and technically grounded, unlike the test-placeholder or typo-only PRs.", + "best_pr_reason": "PR 44815 is the best standalone PR in the set: it has concrete code-path changes, touches relevant runtime files, and appears to address an actual functional issue rather than test noise or a spelling/doc cleanup.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Both are test-oriented, but they target different model areas and the diffs do not indicate the same bug or mergeable change." + "reason": "Both are labeled as fixes, but they target different models and different kinds of changes: Whisper tokenizer/runtime behavior versus CLIP/ViT test edits. No shared code path or same underlying bug is evident." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper tokenizer/test changes are unrelated to the FP8 dequantization and loading fix." + "reason": "Whisper decoding/tokenization changes are unrelated to FP8 dequant/model-loading fixes. Different subsystems, different failure modes." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "One is a vague test-only patch across CLIP/ViT, the other is a concrete FP8 dequantization fix; they do not share the same underlying change." + "reason": "This is test-only CLIP/ViT churn versus a concrete FP8/runtime bug fix. They do not look like the same underlying change and would not plausibly merge as one PR." }, { "left": "pull_request:43665", "right": "pull_request:45747", "accept": false, - "reason": "No evidence of the same bug: one is test edits, the other is a separate batch-size fix with no overlapping code path shown." + "reason": "The CLIP/ViT test edits are unrelated to a split-batch-size fix; no shared code path or concrete bug is visible." }, { "left": "pull_request:43665", "right": "pull_request:45749", "accept": false, - "reason": "Test edits and a docstring spelling correction are clearly different changes." + "reason": "Test-file edits in vision models and a docstring spelling correction in continuous batching are clearly separate cosmetic changes." }, { "left": "pull_request:44815", "right": "pull_request:45747", "accept": false, - "reason": "FP8 dequantization/loading logic is unrelated to split batch size handling." + "reason": "FP8 dequant/model-loading work is unrelated to an unspecified split-batch-size PR; there is not enough evidence of the same bug or change." } ] }, @@ -16696,12 +16702,12 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "e5408c108ce40d7c0b735cbf6c3b779085207ab8b62f0e41f31e838348017a4b", + "prepared_review_unit_hash": "237bb86038e7c63be626a66b75af36fe9c836a44964ecd16a4db74503714532b", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4563, + "serialized_chars": 4562, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -16709,7 +16715,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4563, + "serialized_chars": 4562, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -16718,18 +16724,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two pull requests are not duplicates: one is a small repo-bot/version-format test tweak, while the other changes CI/workflow behavior and several test/support files. The shared Vit test file is incidental, not evidence of the same underlying change.", - "confidence": 0.95, + "summary": "These two open PRs are not duplicates: one is a setup/version-bump + test dependency change, while the other is a workflow/testing-utils change around CI/comment handling. They only overlap on a shared Vit test file, which is not enough to indicate the same underlying fix.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43532 is the better canonical PR because it represents the broader functional change set (workflow and test/support updates), whereas PR 43488 is a narrow [don't merge] bot-format check patch.", + "canonical_pr_reason": "PR #43532 is the broader and more representative change in this pair, but it is not a duplicate of #43488; the two PRs address different code paths and should not be merged into one canonical change.", "best_issue_reason": null, - "best_pr_reason": "PR 43532 is the best overall representative of the cluster since it is the more substantial and concrete code-path change; PR 43488 is clearly a throwaway validation PR.", + "best_pr_reason": "PR #43532 is the better standalone representative of the cluster because it contains the more substantial multi-file behavior change, whereas #43488 looks like a narrow bot/version-format check.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Reject: the PRs target different problems. 43488 is a repo-bot/versioning placeholder with a dependency/version bump and Vit test tweak, while 43532 rewrites CI workflow behavior and related testing/notification code. Shared filenames do not make them the same change." + "reason": "Reject: the diffs touch different concerns. #43488 updates setup/versioning and test dependencies, while #43532 rewires GitHub workflows and testing utilities. A shared test filename alone does not mean they fix the same concrete bug or should be merged together." } ] }, @@ -16759,7 +16765,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "79cfb8dc0f18820c443f8e7c75c5a089b464be3b42358f200fb9710c8ba73aa3", + "prepared_review_unit_hash": "9eb3f17e054b4dc20d017e73b3ab71edafbb818b76396ba5a1f9d957eec25c1f", "component_budget": { "node_count": 2, "item_count": 2, @@ -16781,18 +16787,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate feature PRs for different pipelines: promptable concept segmentation vs promptable visual segmentation. They overlap in documentation and pipeline registration plumbing, but they do not fix the same code-path problem and should not be merged as duplicates.", + "summary": "Two separate PRs add adjacent but distinct pipeline features: one for Promptable Concept Segmentation and one for Promptable Visual Segmentation. They share scaffolding and docs plumbing, but they target different tasks and model integrations, so they should not be deduplicated.", "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43613 is the broader/more general-seeming feature addition, with more model coverage and related pipeline/docs wiring, so it is the better representative of the cluster if one must be chosen.", + "canonical_pr_reason": "No single canonical PR: these are parallel feature additions for different segmentation tasks, not the same underlying change.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the better standalone candidate because it has the broader implementation surface and appears more complete, but it is still a distinct feature from PR 43612 rather than a duplicate.", + "best_pr_reason": "Neither PR is a true duplicate of the other. If forced to pick a representative, PR #43613 is slightly broader in model/test coverage, but it still represents a different feature than PR #43612.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different pipeline features with different target tasks and codepaths. Shared docs/registry changes are not enough to treat them as the same underlying change, and they would not plausibly be merged into one PR as a duplicate." + "reason": "Both add segmentation-related pipelines and share some docs/metadata files, but they implement different concrete features with different pipeline names, model backends, and test suites. They are related, not the same underlying change." } ] }, @@ -16822,7 +16828,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "63d7291c582e251f6bd1654e87978462f32b28e149025086e987671ddd5357e5", + "prepared_review_unit_hash": "67fee8ffee0ab63772978e41931e57141d029424ac932c4f6dd74874efe22a6e", "component_budget": { "node_count": 2, "item_count": 2, @@ -16844,18 +16850,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both items are trainer.py extension points, but they address different behaviors: one changes gradient-accumulation loss scaling, the other factors out model signature column filtering. They are related in scope but not duplicates and should not be merged into one PR.", - "confidence": 0.96, + "summary": "The two open PRs both touch trainer.py and add extension hooks, but they address different behaviors: gradient-accumulation loss scaling vs. signature-column filtering. They should not be treated as duplicates.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No single canonical PR: 43651 adds a GA-loss-scaling hook, while 43663 adds a signature-column override hook; they solve separate trainer extensibility problems.", "best_issue_reason": null, - "best_pr_reason": "Neither PR is a clear duplicate of the other. PR 43651 targets loss scaling semantics during training_step; PR 43663 targets input column filtering/signature inspection. They modify separate code paths and solve different customization needs.", + "best_pr_reason": "If a representative is needed, 43651 is slightly more central because it changes the core training-step loss-scaling path, but it is still not a substitute for 43663.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Same file and similar helper-refactor pattern, but the underlying changes are unrelated: one controls gradient accumulation loss normalization, the other exposes signature-column computation for data filtering. They would not plausibly be merged as one fix." + "reason": "Different underlying changes and code paths: 43651 controls loss normalization during gradient accumulation, while 43663 exposes signature-column filtering for model inputs. They are related only by file/subsystem, not by the same bug or fix." } ] }, @@ -16887,7 +16893,7 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "45effb71b6adb505078630f2524ec3c91c754929b90939d1fd6ae0b7af8a8b64", + "prepared_review_unit_hash": "27686481e71678a329faa06c384b48a860f2015dc3f059bcc1987fa7c8a071be", "component_budget": { "node_count": 3, "item_count": 3, @@ -16909,33 +16915,33 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "PRs #43836 and #43842 both target the TypeAdapter NameError in `src/transformers/cli/serve.py` and are plausible variants of the same fix. PR #43656 is less clearly part of that bug: its explicit issue target is different and the diff reads more like a broader `from __future__ import annotations`/typing cleanup than a direct TypeAdapter fix.", - "confidence": 0.72, + "summary": "All three PRs target the same CLI serve.py TypeAdapter annotation NameError class of bug; 43842 is the most focused fix, while 43656 is a similar variant and 43836 appears to include the same fix alongside broader cleanup/refactor work.", + "confidence": 0.81, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43842 is the clearest and most focused representation of the cluster: it explicitly describes the TypeAdapter NameError path, stays tightly scoped to the relevant annotation fix, and has the smallest, most direct diff.", + "canonical_pr_reason": "PR 43842 is the clearest, most narrowly scoped fix for the concrete TypeAdapter NameError when pydantic is absent; it directly addresses the runtime annotation problem in serve.py with minimal unrelated churn.", "best_issue_reason": null, - "best_pr_reason": "PR #43842 is the best overall representative because it most directly matches the concrete runtime bug without extra refactoring or broader typing churn.", + "best_pr_reason": "PR 43842 best represents the cluster because it fixes the exact NameError path with the smallest, most explicit change set and is easiest to reason about as the canonical duplicate target.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", - "accept": false, - "reason": "This is not conservative enough to merge: #43656 has a different explicit issue target and its diff is broader typing/`__future__` cleanup rather than a direct fix for the same TypeAdapter NameError path." + "accept": true, + "reason": "Both PRs fix the same runtime TypeAdapter annotation NameError in src/transformers/cli/serve.py; the edits are different implementations of the same underlying bug and could plausibly be merged into one fix." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both PRs are aimed at the same concrete TypeAdapter NameError in `serve.py` and share the same file and issue target, so they plausibly describe the same underlying fix despite different implementation styles." + "reason": "Despite 43836 showing broader file churn, its title and touched file indicate the same TypeAdapter string-literal/annotation NameError fix in the same code path, so it is close enough to treat as the same underlying change." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster summary is a bit too strong for the packet. PR #43836 and #43842 are plausibly about the same issue target and same file, but #43656 is not well grounded as the same TypeAdapter bug: its explicit issue target is different, and the shown diff is a broader `from __future__ import annotations`/typing cleanup rather than a direct TypeAdapter fix. Because of that, the soft-edge verdict for 43656\u219443842 overstates the evidence and is not conservative enough." + "accept": true, + "feedback": "The cluster summary is adequately grounded in the packet: all three PRs touch the same file and are tied by titles/diffs to TypeAdapter/annotation NameError fixes in `serve.py`, with 43836 clearly broader than 43842. The soft-edge accepts are conservative enough, especially since 43836 and 43842 share an issue target and 43656 is at least plausibly the same annotation-related bugfix family." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17122,118 +17128,118 @@ "pull_request:44044|pull_request:44154", "pull_request:44024|pull_request:44076" ], - "prepared_review_unit_hash": "4eb2f6d25a010f67e4bdeb902e3b34409c756080018ac5c8cb54d0dd5f9db8a6", + "prepared_review_unit_hash": "f3eb77e844e532f8eef743d71efd201a378d2630cb18b6cfdc66cda45021a458", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 77, - "serialized_chars": 84507, - "estimated_input_tokens": 21127, - "estimated_eval_tokens": 42510 + "serialized_chars": 84498, + "estimated_input_tokens": 21125, + "estimated_eval_tokens": 42506 }, "budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 72, - "serialized_chars": 76941, - "estimated_input_tokens": 19236, - "estimated_eval_tokens": 38728 + "serialized_chars": 76931, + "estimated_input_tokens": 19233, + "estimated_eval_tokens": 38722 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a refactor-theme cluster around standardized output tracing, not one single duplicate PR set. I\u2019d keep same-model variants together, but treat cross-model refactors as separate changes.", - "confidence": 0.92, + "summary": "The packet contains two separate duplicate subclusters, not one: a GPT-J/CodeGen family centered on 44722, and a distinct GPT-Neo pair around 44018/44068. Most other PRs are model-specific output-tracing refactors and should stay separate.", + "confidence": 0.82, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the best canonical representative here: it has the umbrella issue link, a concrete output-tracing refactor, and it covers the core GPT-J/CodeGen path rather than only a tiny follow-up.", + "canonical_pr_reason": "44722 is the best canonical PR for the GPT-J/CodeGen subcluster because it spans both model files, explicitly targets the tracking issue, and is the broadest overlapping implementation. The GPT-Neo duplicates form a separate family and should not be folded into this canonical choice.", "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the strongest standalone representative of the cluster\u2019s main refactor pattern; the rest are mostly model-specific ports of the same broader initiative.", + "best_pr_reason": "44722 is the strongest single PR in the packet, but only for the GPT-J/CodeGen family; 44068 is the better representative for the separate GPT-Neo family.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different models/files (CVT/FNet vs GPT-J); same umbrella issue alone is not enough." + "reason": "Different model families and code paths; same output-tracing theme is too broad." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Separate model refactors in different code paths; not the same concrete change." + "reason": "Different backbones and implementations; not the same concrete change." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both target the GPT-J output-tracing refactor in the same file; this looks like the same underlying change/version." + "reason": "Both are GPT-J output-tracing refactors on the same code path and could plausibly be merged into one PR." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet/ResNet vs EfficientNet are different model implementations, so this is not one duplicate change." + "reason": "RegNet/ResNet-style tracing work vs EfficientNet are unrelated model paths." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet output tracing and GPT-J/CodeGen output tracing are unrelated code paths." + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated implementations." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen vs EfficientNet; only the refactor theme matches, not the concrete change." + "reason": "GPT-J/CodeGen and EfficientNet are different code paths." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTaV2 are separate model refactors." + "reason": "MobileNetV2 and DeBERTa are unrelated models." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen output tracing vs MGP-STR output tracing; different model code paths." + "reason": "GPT-J and MGP-STR are unrelated model code paths." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Both are GPT-Neo output-tracing refactors on the same file set; they appear to be the same underlying change." + "reason": "Same GPT-Neo output-tracing refactor on the same file; these look like duplicate/superset variants." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen vs MPT; same pattern, but not the same model bug/change." + "reason": "GPT-J/CodeGen and MPT are different models; shared decorator migration is not enough." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are distinct model refactors." + "reason": "GPT-J/CodeGen and GPT-Neo are separate model families." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen; too broad to be duplicates." + "reason": "GPT-Neo and GPT-J/CodeGen are different concrete code paths." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet output tracing is unrelated to GPT-J/CodeGen." + "reason": "ResNet and GPT-J/CodeGen are unrelated changes." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are different model paths." + "reason": "MGP-STR and GPT-J/CodeGen are unrelated models." }, { "left": "pull_request:44019", @@ -17245,139 +17251,157 @@ "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are different changes entirely." + "reason": "GPT-Neo and ResNet are unrelated models." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet vs MPT; same refactor style, not the same code path." + "reason": "ResNet and MPT are unrelated code paths." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are separate model-specific refactors." + "reason": "GPT-Neo and Flaubert/XLM are unrelated models." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model implementations." + "reason": "GPT-Neo is a separate duplicate family from GPT-J/CodeGen." }, { "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo vs Flaubert/XLM; not the same underlying bug." + "reason": "GPT-Neo and Flaubert/XLM are unrelated." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are unrelated model paths." + "reason": "MPT and GPT-J/CodeGen are unrelated models." }, { "left": "pull_request:44018", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are different models and changes." + "reason": "GPT-Neo and MGP-STR are unrelated." }, { "left": "pull_request:44018", "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo vs GPT-J; not a duplicate even though both are output-tracing refactors." + "reason": "GPT-Neo and GPT-J are different code paths." }, { "left": "pull_request:44068", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are separate model refactors." + "reason": "GPT-Neo and MGP-STR are unrelated models." }, { - "left": "pull_request:44098", - "right": "pull_request:44101", + "left": "pull_request:44071", + "right": "pull_request:44085", "accept": false, - "reason": "ViLT and Flaubert/XLM are distinct implementations." + "reason": "MPT and GPT-J are unrelated." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-2 and MGP-STR are unrelated model code paths." + "reason": "GPT-2 and MGP-STR are unrelated." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J output tracing vs MGP-STR output tracing; different models." + "reason": "GPT-J and MGP-STR are unrelated model paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44073", + "left": "pull_request:44098", + "right": "pull_request:44101", "accept": false, - "reason": "RegNet and VisualBERT are different model families." + "reason": "ViLT and Flaubert/XLM are unrelated." }, { - "left": "pull_request:44056", - "right": "pull_request:44101", + "left": "pull_request:44059", + "right": "pull_request:44722", "accept": false, - "reason": "MPNet and Flaubert/XLM are unrelated model refactors." + "reason": "GPT-2 and GPT-J/CodeGen are unrelated models." }, { "left": "pull_request:44018", - "right": "pull_request:44059", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo vs GPT-2 are separate implementations." + "reason": "GPT-Neo and MPT are unrelated implementations." }, { - "left": "pull_request:44073", + "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "VisualBERT and LongT5 are not the same code-path change." + "reason": "SegFormer and LongT5 are unrelated models." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert and Flaubert/XLM are different code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 and MPT are unrelated models." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are unrelated." }, { - "left": "pull_request:44101", + "left": "pull_request:44073", "right": "pull_request:44161", "accept": false, - "reason": "Flaubert/XLM and LongT5 are different model refactors." + "reason": "VisualBert and LongT5 are unrelated." }, { "left": "pull_request:43997", "right": "pull_request:44017", "accept": false, - "reason": "RegNet and SegFormer are different architectures." + "reason": "RegNet and SegFormer are different backbones." }, { "left": "pull_request:43997", "right": "pull_request:44056", "accept": false, - "reason": "RegNet and MPNet are unrelated changes." + "reason": "RegNet and MPNet are unrelated." }, { "left": "pull_request:44071", "right": "pull_request:44076", "accept": false, - "reason": "MPT and ImageGPT are different model paths." + "reason": "MPT and ImageGPT are unrelated model implementations." }, { "left": "pull_request:44074", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert/XLM are separate model implementations." + "reason": "TextNet and Flaubert/XLM are unrelated." }, { "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "MPNet and LongT5 are unrelated model-specific refactors." + "reason": "MPNet and LongT5 are unrelated." }, { "left": "pull_request:43997", "right": "pull_request:44018", "accept": false, - "reason": "RegNet and GPT-Neo are not the same underlying change." + "reason": "RegNet and GPT-Neo are unrelated model code paths." }, { "left": "pull_request:43997", @@ -17386,109 +17410,103 @@ "reason": "RegNet and LongT5 are unrelated." }, { - "left": "pull_request:44074", - "right": "pull_request:44161", + "left": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "TextNet and LongT5 are different model refactors." + "reason": "MPT and SpeechT5 are unrelated." }, { "left": "pull_request:43997", "right": "pull_request:44071", "accept": false, - "reason": "RegNet and MPT are distinct implementations." + "reason": "RegNet and MPT are unrelated." }, { "left": "pull_request:44010", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBERT and MPT are unrelated code paths." + "reason": "SqueezeBERT and MPT are unrelated." }, { "left": "pull_request:44010", "right": "pull_request:44073", "accept": false, - "reason": "SqueezeBERT and VisualBERT are different model changes." + "reason": "SqueezeBERT and VisualBert are unrelated." }, { "left": "pull_request:44018", "right": "pull_request:44129", "accept": false, - "reason": "GPT-Neo and SpeechT5 are separate model-specific refactors." + "reason": "GPT-Neo and SpeechT5 are unrelated." }, { - "left": "pull_request:44071", - "right": "pull_request:44129", + "left": "pull_request:44074", + "right": "pull_request:44161", "accept": false, - "reason": "MPT and SpeechT5 are unrelated implementations." + "reason": "TextNet and LongT5 are unrelated." }, { - "left": "pull_request:43996", - "right": "pull_request:44161", + "left": "pull_request:43997", + "right": "pull_request:44074", "accept": false, - "reason": "CVT/FNet and LongT5 are different model code paths." + "reason": "RegNet and TextNet are unrelated." }, { - "left": "pull_request:43996", - "right": "pull_request:44017", + "left": "pull_request:43997", + "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet and SegFormer are separate model refactors." + "reason": "RegNet and SpeechT5 are unrelated." }, { "left": "pull_request:44010", - "right": "pull_request:44044", + "right": "pull_request:44018", "accept": false, - "reason": "SqueezeBERT and DeBERTaV2 are different models." + "reason": "SqueezeBERT and GPT-Neo are unrelated." }, { - "left": "pull_request:44044", - "right": "pull_request:44074", + "left": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "DeBERTaV2 and TextNet are unrelated changes." + "reason": "MPT and SpeechT5 are unrelated." }, { - "left": "pull_request:44066", - "right": "pull_request:44722", - "accept": true, - "reason": "Both are GPT-J/CodeGen standardized output-tracing refactors on the same core files; plausibly one change set." - }, - { - "left": "pull_request:44085", - "right": "pull_request:44722", - "accept": true, - "reason": "Same GPT-J output-tracing refactor family, overlapping file and identical underlying code-path change." + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are unrelated." }, { - "left": "pull_request:44085", - "right": "pull_request:44129", + "left": "pull_request:43996", + "right": "pull_request:44017", "accept": false, - "reason": "GPT-J and SpeechT5 are different model implementations." + "reason": "CVT/FNet and SegFormer are different backbones." }, { - "left": "pull_request:44044", - "right": "pull_request:44129", + "left": "pull_request:44010", + "right": "pull_request:44044", "accept": false, - "reason": "DeBERTaV2 and SpeechT5 are unrelated refactors." + "reason": "SqueezeBERT and DeBERTa are unrelated models." }, { "left": "pull_request:44044", - "right": "pull_request:44154", + "right": "pull_request:44074", "accept": false, - "reason": "DeBERTaV2 and ViTS are different model code paths." + "reason": "DeBERTa and TextNet are unrelated." }, { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "FocalNet and ImageGPT are distinct model-specific changes." + "reason": "FocalNet and ImageGPT are unrelated model implementations." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The canonical/representative PR choice is supported by the shared issue target and the broad GPT-J/CodeGen scope. The accepted soft pairs are all within the same model family and look mergeable as variants of the same output-tracing fix, while the rejected cross-model pairs are appropriately cautious." + "accept": false, + "feedback": "The pair-level verdicts are mostly conservative, but the cluster summary overstates the evidence. The packet supports two separate duplicate subclusters: GPT-J/CodeGen (44066, 44085, 44722) and GPT-Neo (44018, 44068). Saying there is \u201conly real duplicate family\u201d and collapsing GPT-J/GPT-Neo into one family is not grounded. 44722 is a plausible canonical PR for the GPT-J/CodeGen subcluster, but the overall summary should acknowledge the second GPT-Neo duplicate pair as well." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17520,20 +17538,20 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "473e37e275fed4fb5f566b9e7e5c4e3f6bba24d3d02f5955ad3b788be7e68e32", + "prepared_review_unit_hash": "6a2ba859ba3645c59dd92b1424f0673e181fb14fc8ce0774852f9dfad307c8a8", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 77, - "serialized_chars": 84507, - "estimated_input_tokens": 21127, - "estimated_eval_tokens": 42510 + "serialized_chars": 84498, + "estimated_input_tokens": 21125, + "estimated_eval_tokens": 42506 }, "budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 5, - "serialized_chars": 13066, + "serialized_chars": 13067, "estimated_input_tokens": 3267, "estimated_eval_tokens": 6790 }, @@ -17542,42 +17560,42 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs are all thematically similar standardized output-tracing refactors, but they target different model code paths, so they are not duplicates of one another.", - "confidence": 0.93, + "summary": "All items are model-specific PRs that migrate different architectures to the same output-tracing/capture pattern, but they are not duplicates of one another; they touch different code paths and would not be merged into a single PR.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44129 is the strongest representative because it has an explicit issue target and a concrete SpeechT5-specific refactor, but it is still a separate change from the others.", + "canonical_pr_reason": "PR 44129 is the strongest representative because it has an explicit issue target and a clearly scoped refactor to standardized output capture.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the best standalone PR in this set because it is the most clearly scoped and anchored to an explicit issue, with a concrete model-specific implementation change.", + "best_pr_reason": "PR 44129 best captures the cluster theme while remaining a concrete, self-contained change.", "soft_edge_verdicts": [ { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Both are output-tracing refactors, but for different models (VisualBert vs TextNet) and different code paths; they are not the same underlying change." + "reason": "Same refactor pattern, but different models and files; these are separate model-specific changes, not one concrete bug fix." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Both migrate output tracing, but MPNet and VisualBert are separate implementations with different capture targets and forward logic." + "reason": "Both standardize output tracing, but MPNet and VisualBert have distinct implementations and code paths; too broad to merge as duplicates." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Shared refactor theme only; MPNet and TextNet are distinct model-specific changes, not one mergeable fix." + "reason": "Shared helper migration theme only; the PRs modify different model internals and are not the same underlying change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model implementations; the similarity is only that both update output collection patterns." + "reason": "RegNet and SqueezeBert are unrelated model implementations; similar decorator/capture refactors do not make them duplicates." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 are different model code paths and the PRs address separate refactors, so they should not be merged as duplicates." + "reason": "Different architectures and different forward paths; the overlap is only in output-tracing cleanup, not the same fix." } ] }, @@ -17657,268 +17675,274 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "29ed07c83835df780eae2baff078f5ec37311201256ae9cf95a7715cbb6dfa66", + "prepared_review_unit_hash": "5d987a5a3454e225355b4972891993c9df239f47f625858a8e17c6f269882b55", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40170, - "estimated_input_tokens": 10043, - "estimated_eval_tokens": 20342 + "serialized_chars": 40176, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40170, - "estimated_input_tokens": 10043, - "estimated_eval_tokens": 20342 + "serialized_chars": 40176, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are all small, model-specific output-tracing refactors, but they target different architectures and code paths. They share a pattern (`can_return_tuple`, `capture_outputs`, signature cleanup), not the same underlying change, so none should be treated as duplicates.", - "confidence": 0.96, + "summary": "These PRs are thematically similar output-tracing refactors, but they target different model implementations and code paths, so they are not duplicates of one another. No issue artifacts are present.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44003 is the best representative anchor: it is a self-contained refactor in a closely related Mamba-family area and introduces the new tracing helpers in a clear, substantive way.", + "canonical_pr_reason": "44025 is the best representative PR in this set: it applies the output-tracing refactor to a model plus its prompt variant, which captures the cluster\u2019s core pattern without being the same change as the other model-specific PRs.", "best_issue_reason": null, - "best_pr_reason": "PR 44003 is the strongest single representative of the cluster because it is a focused, non-test/documentation change with real implementation updates across a tightly related pair of files.", + "best_pr_reason": "44025 is the most suitable cluster representative for triage because it shows the common refactor pattern cleanly and spans a related pair of files, but it still is not a duplicate of the other PRs.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Same tracing-refactor theme, but different models and unrelated implementations; not the same code-path change." + "reason": "Same refactor theme, but different model code paths (`timm_backbone` vs `upernet`); not the same underlying change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Both adjust output handling, but for different architectures with separate forward paths." + "reason": "Both are output-tracing refactors, but they affect unrelated models and forward paths." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Similar decorator/signature cleanup, but one is timm_backbone and the other is UnivNet; distinct changes." + "reason": "Different architectures (`timm_backbone` vs `univnet`) and different forward logic; only the pattern matches." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Shared output-tracing theme only; timm_backbone and Mamba-family are different code paths." + "reason": "`timm_backbone` and `falcon_mamba/mamba` are separate implementations with different output handling, so this is not one duplicate fix." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Both refactor model outputs, but they touch unrelated model implementations and are not mergeable as one PR." + "reason": "Both touch tracing-like behavior, but they are distinct model families and code paths." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated model paths; the refactor pattern is similar but the change is not the same." + "reason": "`mobilenet_v1` and `univnet` are unrelated models; shared refactor wording is not enough to merge them." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files; this is a parallel refactor, not a duplicate change." + "reason": "Different model subsystems and different forward signatures; not the same bug/change." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Both clean up output tracing, but on different depth-related models with separate forward implementations." + "reason": "Both are refactors around output tracing, but they target different model code paths and cannot plausibly be one PR." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "MobileNetV1 vs vision-encoder-decoder; same refactor style, different underlying code." + "reason": "`mobilenet_v1` vs `vision_encoder_decoder` are unrelated implementations; no shared concrete fix." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Different wrapper/model code paths; similar signature cleanup only." + "reason": "Same general refactor pattern, but distinct encoder-decoder wrapper code paths." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-text dual encoder and UnivNet are unrelated; shared tracing vocabulary is not enough." + "reason": "`vision_text_dual_encoder` and `univnet` do not share the same underlying output-tracing bug." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Both are output-tracing refactors, but they change different models and different forward behavior." + "reason": "Different models and different forward implementations; only the refactor theme is shared." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "One is vision-text dual encoder, the other is Mamba-family; different implementation targets." + "reason": "`vision_text_dual_encoder` and `falcon_mamba/mamba` are separate code paths, so they are not duplicates." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "`vision_text_dual_encoder` and `codegen` change different model logic; same broad subsystem does not imply same change." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different architectures and code paths; not the same concrete fix." + "reason": "Both are output-tracing refactors, but they are for different models and different runtime behavior." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are unrelated models; this is only a generic refactor pattern." + "reason": "`univnet` and `upernet` are unrelated model families with distinct output semantics." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Mamba-family vs UnivNet; distinct implementation changes." + "reason": "Different architectures and different forward/capture behavior; not mergeable as one fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "`univnet` and `codegen` touch different code paths and different output shapes." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Both touch output tracing, but they are separate model-specific refactors." + "reason": "Same theme, but the actual change is model-specific and not the same underlying bug." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "`upernet` segmentation forward logic and `codegen` causal LM tracing are different concrete changes." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are different architectures with independent forward paths." + "reason": "`upernet` and `rwkv` do not share the same code path or fix." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Same refactor motif, but not the same bug/change or mergeable code path." + "reason": "Different model internals; the overlap is only in the refactor pattern." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Mamba-family refactor versus SuperPoint; different subsystems and implementations." + "reason": "`falcon_mamba/mamba` and `superpoint` are unrelated implementations and cannot be merged as one PR." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba-family output tracing and CodeGen cache/output cleanup are not the same change." + "reason": "`falcon_mamba/mamba` and `codegen` change different model code paths and output conventions." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen affect unrelated model code paths." - }, - { - "left": "pull_request:44001", - "right": "pull_request:44004", - "accept": false, - "reason": "UnivNet and CodeGen are unrelated; only the generic refactor style matches." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44004", - "accept": false, - "reason": "Different model families and different forward signatures; not duplicates." + "reason": "`timm_backbone` and `codegen` are separate model implementations; not the same underlying fix." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth Anything and VisionEncoderDecoder are separate models; no shared concrete bug." + "reason": "`depth_anything` and `vision_encoder_decoder` share a refactor motif, but they are different model wrappers and different forward code." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different encoder-decoder style changes in unrelated model wrappers." + "reason": "`depth_anything` and `speech_encoder_decoder` are distinct code paths; no single duplicate PR here." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Depth Anything and SuperPoint are distinct code paths; same refactor pattern only." + "reason": "Different models and different output-tracing implementations; not the same bug/change." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures; the output-tracing cleanup is not the same underlying change." + "reason": "`depth_anything` and `rwkv` modify unrelated forward logic." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Depth Anything and DPR are separate model implementations." + "reason": "`depth_anything` and `dpr` are different model families; only the refactor style is similar." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44029", "accept": false, - "reason": "Both are encoder-decoder wrapper PRs, but for different models and files; not the same concrete fix." + "reason": "`vision_encoder_decoder` and `rwkv` are unrelated code paths and not a duplicate fix." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44027", "accept": false, - "reason": "VisionEncoderDecoder and SuperPoint are unrelated changes." + "reason": "Both are encoder-decoder wrappers, but they are different model families and separate changes." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44028", "accept": false, - "reason": "Different model families and different output semantics." + "reason": "`vision_encoder_decoder` and `superpoint` do not share the same underlying code change." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "VisionEncoderDecoder and DPR are separate code paths." + "reason": "Different model implementations and different output semantics; not mergeable as one PR." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "SpeechEncoderDecoder and SuperPoint are unrelated; same cleanup style only." + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated models; same broad tracing theme is insufficient." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different model architectures; not the same fix." + "reason": "Different architectures and different forward paths; not a duplicate." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "SpeechEncoderDecoder and DPR are distinct implementations." + "reason": "`speech_encoder_decoder` and `dpr` change different model code and output handling." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV have unrelated forward paths." + "reason": "`superpoint` and `rwkv` are unrelated model implementations with no shared concrete bug." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different model code and different output plumbing; not duplicates." + "reason": "Different models and different output logic; only the refactor pattern matches." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are separate model families with different changes." + "reason": "`rwkv` and `dpr` are distinct code paths with no evidence of the same underlying change." } ] }, @@ -17951,52 +17975,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "321a4d8c44dbe398711f83f8007bff3a92e6f583985b671a5358cad200b43c36", + "prepared_review_unit_hash": "dc9d3f85e75d98aa8c3e8a257b74d02c72e8deca7bb00a537be74a82e15a48f7", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10913, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10913, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs are independent model-addition changes that share only broad Transformers boilerplate (auto mappings, docs index, registration files). They target different models and codepaths, so they are not duplicates.", - "confidence": 0.97, + "summary": "All three items are separate model-addition PRs for different models (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share Transformers boilerplate and auto-registration files, but they do not describe the same code-path bug or the same feature change, so none are duplicates.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45401 is the best representative because it has an explicit issue target, is model-specific, and includes a focused TTS implementation rather than a generic scaffold.", + "canonical_pr_reason": "No single PR is a true duplicate-canonical candidate because each adds a different model. If one representative must be chosen for the cluster, PR #45075 is the best anchor since it is the most complete/established model-addition PR and also links an explicit issue target.", "best_issue_reason": null, - "best_pr_reason": "PR #45401 is the strongest standalone PR in the cluster: it is tied to a tracking issue and has a clearly scoped feature addition, making it the most suitable canonical representative.", + "best_pr_reason": "PR #45075 is the most representative of the cluster only in the sense that it has the clearest scope and explicit issue linkage; however, it is still not a duplicate of the others because the model, files, and implementation are distinct.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different models (PenguinVL vs Voxtral TTS) with distinct implementations; overlap is limited to common registration/docs files, not the same bug or change." + "reason": "PenguinVL implementation vs Voxtral TTS support are unrelated model additions. Shared docs/auto-registry files are expected boilerplate, not evidence of the same underlying change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model additions for unrelated architectures; shared auto/config/docs plumbing is boilerplate and does not indicate one underlying change." + "reason": "Both are model implementation PRs, but for different models with different configs, processors, and tests. They do not fix or add the same concrete code path." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are separate model integrations with different codepaths and tests; they cannot plausibly be merged as one PR." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model integrations. Overlap in shared registration and documentation files is too broad to treat them as the same PR." } ] }, @@ -18026,12 +18050,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "53be1a6327c1f9fab50056fe0557019ca11aabf0fdf4aa6daa4743923a92c21e", + "prepared_review_unit_hash": "78d8311b9302eff1d60754b0ae5793baaa0313470dc9281a558135942402c868", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4407, + "serialized_chars": 4408, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18039,7 +18063,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4407, + "serialized_chars": 4408, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -18048,18 +18072,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are about fusion, but they target different layers: #44979 introduces a low-level Module Fusion API, while #45363 wires up KernelConfig-based n-to-1 kernel fusion and related integration points. They are related work, not the same concrete change.", - "confidence": 0.84, + "summary": "Related but distinct PRs: one adds a generic module-fusion API, while the other implements KernelConfig-driven n-to-1 kernel fusion plus integration plumbing and an example. They overlap conceptually, but they are not the same underlying change.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "#44979 is the more direct representative of the shared topic because it introduces the core Module Fusion API itself; #45363 is a broader consumer/integration PR built around kernel fusion and additional plumbing.", + "canonical_pr_reason": "45363 is the clearer representative of the set because it delivers the concrete KernelConfig-based fusion workflow and integration points, whereas 44979 is broader foundational API scaffolding.", "best_issue_reason": null, - "best_pr_reason": "#44979 is the best standalone representative for this cluster because it defines the foundational fusion API rather than a specific integration example.", + "best_pr_reason": "45363 is the most end-user-facing and concrete PR here: it wires fusion through model loading, integration helpers, and a working example, so it best summarizes the cluster theme.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Reject: the PRs are related but not duplicates. #44979 adds a generic Module Fusion API, while #45363 implements KernelConfig-driven n-to-1 kernel fusion and integration changes across different files/code paths. They could not plausibly be merged as one identical fix/change." + "reason": "Reject: 44979 introduces a generic module-fusion API, while 45363 adds a specific n-to-1 kernel-fusion implementation via KernelConfig and related integration code. Similar area, but not the same concrete change and not plausibly one merged PR." } ] }, @@ -18089,12 +18113,12 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "266dd4ee93a82b53da34f7f15e139f76f09d04e548f803cba8d7e77776bb043d", + "prepared_review_unit_hash": "e3005195c7cb66424c7400ec40f5a0b8b77ef2a654964c71948c34c7f431d8ce", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4414, + "serialized_chars": 4413, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18102,7 +18126,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4414, + "serialized_chars": 4413, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -18111,18 +18135,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests implement the same Mistral regex patch in the same file; 45317 is the more complete version because it adds test coverage. They look like duplicate PRs for the same underlying fix.", + "summary": "Both pull requests fix the same _patch_mistral_regex AttributeError in the Mistral tokenizer patch path and target the same issue; 45317 is the more complete variant with tests.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "45317 is the better canonical PR because it contains the same code fix as 45086 plus accompanying tests, making it the more complete and merge-ready change.", + "canonical_pr_reason": "PR 45317 is the better canonical representative because it contains the same core fix as 45086 plus a test update and a clearer, more specific title.", "best_issue_reason": null, - "best_pr_reason": "45317 is the best representative PR for the cluster: same fix, same target issue, and it includes tests that validate the AttributeError fix.", + "best_pr_reason": "PR 45317 is the strongest overall representative of the cluster: same bug fix, same file, and it includes validation coverage.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same code-path fix in tokenization_utils_tokenizers.py for _patch_mistral_regex; 45317 is essentially the tested superset of 45086, so they can plausibly be merged as one PR." + "reason": "Same concrete AttributeError fix in _patch_mistral_regex on the same code path; 45317 is essentially the tested refinement of 45086, so these look mergeable into one PR." } ] }, @@ -18152,7 +18176,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "194c0df03eed165d872b6b2546e41e25a3e6c34e4aa4a8d509cf58fbb9cddb38", + "prepared_review_unit_hash": "16032a8c74bdf26305b4cbf8ec8470130c8855d0e81db4387316ee16bd694695", "component_budget": { "node_count": 2, "item_count": 2, @@ -18174,18 +18198,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs concern NemotronH, but they target different scopes: #45115 is a narrow refactor around inheritance/conversion mapping, while #45569 is a broader model-splitting and documentation update for NemotronH dense/sparse variants. They overlap in shared NemotronH files, but they are not the same underlying change.", - "confidence": 0.93, + "summary": "Both pull requests are about NemotronH model refactoring, but they target different concrete changes: one is a conversion/mapping and inheritance cleanup, the other introduces separate dense/sparse model implementations and docs updates. They are related, but not the same underlying change set.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "#45569 is the broader, more complete NemotronH change set and best represents the overall modeling update, including the new dense/sparse variants and the dispatcher/docs work.", + "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the broader, more complete NemotronH restructuring: it adds the dedicated dense/sparse model split plus auto-mapping, docs, and tests, while 45115 is a narrower conversion/inheritance refactor.", "best_issue_reason": null, - "best_pr_reason": "#45569 is the best representative PR because it covers the full architecture change and model organization, whereas #45115 is a narrower refactor focused on conversion/mapping and inheritance details.", + "best_pr_reason": "PR 45569 is the best overall PR candidate for this cluster because it represents the main user-facing architecture change and subsumes more of the NemotronH work than the narrower mapping-focused PR.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Overlap is only at the subsystem/file level (NemotronH core modules). #45115 is a refactor/inheritance mapping change; #45569 adds separate dense/sparse model docs, configs, and tests. They are not the same concrete fix and would not plausibly merge as one PR." + "reason": "Related NemotronH work, but not the same concrete bug/change: 45115 focuses on checkpoint conversion and class renaming/inheritance, while 45569 splits NemotronH into dense/sparse variants with docs/tests. They would not naturally merge into one PR as a single fix." } ] }, @@ -18215,7 +18239,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "f9353621e3058c49fed0f0f3c9b0a1f05bb382ab85b5940a7d4dc1e12317f4a0", + "prepared_review_unit_hash": "12a2dcf035a6dbaa361e70043a7ef3db7560976af018ae0cb944407ac9bdaa08", "component_budget": { "node_count": 2, "item_count": 2, @@ -18237,18 +18261,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct pull requests: one adds heterogeneous per-layer configuration support, the other adds heterogeneous model/runtime support on top of that foundation. They share files and theme but are not the same concrete change.", - "confidence": 0.91, + "summary": "These are closely related feature PRs for heterogeneous model support, but they are not duplicates: 45333 adds per-layer config plumbing, while 45332 adds the downstream modeling/cache/masking changes that consume that plumbing.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader end-to-end implementation and subsumes the runtime/modeling side of heterogeneous support, making it the more canonical representative of the feature work.", + "canonical_pr_reason": "45332 is the broader representative PR because it covers the end-to-end heterogeneous modeling path, not just config scaffolding.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the best overall PR because it covers the larger, user-visible heterogeneous model support rather than only the configuration plumbing.", + "best_pr_reason": "45332 is the best overall PR to represent the cluster since it includes the more complete change set; 45333 is narrower groundwork for the same feature area.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Related feature work, but not a duplicate: #45333 adds per-layer config plumbing, while #45332 adds heterogeneous model/cache/runtime behavior using that foundation. They are complementary and would not be merged as the same concrete fix/change." + "reason": "Related but not the same concrete change: 45333 adds heterogeneous config support, while 45332 adds modeling/cache handling that depends on that config. They are complementary, not duplicate fixes, and would not naturally collapse into one PR." } ] }, @@ -18278,7 +18302,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "9daadaf63d951c4097ef01a75e53ccf7ea98f288b0764d3d68306cbef5a6db00", + "prepared_review_unit_hash": "4fee7047114a985ccf633afd33d0422cc5ee0319096c46a692b227271d747ffc", "component_budget": { "node_count": 2, "item_count": 2, @@ -18300,18 +18324,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both concern typing cleanup in Transformers, but they address different scopes: one is a broad repo-wide type-checking pass, the other is a targeted typing support change for specific model/PEFT utilities.", - "confidence": 0.93, + "summary": "These are related typing-focused PRs, but they are not duplicates: one is a broad repo-wide type-checking cleanup, while the other adds/adjusts typing protocols and helpers in specific code paths.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45425 is the better canonical PR because it is the more focused, self-contained change and better represents a specific typing enhancement, whereas 45415 is a broad sweeping type-checking pass across many files.", + "canonical_pr_reason": "PR 45415 is the broader, more representative typing cleanup across many `src/transformers/*` files and the type-checking config, so it fits best as the cluster\u2019s canonical PR.", "best_issue_reason": null, - "best_pr_reason": "PR 45425 is the best PR to surface for this cluster since it has a clearer, narrower purpose and is more plausibly a single mergeable change than the large multi-file typing sweep in 45415.", + "best_pr_reason": "PR 45415 is the strongest overall representative because it covers the widest scope of the typing work and is closer to the cluster\u2019s apparent theme than the narrower helper-type refactor in PR 45425.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Reject: both are typing-related, but 45415 is a broad type-checking sweep with many unrelated files and ignores, while 45425 adds specific typing protocols/aliases for model utility integrations. They do not look like the same concrete bug or change and would not naturally merge into one PR." + "reason": "Both are typing-related, but they address different changes: 45415 is a broad type-checking sweep, while 45425 introduces specific typing protocol/helper definitions. They do not look like the same concrete bug or change and would not plausibly merge as one PR." } ] }, @@ -18341,12 +18365,12 @@ "soft_pairs": [ "pull_request:45487|pull_request:45615" ], - "prepared_review_unit_hash": "5d5819af07aba74a31ddfa50ef180f3dc26e0cedfe7029608dc9078aff403e3e", + "prepared_review_unit_hash": "e0368674c8d01752fcef3010dab830c751cb9885c1eb9648addb11c5d4cf9fcc", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5160, + "serialized_chars": 5159, "estimated_input_tokens": 1290, "estimated_eval_tokens": 2836 }, @@ -18354,7 +18378,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5160, + "serialized_chars": 5159, "estimated_input_tokens": 1290, "estimated_eval_tokens": 2836 }, @@ -18363,18 +18387,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are unrelated: one fixes a model-parallel/device placement bug in AltCLIP/ChineseCLIP code paths, while the other only updates Qianfan OCR XPU test expectations. They should not be clustered together as duplicates.", + "summary": "Two pull requests: one fixes a real model-parallel device placement bug in AltCLIP/ChineseCLIP-related model code; the other only adds XPU test expectations for Qianfan OCR. They are not the same underlying change.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45487 is the substantive code fix: it changes model code to move buffered token type ids onto the correct device, addressing an actual parallelism/device bug across affected models.", + "canonical_pr_reason": "PR 45487 is the stronger canonical PR because it contains the substantive code fix across model implementations, not just test-data updates.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the best representative because it targets a concrete runtime bug in model code, not just a test-data update. PR 45615 is only an expectations change for XPU tests and does not represent the same underlying change.", + "best_pr_reason": "PR 45487 is the best representative of the cluster since it addresses the actual bug in model forward logic and has broader functional impact than the test-only PR.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45615", "accept": false, - "reason": "Different artifacts and different problems: 45487 fixes device placement in AltCLIP/ChineseCLIP forward paths; 45615 only adds XPU test expectations for Qianfan OCR. They do not fix the same code-path issue and would not plausibly merge into one PR." + "reason": "Different subsystems and different change types: 45487 fixes device placement in AltCLIP/ChineseCLIP model code, while 45615 only adds XPU expectations to Qianfan OCR tests. They do not appear mergeable into one PR or to address the same concrete bug." } ] }, @@ -18404,7 +18428,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "1cba467b0343c7bfe7620e82aa8473d0b41fbaa8cde96e8612fc68dcada15e8f", + "prepared_review_unit_hash": "d980997f34a5a13858a7d7bcb1e998c652b53d4e79a484adda636ef444c61fbe", "component_budget": { "node_count": 2, "item_count": 2, @@ -18426,18 +18450,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are about expert parallelism loading, but they fix different bugs in different code paths: one is about ZeRO-3/accelerate loading and config serialization, the other about FSDP2/rank-0 broadcast overwriting experts.", - "confidence": 0.89, + "summary": "Both items are expert-parallelism loading fixes, but they address different failure modes: one removes `distributed_config` from serialization and adds `has_ep` for DeepSpeed ZeRO-3/accelerate loading, while the other prevents expert parameters from being overwritten during FSDP2 loading by post-shard wrapping. The shared `modeling_utils.py` touch is superficial, not evidence of the same bug.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45662 is the better canonical representative because it states a concrete failure mode (experts being silently overwritten) and makes a targeted fix in the loading path.", + "canonical_pr_reason": "No single canonical PR: these are distinct EP-loading bugs with different code paths and fixes, so neither PR is a duplicate of the other.", "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the strongest overall fit for the cluster: it has the clearest symptom, the most directly relevant fix, and the broadest set of code-path adjustments around EP loading.", + "best_pr_reason": "PR 45662 is the stronger representative of an EP-loading bug because it fixes a concrete parameter materialization issue in the loader path, but it still does not subsume 45548.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Do not merge as duplicates: #45548 fixes EP + DeepSpeed ZeRO-3 loading via accelerate launch by serializing distributed_config and adding has_ep, while #45662 fixes a different EP bug where experts are overwritten during FSDP2/rank-0 broadcast. Same subsystem, different underlying defect." + "reason": "Different underlying problems: 45548 is about config serialization and EP detection for ZeRO-3/accelerate, while 45662 is about FSDP2 load-time overwriting of experts and shard wrapping. They are related but not the same fix." } ] }, @@ -18467,12 +18491,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "a38bee02aa041678580f82b3db7a0ccfa4a56fe6803eb3aba97302de10a7ac87", + "prepared_review_unit_hash": "d03f85e9194c61794d0f0bd1f6cd16c7f1b2537c16740dd04f65fcebfb20afaa", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4590, + "serialized_chars": 4589, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -18480,7 +18504,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4590, + "serialized_chars": 4589, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -18489,18 +18513,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same underlying xdist-safe captured_info artifact problem in `testing_utils`; PR 45645 is the broader superset, adding CI log handling around the same fix.", - "confidence": 0.88, + "summary": "Both PRs address the same xdist-related captured_info collision problem, with 45645 effectively extending the core fix from 45639 into CI log collection and related cleanup.", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the more complete representation of the change: it includes the core `captured_info` xdist-safe fix plus the CI/workflow updates needed to preserve and aggregate those logs.", + "canonical_pr_reason": "45645 is the more complete representative: it includes the xdist-safe output-file change plus the CI workflow update to collect multiple captured_info artifacts.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the best standalone PR because it addresses the main bug and the surrounding CI artifact handling in one coherent change, whereas PR 45639 is only the narrower code-path fix.", + "best_pr_reason": "45645 is the best standalone representative because it covers the underlying bug fix and the downstream CI handling needed to preserve those logs.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same concrete bug family and same affected code path (`testing_utils` captured_info handling); 45645 appears to extend 45639 rather than introduce a different change." + "reason": "Both PRs fix the same concrete captured_info/xdist collision path in testing_utils, and 45645 appears to build on the same fix rather than introduce a separate change." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 43ba2c9a0ceaff23ebbf58b2595a8c45cc8452cd..3d300bdd6047f1f718841421515cdebb35d8c3f5 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260504t180032z", + "analysis_id": "hybrid-model-20260505t000047z", "archived_artifacts": { - "hybrid": "snapshots/20260504T180032Z/analysis-runs/hybrid-model-20260504t180032z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260504T180032Z/analysis-runs/hybrid-model-20260504t180032z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-04T18:07:13Z", + "published_at": "2026-05-05T00:04:58Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260504T180032Z", + "snapshot_id": "20260505T000047Z", "variant": "hybrid" } diff --git a/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.json b/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..054e57a2434f1e6dbe683593b407e2436026b93d --- /dev/null +++ b/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.json @@ -0,0 +1,2205 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260505T000047Z", + "generated_at": "2026-05-05T00:04:56Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44018-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44068, + "issue_numbers": [], + "pr_numbers": [ + 44018, + 44068 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44018, + "right_pr_number": 44068, + "code_similarity": 0.766, + "size_similarity": 0.939, + "file_overlap": 1.0, + "area_overlap": 0.425, + "patch_similarity": 0.866, + "shared_filenames": [ + "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "tests/models/gpt_neo/test_modeling_gpt_neo.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "left_ranges": [ + [ + 26, + 46 + ], + [ + 138, + 143 + ], + [ + 182, + 187 + ], + [ + 283, + 295 + ], + [ + 327, + 341 + ], + [ + 348, + 354 + ], + [ + 360, + 369 + ], + [ + 399, + 406 + ], + [ + 411, + 419 + ], + [ + 428, + 433 + ], + [ + 472, + 492 + ], + [ + 507, + 513 + ], + [ + 519, + 528 + ], + [ + 541, + 559 + ], + [ + 562, + 567 + ], + [ + 595, + 601 + ], + [ + 607, + 614 + ], + [ + 627, + 643 + ], + [ + 685, + 690 + ], + [ + 708, + 714 + ], + [ + 720, + 727 + ], + [ + 740, + 757 + ], + [ + 761, + 766 + ], + [ + 780, + 786 + ], + [ + 791, + 798 + ], + [ + 807, + 822 + ], + [ + 840, + 845 + ] + ], + "right_ranges": [ + [ + 26, + 31 + ], + [ + 34, + 44 + ], + [ + 136, + 141 + ], + [ + 180, + 185 + ], + [ + 281, + 293 + ], + [ + 325, + 339 + ], + [ + 346, + 352 + ], + [ + 358, + 367 + ], + [ + 397, + 404 + ], + [ + 409, + 417 + ], + [ + 426, + 434 + ], + [ + 463, + 483 + ], + [ + 498, + 504 + ], + [ + 510, + 519 + ], + [ + 532, + 550 + ], + [ + 553, + 564 + ], + [ + 586, + 592 + ], + [ + 598, + 605 + ], + [ + 618, + 634 + ], + [ + 676, + 688 + ], + [ + 699, + 705 + ], + [ + 711, + 718 + ], + [ + 731, + 748 + ], + [ + 752, + 762 + ], + [ + 771, + 777 + ], + [ + 782, + 789 + ], + [ + 798, + 813 + ], + [ + 831, + 836 + ] + ] + }, + { + "filename": "tests/models/gpt_neo/test_modeling_gpt_neo.py", + "left_ranges": [ + [ + 458, + 464 + ] + ], + "right_ranges": [ + [ + 458, + 464 + ] + ] + } + ] + } + ] + } + ], + "duplicate_issues": [], + "duplicate_prs": [ + { + "cluster_id": "cluster-41115-3", + "canonical_pr_number": 45613, + "duplicate_pr_numbers": [ + 41116 + ], + "target_issue_number": 41115, + "reason": "PRs in cluster-41115-3 are treated as duplicates because they converge on issue #41115 with closing_reference evidence." + }, + { + "cluster_id": "cluster-41211-3", + "canonical_pr_number": 44339, + "duplicate_pr_numbers": [ + 41356 + ], + "target_issue_number": 41211, + "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43656-4", + "canonical_pr_number": 43656, + "duplicate_pr_numbers": [ + 43836, + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43656-4 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45561-3", + "canonical_pr_number": 45645, + "duplicate_pr_numbers": [ + 45639 + ], + "target_issue_number": 45561, + "reason": "PRs in cluster-45561-3 are treated as duplicates because they converge on issue #45561 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45647-3", + "canonical_pr_number": 45738, + "duplicate_pr_numbers": [ + 45737 + ], + "target_issue_number": 45647, + "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + } + ], + "best_issue": { + "cluster_id": "cluster-45647-3", + "issue_number": 45647, + "reason": "Issue #45647 is the strongest global issue candidate because it is open, belongs to a cluster with 3 artifacts, and carries 12 discussion comments plus 8 inbound references.", + "score": 162.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..9a0ef737745819e48fc493aca0d022755725d70d --- /dev/null +++ b/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,18668 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260505T000047Z", + "generated_at": "2026-05-05T00:04:56Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "30feca13ee61f1371a80548f6ff5c721f885c74e66adddd7b85f7a1178a6bb01", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2477, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2477, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Only one issue is plausibly related to model-loading/auth errors; the Tapas tokenization report is unrelated. The two model-loading issues still look like different failure modes, so I would not merge them as duplicates.", + "confidence": 0.62, + "canonical_issue_reason": "issue:16618 is the broadest user-facing model-loading failure report; issue:13244 is unrelated, and issue:15980 is a narrower auth/error-message case.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:16618 is the best representative for the cluster because it is the most generic and likely to attract related model-load reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization vs. loading 'bert-base-uncased' are different subsystems and different bugs." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "One is a private-model login/error-message problem; the other is a generic inability to load a public model, so they do not appear to be the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44661", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45084", + "issue:45161", + "issue:45237", + "issue:45362", + "issue:45464", + "issue:45507", + "issue:45685" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:44661|issue:44805", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43975|issue:44457", + "issue:43039|issue:45161", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:43828|issue:45161", + "issue:43425|issue:44292", + "issue:44918|issue:45161", + "issue:34928|issue:41720", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44560|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:43039|issue:44805", + "issue:34928|issue:36010", + "issue:43901|issue:44512", + "issue:41762|issue:43596", + "issue:39290|issue:41720", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:39290|issue:43531", + "issue:41093|issue:43638", + "issue:43425|issue:45070", + "issue:45362|issue:45464", + "issue:43792|issue:45070", + "issue:43404|issue:43866", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762" + ], + "prepared_review_unit_hash": "96df2ee5abb1460ae9963ed3ad6a623223b9c52434dd7feaef98a645afab8255", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 67, + "serialized_chars": 47123, + "estimated_input_tokens": 11781, + "estimated_eval_tokens": 23818 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly similarity noise. The only clearly supported duplicate family is the DeepSpeed ZeRO-3 size-0/index-0 loading bug, centered on 43638 with close variants 43596 and 41762. The mask-shape-mismatch links are not accepted here and should not be treated as a duplicate family.", + "confidence": 0.86, + "canonical_issue_reason": "43638 is the best anchor because it states the generic ZeRO-3 size-0/index-0 loading failure and matches the accepted close variants most directly.", + "canonical_pr_reason": null, + "best_issue_reason": "43638 is the most representative issue for the ZeRO-3 loading bug family and is broad enough to subsume the accepted nearby reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Same model family, but different API paths and symptoms; too broad to be one bug." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different backends and failures; not the same concrete bug." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime failures; no shared code-path." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime failures; not the same bug." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different model/backend problems; not mergeable as one fix." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different model and hardware context; not the same bug." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Unrelated distributed-training and export/runtime failures." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different model/export issue; no shared concrete bug." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "Different runtime failure and model path; not a duplicate." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs cleanup, but they target different removed references." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "Unrelated export bug vs import error; no shared fix." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both are IndexError-ish, but the error contexts and root causes differ." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different failure modes: ZeRO-3 load error versus mask-shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different symptoms and model paths; too broad." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different training-time errors; not the same underlying bug." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer mapping bug vs tensor mask mismatch; unrelated." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "Different component and failure type; not duplicates." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both mention ZeRO-3, but the concrete errors and code paths differ." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0/size-0 loading failure; clearly the same underlying bug." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different models and different detokenization/LoRA behaviors." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Different feature area and failure mode." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different model/runtime issue; no shared code-path." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Both involve tensor shapes, but the specific bugs are different." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Different distributed training errors with no concrete overlap." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 load error versus GPT-OSS tensor-parallel issue; unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Training-shape mismatch vs trainer API signature mismatch; unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different model-loading bug and tensor-parallel issue." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and different runtime failures." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Different model/config failures with no concrete overlap." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Different model/runtime behavior and different root cause." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Compatibility issue vs model runtime failure; not a duplicate." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Different training feature failures; no shared concrete bug." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "Activation-checkpointing/FSDP issue versus Qwen3 device-mapping crash." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different model-specific failures with no shared bug." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Different models and different runtime failures." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Both are dtype/runtime issues, but not the same underlying problem." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Different feature areas and failure causes." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "Distributed collective mismatch vs trainer API incompatibility; unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger-kernel/cross-entropy issue is unrelated to mask-shape mismatch." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Training checkpointing bug vs import error; no shared bug." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs issues, but they concern different removed references." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": true, + "reason": "Same ZeRO-3 size-0/index-0 loading bug; different model examples only." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different model/config failures with no concrete overlap." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Different feature areas and runtime errors." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Both are load failures, but the root causes and models differ." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Different model/test problem vs corrupted checkpoint report." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Similar wording, but different model/config contexts." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are IndexErrors, but they refer to different failure modes." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Compatibility/version issue vs pydantic config bug; unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Same model family, but different API scenarios and symptoms." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Different subsystem: model load/runtime vs config serialization." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Different model-loading bugs and different underlying causes." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated runtime failures." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Different model classes and different runtime failures." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Different model/runtime bugs; not the same fix." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "Import error vs config attribute error; unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Different processor/template bugs." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Different error signatures and likely different root causes." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0/size-0 load failure; same underlying bug." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs issues, but they remove different obsolete references." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different model-specific failures with no shared bug." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different runtime errors and different model/backends." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Different model/backend failures; not duplicates." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Different feature areas and error paths." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption vs unsupported implementation; not the same underlying bug." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Different model/test problems; no shared concrete bug." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different model config problems, only loosely related by wording." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Different IndexErrors with different shapes and contexts." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Version incompatibility vs pydantic field regression; unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Related model family, but different endpoints and failures." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Different subsystems and causes; not a duplicate." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Different model-loading problems with different root causes." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated runtime failures." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Different backend/model issues; no shared fix." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Different model/runtime bugs." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "ImportError and config attribute error are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Different processor/template bugs." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Different error signatures and likely different root causes." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The ZeRO-3 size-0/index-0 loading family is grounded in the packet, but the summary overstates evidence by claiming a true duplicate family for the mask-shape-mismatch issues as well. In the packet, the mask-shape pairs are all marked false, so they should not be described as standing out as a duplicate family. The soft-edge verdicts should stay conservative and only support the ZeRO-3 family." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 2, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:39186", + "issue:39290", + "issue:39692", + "issue:40990", + "issue:41093", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43742", + "issue:43828", + "issue:43866", + "issue:43873", + "issue:43950", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45070", + "issue:45161", + "issue:45399", + "issue:45464", + "issue:45507", + "issue:45632", + "issue:45685", + "issue:45698" + ], + "soft_pairs": [ + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:43531|issue:45070", + "issue:39290|issue:43742", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:43716|issue:44918", + "issue:45632|issue:45698", + "issue:44918|issue:45685", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:40990|issue:44960", + "issue:44530|issue:45005", + "issue:42915|issue:45399", + "issue:44360|issue:44512", + "issue:44863|issue:45005", + "issue:43873|issue:45005", + "issue:39186|issue:44918", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:44292|issue:45507", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:43866|issue:44403" + ], + "prepared_review_unit_hash": "fdea643cfcca02e53c4cbdd9dda220a62824c0db7de7972e5c4e6b593b7d4540", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36620, + "estimated_input_tokens": 9155, + "estimated_eval_tokens": 18566 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated Transformers/vLLM/model-loading issues. The only clear duplicate group is the v5 non-persistent buffer regression, which shows up in multiple similarly worded reports.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43950 is the most specific and central report for the non-persistent buffer regression: it clearly describes silent corruption in from_pretrained() and matches the other buffer-related reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 is the best representative issue because it states the bug precisely, is broad enough to cover the related buffer-corruption reports, and is actionable for a fix.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Different problems: PaddleOCR-VL loading failure vs GGUF gpt-oss support." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Both involve config/API regressions, but they are different fields and different failure modes." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "One is an int4 memory/OOM regression; the other is tied-weights handling in translation models." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Different MoE issues: grouped_mm tracing error vs tensor-parallel support not working." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Different symptoms and code paths: autocast dtype mismatch vs streaming chat/completions failure." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Unexpected init_empty_weights argument is unrelated to the pydantic PretrainedConfig field breakage." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF architecture support and streaming inference are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug is not the same as the PretrainedConfig/pydantic regression." + }, + { + "left": "issue:39290", + "right": "issue:43742", + "accept": false, + "reason": "Different models and distinct missing-attribute/key-error failures." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Grouped_mm tracing failure is unrelated to missing Float8 storage support." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Different indexing errors in different execution contexts." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Both are about SigLIP2, but one is a relative quality complaint and the other is an AutoModel/pipeline correctness issue; not clearly the same bug." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Image preprocessor/model dtype mismatch is unrelated to TRL SFT input-embedding unpacking." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom module loading, but one is a local-path cache collision and the other is save_pretrained/from_pretrained picking the wrong module." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3.5 SFT embedding handling is unrelated to the MPS histogram kernel error." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Related to tied weights in name only; these are different models and different bugs." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Jupyter custom-model initialization and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "Different models and different evaluation/perplexity claims." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache group-type error is not the same as tied-weights regressions." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "FineGrainedFP8Config failure is unrelated to flash-attn fallback checks." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer behavior and documentation typo are unrelated." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading is unrelated to tied-weights handling." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization offloading behavior is unrelated to tied-weight regressions." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP 2-D weight error and Qwen3.5 embedding unpacking are different failure modes." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo is not the same as stale docs about the removed run command." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and unrelated invalid-method/runtime errors." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Incorrect detokenization and NVFP4 runtime failure are unrelated." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "These describe the same v5 non-persistent buffer corruption regression with nearly identical wording and behavior." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Both report the same non-persistent buffer corruption regression in Transformers 5.x." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "NVFP4 runtime failure and GraniteMoEHybrid invalid-method calls are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Documentation example errors are not the same as SigLIP2 embedding-quality regression." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Different Qwen/Phi training-time issues with different root causes." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption and noisy load logging are not the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet, and the duplicate call on the v5 non-persistent buffer regression (43950/43644/44534) is supported. The other soft-edge rejections read conservative overall, with no clear overstatement of evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 3, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:41553", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43257", + "issue:43404", + "issue:43493", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43854", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43940", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44589", + "issue:44661", + "issue:44863", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45237", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45520", + "issue:45701" + ], + "soft_pairs": [ + "issue:36331|issue:41762", + "issue:41553|issue:43883", + "issue:43872|issue:44589", + "issue:38175|issue:43054", + "issue:41553|issue:43881", + "issue:43054|issue:45701", + "issue:42947|issue:44387", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43881|issue:43883", + "issue:43975|issue:45520", + "issue:43054|issue:43493", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:42491|issue:44368", + "issue:41762|issue:42915", + "issue:43975|issue:44451", + "issue:44661|issue:45020", + "issue:43824|issue:43872", + "issue:44991|issue:45399", + "issue:45020|issue:45356", + "issue:43782|issue:44960", + "issue:43827|issue:44509", + "issue:45081|issue:45399", + "issue:43792|issue:44220", + "issue:43404|issue:43950", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43257|issue:43866", + "issue:43742|issue:45020", + "issue:41553|issue:44991", + "issue:43940|issue:45313", + "issue:43872|issue:44291", + "issue:43854|issue:44863", + "issue:42915|issue:43872" + ], + "prepared_review_unit_hash": "24078b38d4b9832995866c3b200f02029243d3137da6d096b4a4309effab2f29", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37861, + "estimated_input_tokens": 9466, + "estimated_eval_tokens": 19188 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous and mostly splits into a few separate duplicate subgroups rather than one true cluster-wide duplicate set. Clear duplicate pairs appear for the docs pipeline-removal reports, the Qwen3 ZeRO-3 loading failures, and the _is_hf_initialized/init_empty_weights TypeError; most other suggested edges are not duplicates.", + "confidence": 0.31, + "canonical_issue_reason": "No single issue is a clean canonical for the whole cluster; it splits into multiple unrelated subclusters (docs, SigLIP2 quality/regression, ZeRO-3 loading, and init_empty_weights/bitsandbytes TypeErrors).", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must anchor the cluster, 45020 is the broadest umbrella candidate among the loading-regression reports, but it still does not cover the whole set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Unrelated: trainer compute_loss signature mismatch vs Gemma3/DeepSpeed ZeRO-3 loading failure." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Different problems: Voxtral AutoTokenizer error messaging vs Molmo missing all_tied_weights_keys." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Both are loading-related, but the failure modes differ: bitsandbytes _is_hf_initialized kwarg vs missing Float8 storage object." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": true, + "reason": "Both report SigLIP2 behaving incorrectly at inference quality/output-distribution level; likely the same underlying SigLIP2 implementation issue." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Unrelated: Voxtral tokenizer error message vs GLM-4v-9b loading failure." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality issue vs a broader tokenization-version regression; not the same code-path." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Different regressions: LoRA gradient checkpointing ineffective vs int4 quantization memory growth/OOM." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Unnecessary loading noise vs inability to load ScandiBERT; symptoms and targets do not match." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Related theme, but not the same bug: missing fields from AutoConfig with trust_remote_code vs a broader remote_code breakage report." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Different model load failures: GLM-4v-9b load problem vs Molmo missing all_tied_weights_keys." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization regression vs import_utils flash_attn KeyError; unrelated code paths." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "Same model family, but this pair is not explicit enough to treat as a duplicate without stronger evidence of the same root cause." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Tokenizer/detokenization regression vs AMD GPU runtime incompatibility; unrelated." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Different load issues for different models; no clear shared underlying bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA gradient-checkpointing issue vs Qwen3 MoE memory usage; different concrete failures." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "LoRA/Qwen3 MoE conversion issue vs a warning about tie_word_embeddings; not the same problem." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure vs Qwen3 MoE FP8 failure; same broad area, different bugs." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "add-new-model-like/tokenizer mapping bug vs remote_code regressions; different code paths." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "ImportError for Qwen2_5_VL symbol vs bitsandbytes init kwarg TypeError; unrelated." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure for a specific model vs flash-attn fallback checks; unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Broad remote_code breakage vs Kimi-K2.5 tokenizer codec regression; not the same bug." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error vs GLM5; unrelated models and failures." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Near-verbatim docs issue: both say v5 docs still reference removed pipeline tasks like text2text-generation/summarization/translation." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex crash vs flash-attn fallback blocked by checks; different issues." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper runtime failure vs _torch_extract_fbank_features bug; related speech area but not clearly the same concrete defect." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Mistral3 lm_head tying bug vs non-persistent buffer corruption in from_pretrained; unrelated." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM load KeyError vs flash-attn fallback gating; not the same underlying bug." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Qwen3 MoE FP8 failure vs broad remote_code regressions; too different to merge." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate/deepspeed vs Ovis2 checkpoint corruption; unrelated." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Specific MobileLLM KeyError vs general remote_code breakage; not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Different model/tokenizer loading failures with no clear shared code-path." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": true, + "reason": "Same concrete class of bug: ZeRO-3 weight loading fails for Qwen3-family models, just on different variants." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same `_is_hf_initialized`/init_empty_weights incompatibility causing TypeError during model loading." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "GLM-4.7-Flash unit-test load issue vs NemotronH checkpoint loading failure; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE FP8 training/loading issue vs bitsandbytes `_is_hf_initialized` TypeError; different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analyst summary is grounded in the packet and stays conservative. It correctly treats the cluster as heterogeneous, avoids over-claiming a single canonical issue, and only accepts soft edges that look clearly mergeable by symptom/root cause (docs pipeline removals, SigLIP2 inference-quality regressions, Qwen3 ZeRO-3 loading failures, and the _is_hf_initialized/init_empty_weights TypeError). The rejected edges are generally supported by distinct titles and failure modes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 4, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:41093", + "issue:41553", + "issue:42617", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43638", + "issue:43645", + "issue:43646", + "issue:43824", + "issue:43828", + "issue:43872", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:45030", + "issue:45305", + "issue:45313", + "issue:45325", + "issue:45357", + "issue:45538", + "issue:45584", + "issue:45588" + ], + "soft_pairs": [ + "issue:44928|issue:45588", + "issue:41553|issue:44488", + "issue:36331|issue:41093", + "issue:43257|issue:45305", + "issue:43872|issue:45538", + "issue:44530|issue:44863", + "issue:41093|issue:44805", + "issue:44479|issue:44560", + "issue:24643|issue:30064", + "issue:43366|issue:43828", + "issue:43366|issue:43531", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:43950|issue:45325", + "issue:43366|issue:44589", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:42915|issue:43957", + "issue:43824|issue:43957", + "issue:36010|issue:42915", + "issue:38175|issue:43994", + "issue:43646|issue:43950", + "issue:44155|issue:45584", + "issue:44877|issue:45030", + "issue:44560|issue:44805", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:43317|issue:44756", + "issue:38175|issue:39692", + "issue:45313|issue:45357" + ], + "prepared_review_unit_hash": "1d86b55b0d5beed4871125f8573403060984a20786a702acd59dba03a7e4f391", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36301, + "estimated_input_tokens": 9076, + "estimated_eval_tokens": 18408 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of Transformers bug reports, with only a few true duplicate-looking subclusters. The strongest matches are the custom model initialization regression, the identical mask-shape IndexError, and a SigLIP2 broken-inference report; the rest are too different in bug class or code path.", + "confidence": 0.62, + "canonical_issue_reason": "No single issue cleanly covers the whole cluster, but issue:43646 is the best canonical anchor among the true duplicates: it states the broad Transformers 5.0 custom-model-initialization regression, while issue:43645 is just a narrower Jupyter repro.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the most general, reusable bug report in the strongest duplicate subcluster, so it is the best issue to track even though the overall cluster is not one single bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "Different failures: Qwen3.5 RLHF/3D position_ids vs a flash-attention integration AttributeError on sink-less models." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading/error-reporting issues, but one is AutoTokenizer/Voxtral messaging and the other is loading a different model; no shared code path." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Trainer API keyword mismatch versus a tensor/mask shape IndexError; unrelated bugs." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Both involve DeepSpeed/Qwen3, but one is weight conversion on load and the other is gradient averaging with GAS; different code paths." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes constructor incompatibility versus a tokenizer max_length constant; unrelated." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "Both mention model internals, but one is a PagedAttentionCache crash on Qwen3.5 and the other is a NemotronH checkpoint loading failure." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same IndexError family with the same mask-vs-tensor shape mismatch; 44805 looks like a later/generalized repro of the same bug." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Different regressions: a broad video-input regression across several Qwen VL variants versus a StopIteration on Qwen3-vl-embedding." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "DeepSpeed training weight-dimension error versus image processor handling of void segmentation maps; unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF/gpt-oss support request versus a torch.autocast dtype mismatch on Phi-tiny-MoE; not the same bug." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "GGUF support request versus a Qwen3-MoE sliding_window issue; different changes." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Both touch attention, but Bamba SDPA/torch.compile and Qwen3.5 flash-attention position_ids are separate failures." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These describe the same Transformers 5.0 custom-model-initialization regression; the notebook mention is just a specific repro." + }, + { + "left": "issue:43950", + "right": "issue:45325", + "accept": false, + "reason": "Non-persistent buffer loading corruption versus Qwen2.5-VL rope-position scaling; different subsystems." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF architecture support versus a missing Float8 storage type error; unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both are Qwen VL/input-embedding related, but one is a video StopIteration and the other is TRL SFT unpacking failure; not the same concrete bug." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py runtime problem versus GGUF gpt-oss support; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "FineGrainedFP8Config failure on Qwen3Moe versus meta-device loading regressions; different code paths." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Import error for a Qwen2.5-VL class versus meta-device model loading breakage; unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "GenerationMixin import failure versus Qwen3Moe FP8 config failure; unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 checkpoint with broken inference outputs; zero probabilities and nonsensical pipeline/AutoModel results look like the same underlying regression." + }, + { + "left": "issue:43646", + "right": "issue:43950", + "accept": false, + "reason": "Custom model initialization regression versus non-persistent buffer corruption on from_pretrained(); different issues." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 batched-inference token leak versus Whisper empty-transcription generation failure; unrelated." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Strict config blocking granite_speech versus tiny-random glm4v config validation; different model families and failures." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Qwen3-vl video StopIteration versus a generic mask-shape IndexError; not the same bug." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Zero-size tensor IndexError under DeepSpeed ZeRO-3 versus tokenizer-mapping-name handling in add-new-model-like; unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Both are IndexErrors, but one is ZeRO-3/BertModel loading and the other is a tokenizer mapping edge case; different root causes." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Dequantized model offload loading failure versus mmap OOM on Strix Halo; different memory-loading problems." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Both mention SigLIP2, but one is bad model outputs and the other is a documentation example with model/processor mismatch plus quantization failure; not the same concrete bug." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "ZeRO-3 loading weights for Qwen3.5 language_model versus save_pretrained storing incorrect visual encoder keys; separate regressions." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about a mostly heterogeneous cluster. The accepted duplicate subclusters are plausible from the issue titles alone: 43645/43646, 41093/44805, and 38175/43994. The non-duplicate verdicts also avoid over-claiming by generally citing distinct failure modes or code paths. No PR-pair mergeability concerns apply here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 5, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43720", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44164", + "issue:44291", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44661", + "issue:44683", + "issue:44756", + "issue:44910", + "issue:44960", + "issue:44977", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759" + ], + "soft_pairs": [ + "issue:43644|issue:44534", + "issue:44960|issue:44977", + "issue:44451|issue:44488", + "issue:42491|issue:43720", + "issue:43854|issue:43931", + "issue:43708|issue:44075", + "issue:41720|issue:42915", + "issue:42491|issue:45276", + "issue:43856|issue:43873", + "issue:43257|issue:43854", + "issue:39692|issue:43994", + "issue:42915|issue:44756", + "issue:42491|issue:43931", + "issue:43856|issue:44387", + "issue:44661|issue:44683", + "issue:43644|issue:43645", + "issue:44910|issue:45588", + "issue:45362|issue:45406", + "issue:44488|issue:44991", + "issue:42491|issue:45292", + "issue:43404|issue:43454", + "issue:36010|issue:39404", + "issue:45276|issue:45335", + "issue:44164|issue:44291", + "issue:44402|issue:44488", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:43425|issue:43957", + "issue:43335|issue:45663", + "issue:45663|issue:45759", + "issue:43873|issue:44387", + "issue:44387|issue:44756", + "issue:43854|issue:45216" + ], + "prepared_review_unit_hash": "458006a1b71cabd454ad0c61ab0d278d12bbaa6fc6e012e772b71deaf57f7e9a", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37020, + "estimated_input_tokens": 9255, + "estimated_eval_tokens": 18766 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "One clear duplicate pair stands out: the non-persistent-buffer regression in Transformers 5.0.0. The rest are related by subsystem or model family, but they do not look like the same concrete bug.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43644 is the earlier, broader report of the non-persistent buffer regression in Transformers 5.0.0; it is the better canonical thread for the duplicate pair with issue:44534.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the strongest issue candidate overall because it captures a concrete, version-specific regression with a clear duplicate and broad impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Same bug: both report Transformers v5 filling non-persistent buffers with junk; 44534 is just a shorter rewording of the same regression." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Both mention flash-attention/generation failures, but they affect different models and appear to be different code-path bugs." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading failures for different BERT checkpoints, but there is no clear evidence they share the same underlying defect." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Completely different problems: Qwen3 MoE LoRA compatibility vs BitNet packed-weight loading in accelerate." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different model-load failures with different symptoms; no sign of a shared root cause." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer checkpoint math and SGD argument handling are unrelated bugs." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Different Qwen3 issues: device-mapping CUDA assert vs FineGrainedFP8Config failure." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Unrelated issues; one is a Qwen3 MoE LoRA compatibility problem, the other is resize_token_embeddings behavior in Gemma4." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both involve Qwen3 MoE/quantization, but one is training memory usage and the other is offloading behavior; not the same bug." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Different failures: Qwen3 MoE weight conversion with accelerate/deepspeed vs GLM-4.7 loading in tests." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Both concern SigLIP2, but one is a broken documentation example and the other is bad outputs in AutoModel/pipeline; not the same concrete issue." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3Moe FP8 failure and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Different model-loading/training problems with no shared code-path evidence." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "One is Qwen3 MoE memory use during training; the other is int4 CUDA reserved-memory/OOM under Transformers 5.x." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Tokenizer-mapping registration bug and compiled flex_attention/torch-version failure are unrelated." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Related to Transformers 5.0.0 regressions, but one is non-persistent buffers and the other is custom-model initialization in Jupyter; different bugs." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both are flash-attention crashes, but the root causes differ: packed-sequence misinterpretation vs s_aux=None handling." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different failures in different model stacks: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer/model-loading complaints, but they concern different checkpoints and different failure modes." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "No concrete overlap; one is Qwen3 MoE LoRA compatibility, the other is output_embeddings not updating on resize." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both are weight-tying problems, but they affect different model classes and are not clearly the same code-path bug." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "ImportError for GenerationMixin and Whisper return_language pipeline regression are unrelated." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "Very similar symptom, but different model families and different embedding targets; not enough evidence of one shared bug." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Saving/from_pretrained extra_state handling and init_empty_weights unexpected argument handling are distinct loading issues." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab-size mismatch and a model-loading failure for cjvt/sleng-bert are different defects." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Different model families and different problem types; no shared underlying bug." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Both touch training stability/memory, but PEFT gradient checkpointing and apex FusedRMSNorm memory leak are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch 2.10 incompatibility and meta-device loading regressions are separate problems." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers config construction and Gemma-4 FSDP2 shared_kv_states behavior are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma-4 FSDP2 attention state bug and Qwen multimodal config unwrapping are different issues." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Offloading with quantization and int4 CUDA reserved-memory/OOM are related at a high level but not the same concrete bug." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Different performance/memory regressions: int4 quantization OOM vs disabling mmap on Strix Halo." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Different Qwen3/VL loading and save_pretrained regression issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The only accepted pair, issue:43644 / issue:44534, is well-supported by the titles and is a reasonable canonical duplicate thread. The rejected pairs are all framed cautiously with no obvious overstatement." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 6, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:39404", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43299", + "issue:43381", + "issue:43425", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43854", + "issue:43856", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44265", + "issue:44291", + "issue:44292", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45084", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701" + ], + "soft_pairs": [ + "issue:44292|issue:44912", + "issue:44291|issue:44756", + "issue:42947|issue:43381", + "issue:45684|issue:45698", + "issue:45276|issue:45292", + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:41720|issue:44155", + "issue:45588|issue:45663", + "issue:44479|issue:44877", + "issue:43646|issue:43708", + "issue:43854|issue:44960", + "issue:43957|issue:44756", + "issue:45292|issue:45335", + "issue:44402|issue:44451", + "issue:43645|issue:44164", + "issue:43828|issue:43957", + "issue:43257|issue:44863", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:44479|issue:45663", + "issue:43906|issue:44530", + "issue:39404|issue:45701", + "issue:43611|issue:43645", + "issue:44530|issue:45084", + "issue:43931|issue:44863", + "issue:43425|issue:43716", + "issue:43901|issue:44509", + "issue:39404|issue:44912", + "issue:44863|issue:45663", + "issue:44265|issue:44898", + "issue:43299|issue:43931", + "issue:44479|issue:44805", + "issue:43856|issue:44756", + "issue:43425|issue:44918", + "issue:44589|issue:45084" + ], + "prepared_review_unit_hash": "dcafaf54bee22a60bbca48dfba4a0e916a5ba837cf28b58330a9f6f5494bcc32", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38455, + "estimated_input_tokens": 9614, + "estimated_eval_tokens": 19484 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers regressions, with one clear duplicate subcluster around `resize_token_embeddings` not propagating to downstream embedding/output modules.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45292 is the broadest, cleanest description of the resize-token-embedding propagation bug and can serve as the anchor for the small duplicate subcluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the best representative issue because it states the shared failure mode without being overly model-specific.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Both are quantization/loading failures, but for different models and different failure modes; no clear same underlying bug." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "`init_empty_weights` argument handling and Strix Halo mmap/OOM are unrelated bugs." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both mention gradient checkpointing, but one is a PEFT/LoRA ineffectiveness bug and the other is an eval-mode restriction." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load custom-model workflows, but one is about read-only file permissions and the other is about loading the wrong module." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same underlying bug: `resize_token_embeddings` is not propagating updates to output-side embeddings; 45276 is the gemma4-specific manifestation." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Unrelated gradient-checkpointing behavior vs RLHF/SDPA/BF16 instability." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "`extra_state` serialization and Strix Halo mmap/OOM are different problems." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Different models and different failures: device-map assertion vs batched inference token leakage." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Different code paths and symptoms: flash-attention aux-state handling vs Gemma-4 FSDP shared-kv-state rebuilding." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression for Qwen models and strict-config loading for granite_speech are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization and Trainer checkpoint-resume step calculation are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:44960", + "accept": false, + "reason": "GLM-4.7-Flash test loading and GLM5 are not the same bug." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "`torch.device('meta')` loading regressions and Strix Halo mmap/OOM are different issues." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same resize-token-embedding propagation bug, with 45335 describing the decoder embedding side specifically." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Tokenizer vocab mismatch and ScandiBERT loading failure are too vague to treat as the same bug." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook custom-model init and `extra_state` save/load handling are different failures." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch and meta-device loading failure are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Different model families and different loading/conversion failures." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility is too broad to merge with a specific autocast dtype-mismatch bug." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure and Strix Halo mmap/OOM are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45663", + "accept": false, + "reason": "Qwen video-input regression and Gemma-4 FSDP cache/state bug are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "A reproduction of an earlier issue and a PagedAttentionCache/Qwen3.5 crash are not the same bug." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline `return_language` regression and tokenizer-version changes are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Base-model-prefix loading regression and notebook-defined custom-model initialization are different code paths." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash and template-node compilation error are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Different model families and different loading errors." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch version compatibility and Mistral-3 image-preprocessor dtype mismatch are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs issues, but they cover different pipeline deprecations and should not be merged." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language-return regression and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:44863", + "right": "issue:45663", + "accept": false, + "reason": "NemotronH checkpoint loading and Gemma-4 FSDP state rebuilding are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "`torch.export`/`torch_compilable_check` failure and Perceiver interpolation failure are different bugs." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both involve Qwen3-VL loading, but one is a v5 regression for MoE models and the other is a specific checkpoint shape mismatch." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression and mask/tensor shape mismatch are unrelated." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE memory usage and Strix Halo mmap/OOM are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch compatibility and TRL SFT input-embedding unpacking are different bugs." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure and non-template-node compilation failure are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: most pairs are conservatively rejected as different bugs, and the two accepted edges around `resize_token_embeddings` are well-supported by the issue titles and high similarity. The canonical issue choice is also reasonable for the shared embedding-propagation bug." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 7, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:42947", + "issue:43317", + "issue:43404", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43482", + "issue:43541", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43716", + "issue:43883", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44466", + "issue:44488", + "issue:44530", + "issue:44671", + "issue:44683", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45507", + "issue:45584", + "issue:45685", + "issue:45759" + ], + "soft_pairs": [ + "issue:43596|issue:44683", + "issue:40990|issue:42947", + "issue:43425|issue:45685", + "issue:39404|issue:44671", + "issue:43994|issue:44079", + "issue:44671|issue:44991", + "issue:36032|issue:43452", + "issue:44164|issue:45759", + "issue:44991|issue:45081", + "issue:32090|issue:39404", + "issue:43957|issue:44164", + "issue:44488|issue:45081", + "issue:40990|issue:43421", + "issue:43582|issue:43632", + "issue:43883|issue:44488", + "issue:43611|issue:43644", + "issue:44206|issue:44220", + "issue:44811|issue:45584", + "issue:43716|issue:45084", + "issue:44488|issue:44987", + "issue:34567|issue:40444", + "issue:43643|issue:44530", + "issue:43644|issue:43646", + "issue:43883|issue:44991", + "issue:44451|issue:44987", + "issue:36032|issue:42915", + "issue:43452|issue:43482", + "issue:43541|issue:45084", + "issue:42915|issue:44530", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:43404|issue:44466", + "issue:36032|issue:43645", + "issue:45084|issue:45507" + ], + "prepared_review_unit_hash": "19ba22a1c0cccd5e491c58eec52701712f504e9e46f66cf8882549d7691a42b0", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37904, + "estimated_input_tokens": 9476, + "estimated_eval_tokens": 19208 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose collection of unrelated Transformers regressions. The only likely duplicate-style overlap is the GGUF loading pair; the rest look like separate bugs affecting different code paths or models.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43452 is the strongest anchor because it describes a concrete, broad GGUF loading regression affecting both tokenizer and CausalLM from_pretrained paths.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43452 is the best standalone issue to keep because it is the most general and actionable description of the GGUF-loading failure in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Different failure surfaces: DeepSpeed ZeRO3 initialization vs compiled flex_attention on newer torch." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Unrelated bugs: perplexity quality issue vs gradient checkpointing/LoRA behavior." + }, + { + "left": "issue:43425", + "right": "issue:45685", + "accept": false, + "reason": "Torch version compatibility on one side and an MPS histogram-op error on the other; not the same bug." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline language return bug and CamemBERT masked-LM predictions are separate model-specific issues." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP inference quality regression vs ModelOutput key assignment logic; different code paths." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "Different models and failures: CamemBERT prediction bug vs tokenizer loading for est-roberta." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "Tokenizer special-token method conflict is unrelated to GGUF loading failure." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "Save/load extra_state handling and from_config text_config unwrapping are distinct loader issues." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizers, but one is a tokenizer loading regression and the other is a Mistral regex patch crash; not the same bug." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error does not match Whisper pipeline return_language behavior." + }, + { + "left": "issue:43957", + "right": "issue:44164", + "accept": false, + "reason": "Meta-device model loading and extra_state save/load handling are different regressions." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Loading a specific BERT model and crashing in Mistral regex patching are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity regression vs runtime special-token post-processor update behavior." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError and _is_hf_initialized flag breakage are separate issues." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing tied-weights key attribute vs model loading failure for a specific BERT repo are not the same underlying bug." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer serialization; different fixes." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Likely related audio feature-extraction area, but the titles point to different failures and there is not enough evidence of one shared bug." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper token-handling issues, but one is batch_decode skipping special tokens and the other is empty-transcription generation after align_special_tokens." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Image preprocessor dtype mismatch and Jinja/template compilation failure are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Different loading failures for different models; no shared code-path evidence." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "Trainer token-count tracking and multi-image IterableDataset fine-tuning are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss is unrelated to PagedAttentionCache's linear_attention group-type crash." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both mention v5 model initialization problems, but one is non-persistent buffers and the other is custom model init semantics; not the same bug." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Different symptoms and subsystems: tied-weights attribute vs tokenizer load regression." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Model-specific loading failure vs a broad transformers>=5.1.0 regression loading a different repo." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "Tokenizer class conflict and FineGrainedFP8Config failure are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": true, + "reason": "Both point to the same GGUF loading regression in transformers v5, affecting from_pretrained loading of GGUF models/tokenizers." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch dynamo tracing grouped_mm failure is unrelated to template compilation errors." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "FineGrainedFP8Config failure and PagedAttentionCache group-type crash are separate MoE/model-loading issues." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Dequantized model offload/device_map loading and GGUF model loading are different bugs." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 hidden-state output bug and Qwen2.5-VL rope-index scaling bug are distinct model-specific regressions." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Tied lm_head weight bug in Mistral3 and serialization inconsistency across devices are related only loosely, not the same concrete defect." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer special-token conflict is unrelated to custom model initialization in Jupyter notebooks." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template compilation failure and GraniteMoEHybrid invalid-method calls are unrelated code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about the soft-edge pairs. The GGUF overlap is the only clearly supported duplicate-style link, and the other false verdicts are adequately cautious given the titles alone." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 8, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:36032", + "issue:40990", + "issue:41553", + "issue:42175", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43540", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43818", + "issue:43819", + "issue:43856", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45542" + ], + "soft_pairs": [ + "issue:43262|issue:43377", + "issue:43646|issue:44534", + "issue:43994|issue:44610", + "issue:44987|issue:44991", + "issue:44403|issue:45081", + "issue:43322|issue:43540", + "issue:43377|issue:43819", + "issue:44220|issue:44683", + "issue:44451|issue:45081", + "issue:45216|issue:45357", + "issue:43645|issue:44534", + "issue:42915|issue:45084", + "issue:44265|issue:44610", + "issue:44987|issue:45081", + "issue:43404|issue:45127", + "issue:41553|issue:43582", + "issue:43632|issue:44756", + "issue:43296|issue:43531", + "issue:44062|issue:44987", + "issue:42915|issue:44291", + "issue:36032|issue:43742", + "issue:43531|issue:44877", + "issue:43611|issue:44534", + "issue:42915|issue:44589", + "issue:40990|issue:44811", + "issue:43317|issue:43856", + "issue:44479|issue:45325", + "issue:42175|issue:45542", + "issue:43425|issue:44403", + "issue:43818|issue:45357" + ], + "prepared_review_unit_hash": "6396ecb9b1a351d457ebd541364f3cd2c1c39731e5e1093122e5fa1e7b25d38e", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36044, + "estimated_input_tokens": 9011, + "estimated_eval_tokens": 18278 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers v5/model-loading regressions. I only see two likely duplicate subpairs: Qwen3.5 save_pretrained checkpoint corruption and TensorFlow backend packaging/import failures.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43611 is the broadest representative of the dominant theme here: Transformers v5 loading regressions in model initialization/loading paths.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single anchor for the cluster because it captures the core loading-path regression theme more generally than the narrower model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio chat-template sampling-rate behavior and MIMI batch padding-mask behavior are different model/component bugs." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization and non-persistent buffer corruption are different v5 regressions with different code paths." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and OmDet-Turbo processor size mismatch are unrelated model/preprocessing issues." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are loading failures, but for different models and likely different root causes; not one concrete bug." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise and the Mistral tokenizer backend_tokenizer crash are different problems." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Both are multimodal crashes, but one is Llava Next segfaulting and the other is Qwen3OmniMoe video ValueError; different bugs." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI padding-mask mismatch and DAC.from_latents STE mismatch are unrelated audio-model correctness bugs." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Fbank feature extraction and compiled flex_attention on newer torch are unrelated issues." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Specific model loading failure and Mistral tokenizer patch crash are unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Both describe the same Qwen3.5 save_pretrained checkpoint corruption/incorrect saved keys on the same code path." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom-model initialization and junk-filled non-persistent buffers are different regressions." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and template-node compilation error are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export/torch_compilable_check failure and OmDet input-size mismatch are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different model-loading/tokenizer failure modes; too little to treat as one bug." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "lm_head tying in Mistral3ForConditionalGeneration and LoRA merge collapse are different problems." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Tokenizer-loading error and Apple Silicon allocator warmup TypeError are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized regression and mmap/OOM behavior are unrelated." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window issue are different bugs." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken special-argument conflict and model loading failure for a specific repo are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Both involve v5 initialization, but one is FineGrainedFP8Config and the other is init_empty_weights/_is_hf_initialized; different concrete failures." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5 tokenizer special-token conflict and MobileLLM key error are unrelated loading issues." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window and granite_speech strict config loading are different bugs." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 loading regressions, but one is base_model_prefix handling and the other is non-persistent buffer initialization; not the same concrete bug." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss and Whisper batch_decode skip_special_tokens behavior are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "device_map/offload loading failure and Qwen3 MoE training memory use are related only broadly by memory concerns, not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both touch Qwen video/VL models, but one is a video-input regression and the other is a rope-index scaling bug for still images; different code paths." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": true, + "reason": "Both point to the same TensorFlow-backend packaging/import problem where TF is missing or only partially installed under non-TF extras." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version incompatibility and generic loading noise are unrelated." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA temporal-attention/weight-sharing bug and Qwen3.5 save_pretrained regression are unrelated model families and code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The summary does not overclaim beyond the packet, and the two accepted pairs (45216/45357, 42175/45542) look plausibly duplicate enough from the titles/descriptions. The other soft-edge rejections stay appropriately cautious." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 9, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:36032", + "issue:40444", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43377", + "issue:43421", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43792", + "issue:43828", + "issue:43881", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44403", + "issue:44466", + "issue:44488", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44617", + "issue:44683", + "issue:44829", + "issue:44877", + "issue:44898", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45663" + ], + "soft_pairs": [ + "issue:43421|issue:44568", + "issue:44079|issue:45663", + "issue:44683|issue:45020", + "issue:36032|issue:41720", + "issue:43632|issue:44534", + "issue:43792|issue:44589", + "issue:44403|issue:44991", + "issue:43482|issue:45538", + "issue:33666|issue:40444", + "issue:44829|issue:45479", + "issue:40444|issue:45325", + "issue:43482|issue:43525", + "issue:43377|issue:45491", + "issue:44291|issue:44589", + "issue:41720|issue:45081", + "issue:44265|issue:45072", + "issue:42175|issue:43296", + "issue:43632|issue:45072", + "issue:43611|issue:43646", + "issue:44079|issue:44534", + "issue:43531|issue:44291", + "issue:43994|issue:44898", + "issue:43454|issue:44466", + "issue:43881|issue:44488", + "issue:43828|issue:44683", + "issue:42915|issue:43482", + "issue:44079|issue:45072", + "issue:43792|issue:43957", + "issue:43644|issue:44079", + "issue:40444|issue:45381", + "issue:45325|issue:45381", + "issue:44387|issue:44617", + "issue:35707|issue:40444", + "issue:44291|issue:44877" + ], + "prepared_review_unit_hash": "52207d60e831ca0d8a25123e19455468cbb6d0d4e543ba7ad4e5f9875651462f", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 38078, + "estimated_input_tokens": 9520, + "estimated_eval_tokens": 19296 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a grab bag of unrelated Transformers/model-specific bugs. The only soft edge that looks plausibly like the same underlying defect is the Qwen2.5-VL position-id / rope-index regression pair.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45325 is the clearest root-cause report: it points to `get_rope_index` incorrectly scaling still-image temporal `position_ids` by `tokens_per_second` in Qwen2.5-VL. That is more specific and more actionable than the companion symptom report.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45325 is the best representative of the duplicate-like pair because it names the concrete failing code path and likely underlying fix. The rest of the set does not form one coherent duplicate cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer issues, but one is about runtime post-processor updates and the other about BOS/EOS insertion in a specific tokenizer; different bugs." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "`ModelOutput` key handling and Gemma-4 FSDP2 `shared_kv_states` rebuilding are unrelated code paths." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "A torch 2.9 `flex_attention` compile failure is not the same as broad remote-code loading regressions." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer method-name conflict and Qwen3 auto device-mapping CUDA assert are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "Both mention Transformers v5 regressions, but one is `_is_hf_initialized` and the other is non-persistent buffers; different failures." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper model loading and Float8 storage lookup are different error modes." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Generic loading noise is not the same as tokenizer loading failure for a specific model." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading failure and CLIPTokenizer `model_max_length` behavior are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both involve Qwen2-VL fine-tuning, but multi-GPU training and multi-image iterable dataset failures are different bugs." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Flash-attention training degeneration and zero-loss single-label classification are distinct issues." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Multi-image prompt handling and still-image temporal position-id scaling are different Qwen2.5-VL failures." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Model loading failure for Qwen2.5-GGUF and missing `pad_token_id` on Llama4Config are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Batched-vs-single MIMI padding-mask mismatch and Gemma3 all-padding-window NaNs are different bugs." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Unexpected `_is_hf_initialized` init arg and Float8 storage lookup are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 device-mapping crash and Mistral tokenizer regex patch crash are different code paths." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "`torch.export`/`torch_compilable_check` and bfloat16 dtype mismatches are separate problems." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Backend packaging for pip extras and PaddleOCR-VL load failure in vLLM are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "Initializer flag regression and dtype mismatch/OOM behavior are not the same bug." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 model-init regressions, but one is about `base_model_prefix` loading and the other about custom initialization; not clearly the same defect." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "`ModelOutput` field assignment and non-persistent buffer junk values are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and `init_empty_weights` argument handling are different issues." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and Perceiver resolution/interpolation failure are not the same bug." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied weights/lm_head, but one is a broken tie at model config time and the other is serialization inconsistency; different code paths." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Separate model-loading failures for different models." + }, + { + "left": "issue:43828", + "right": "issue:44683", + "accept": false, + "reason": "Autocast dtype mismatch and compiled flex_attention failure are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Fine-grained FP8 config failure and GGUF loading failure are different problems." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "`ModelOutput` key assignment and bfloat16 dtype mismatch are unrelated." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper loading failure and `torch.device(\"meta\")` loading regressions are different classes of bugs." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk values and `ModelOutput` key assignment are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Multiple-images-per-prompt failure and video `vision_position_ids` bug are distinct Qwen2.5-VL issues." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": true, + "reason": "Both reports point to the Qwen2.5-VL position-id/rope-index path; one is the root-cause description and the other is a symptom on video inputs, so they plausibly collapse to one fix." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Int4 quantization memory growth and Sam3Video OOM are not the same underlying issue." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with `inputs_embeds`/`past_key_values` and Qwen2.5-VL multi-image finetuning failures are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected init argument handling and strict config loading for `granite_speech` are different problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet: it treats the set as mostly unrelated, and the only accepted soft edge (45325/45381) is plausibly supported by the issue titles around the same Qwen2.5-VL position-id/rope-index path. The other pair judgments are conservative and do not overstate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 10, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43404", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43632", + "issue:43701", + "issue:43708", + "issue:43720", + "issue:43746", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:44186", + "issue:44265", + "issue:44423", + "issue:44466", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45357", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:43526|issue:43883", + "issue:43317|issue:43873", + "issue:43606|issue:44265", + "issue:43881|issue:44991", + "issue:43701|issue:45325", + "issue:44186|issue:44265", + "issue:43632|issue:45563", + "issue:43262|issue:43746", + "issue:43606|issue:43819", + "issue:44610|issue:45325", + "issue:43454|issue:43550", + "issue:43377|issue:44610", + "issue:43454|issue:45072", + "issue:40990|issue:45584", + "issue:43572|issue:45759", + "issue:43377|issue:44898", + "issue:39692|issue:40444", + "issue:44466|issue:45357", + "issue:43296|issue:44991", + "issue:43296|issue:44877", + "issue:43792|issue:44683", + "issue:43454|issue:43720", + "issue:43873|issue:45701", + "issue:41720|issue:44977", + "issue:45632|issue:45684", + "issue:43404|issue:45357", + "issue:44423|issue:45406", + "issue:44186|issue:45072", + "issue:43577|issue:43708", + "issue:34634|issue:35707", + "issue:35707|issue:41720", + "issue:43873|issue:44756" + ], + "prepared_review_unit_hash": "2eded9273d7dc0f0f44cc945ade98ef2c3bcaf343aa321dd9654af051897cec6", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37537, + "estimated_input_tokens": 9385, + "estimated_eval_tokens": 19026 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a loose thematic bundle of unrelated Transformers bugs, not a true duplicate cluster. None of the soft edges look safe to merge; 43873 is the broadest and most active issue, but the overall cluster is too heterogeneous for a strong canonical.", + "confidence": 0.88, + "canonical_issue_reason": "issue:43873 is the broadest open report here, with the most discussion/inbound references and an umbrella framing around offloading/quantization problems; it is the least-bad canonical issue choice for triage.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best available issue to anchor the cluster because it is open, active, and general enough to serve as a catch-all for nearby offloading complaints, even though the rest of the set is not truly duplicate-related.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "Different bugs: one is a BEiT image processor label-reduction error, the other is a Molmo tied-weights attribute error." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both mention offloading/quantization, but one is a specific gpu+cpu offload load failure for a dequantized model while the other is a broader offloading complaint." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "Bark CPU-offload device mismatch and torch.export failures with torch_compilable_check are unrelated code paths." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "A model load failure and a tokenizer loading regression are different failure modes." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint key mismatch is unrelated to Qwen2.5-VL rope-index scaling on still images." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crashes on NER/padding are not the same issue as export failures with torch_compilable_check." + }, + { + "left": "issue:43632", + "right": "issue:45563", + "accept": false, + "reason": "Transformers v5 flag regression and a stale generate warning are unrelated bugs." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Sampling-rate defaulting in audio chat templates is unrelated to GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "CPU offload device mismatch and DAC latent/STE mismatch are different audio-model bugs." + }, + { + "left": "issue:44610", + "right": "issue:45325", + "accept": false, + "reason": "Processor output resolution mismatch and Qwen2.5-VL temporal position scaling affect different paths." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Tied lm_head weights and torch.compile SDPA failures are not the same underlying defect." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Missing padding-mask support in MIMI is unrelated to OmDet-Turbo\u2019s image-size mismatch." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "A tied-weights serialization bug is not the same as bfloat16 dtype mismatches in CI." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and Whisper empty-transcription failures are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to AutoModelForCausalLM.from_config text_config unwrapping." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI batch-padding behavior and Perceiver non-default-resolution behavior do not share the same bug." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc-example errors are not the same as Qwen2.5-VL IterableDataset multi-image fine-tuning failures." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "lm_head.weight serialization inconsistency and incorrect visual-encoder keys are different save_pretrained problems." + }, + { + "left": "issue:43296", + "right": "issue:44991", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM and tokenizer loading for est-roberta are unrelated." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "A vLLM model load failure is not the same as strict config blocking granite_speech config loading." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper runtime failure and compiled flex_attention failing on torch>=2.9 are different issues." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Tied lm_head weights and unpacking packed BitNet weights during accelerate loading are separate bugs." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Offloading/quantization behavior is unrelated to version-dependent tokenization changes." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3 auto device-map cuda asserts and Qwen3.5 flash-attention generation failures are different code paths." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collisions for local models and read-only permission propagation in save_pretrained are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 lm_head tying and Qwen3.5 visual-encoder key serialization are different model-specific bugs." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Continuous-batching multimodal serve crashes and Gemma4Processor missing _tokenizer are distinct failures." + }, + { + "left": "issue:43632", + "right": "issue:45563", + "accept": false, + "reason": "Transformers v5 initialization flag breakage and a stale paged-generate warning are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Quantization/offloading complaints and disabling mmap on Strix Halo to avoid OOM are not the same defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 11, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43388", + "issue:43421", + "issue:43450", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43720", + "issue:43749", + "issue:43782", + "issue:43881", + "issue:44186", + "issue:44292", + "issue:44361", + "issue:44387", + "issue:44479", + "issue:44492", + "issue:44509", + "issue:44534", + "issue:44610", + "issue:44671", + "issue:44743", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44991", + "issue:45059", + "issue:45161", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45704" + ], + "soft_pairs": [ + "issue:43749|issue:44534", + "issue:43526|issue:43881", + "issue:44877|issue:44991", + "issue:42617|issue:42915", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:36331|issue:42915", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:44387|issue:45704", + "issue:44479|issue:44918", + "issue:36331|issue:42617", + "issue:43316|issue:44913", + "issue:42915|issue:43317", + "issue:41720|issue:43322", + "issue:40990|issue:45701", + "issue:43550|issue:43606", + "issue:43295|issue:45701", + "issue:41720|issue:45161", + "issue:44671|issue:44743", + "issue:43531|issue:43572", + "issue:44292|issue:44479", + "issue:41720|issue:42617", + "issue:44186|issue:44361", + "issue:36010|issue:42617", + "issue:43540|issue:43782", + "issue:45406|issue:45464", + "issue:41720|issue:44292", + "issue:43421|issue:45701", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:43388|issue:45059", + "issue:42915|issue:43322", + "issue:43606|issue:43720" + ], + "prepared_review_unit_hash": "0ae3c7367f13b2bf9837e92fb3cecb99bd43c72c7c1b8b30b4a99d24eddd666d", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 36943, + "estimated_input_tokens": 9236, + "estimated_eval_tokens": 18728 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a broad semantic bucket of unrelated Transformers issues, mostly around model loading, tokenizers, processors, and device/offload behavior. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU/RAM-efficient loading vs non-persistent buffer corruption; different failure modes." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BEiT label reduction bug vs GLM-4V loading failure; unrelated components." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Config strictness vs tokenizer-loading regression; same broad area, not same bug." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel runtime failure vs Qwen3-MoE FineGrainedFP8 loading issue." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video batching shape bug vs tokenization-version regression; different subsystems." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "SDPA torch.compile bug vs BitNet packed-weight unpacking bug; different code paths." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "CustomTrainer argument mismatch vs Qwen3-MoE FP8 loading; unrelated." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "OmDet input-size mismatch vs Perceiver resize/interpolation issue; different models." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash vs OmDet processor resolution mismatch; unrelated." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Int4 CUDA memory regression vs apex RMSNorm leak; different root causes." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Video-input regression vs embedding unpacking/TRL trainer issue; different paths." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Trainer loss signature bug vs 3d_parallel runtime failure." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Gemma3 config API mismatch vs GPTNeoX rotary_pct reload bug." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Qwen3-MoE FP8 loading vs dequantized model offload loading; distinct loading issues." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 auto-device-map CUDA assert vs Llava Next segfault; unrelated failures." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Perplexity/evaluation issue vs tokenizer-version behavior change." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba compile/SDPA bug vs Bark CPU-offload device mismatch." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor.tokenizer regression vs tokenization-version change; different concrete breakages." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Qwen3 auto-device-map assert vs GPT-OSS MoE tensor-parallel issue." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT MLM output issue vs Qwen3 recurrent-state caching bug." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Sliding-window MoE issue vs missing pad_token_idx config field." + }, + { + "left": "issue:44292", + "right": "issue:44479", + "accept": false, + "reason": "Qwen-3 NVFP4 runtime error vs Qwen3.5 video-input regression." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Auto device mapping assert vs 3d_parallel execution failure; different components." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "LayoutLMv2 tokenizer padding crash vs MLukeTokenizer task AttributeError." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "GenerationMixin import break vs 3d_parallel runtime failure; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Video-processing ValueError vs Qwen3VL weight-only loading error." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer vs Qwen3.5 streaming chat failure; different models and paths." + }, + { + "left": "issue:41720", + "right": "issue:44292", + "accept": false, + "reason": "Auto device-map CUDA assert vs NVFP4 runtime error; different quantization/device issues." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Runtime special-token/post-processor update bug vs tokenizer-version behavior change." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Void segmentation-map processing vs Bark voice_preset issue; unrelated processors." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "Cache-strategy typo vs docs mentioning removed pipeline tasks." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Mask2Former gather_for_metrics bug vs SAM3 text/bbox behavior; different data paths." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3-MoE FP8 loading vs Llava Next segmentation fault; unrelated failures." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Bark CPU-offload device mismatch vs BitNet packed-weight unpacking bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 12, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:33666", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43606", + "issue:43653", + "issue:43746", + "issue:43782", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44186", + "issue:44220", + "issue:44368", + "issue:44451", + "issue:44514", + "issue:44545", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44671", + "issue:44843", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45356", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45704", + "issue:45759" + ], + "soft_pairs": [ + "issue:44514|issue:44545", + "issue:43550|issue:43653", + "issue:43531|issue:45759", + "issue:43606|issue:43653", + "issue:43421|issue:43927", + "issue:34567|issue:35707", + "issue:44368|issue:45357", + "issue:44898|issue:45072", + "issue:43873|issue:45704", + "issue:44451|issue:44991", + "issue:41720|issue:43746", + "issue:44062|issue:44451", + "issue:43421|issue:43653", + "issue:42886|issue:44843", + "issue:44987|issue:45042", + "issue:45588|issue:45759", + "issue:33666|issue:35707", + "issue:43531|issue:44589", + "issue:43421|issue:44186", + "issue:43381|issue:43844", + "issue:39692|issue:44610", + "issue:44918|issue:44936", + "issue:45081|issue:45356", + "issue:44625|issue:45479", + "issue:43525|issue:43531", + "issue:43782|issue:45381", + "issue:43994|issue:44671", + "issue:34634|issue:41720", + "issue:43381|issue:45704", + "issue:43596|issue:44220", + "issue:39692|issue:43873" + ], + "prepared_review_unit_hash": "8cb002688b153384541072a1b40781a2eb83e31cd3bb28dfe75fa08ad92e3d13", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37274, + "estimated_input_tokens": 9319, + "estimated_eval_tokens": 18894 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous tokenizer/model/runtime bug reports with one clear duplicate pair and a few loose semantic similarities, so only the exact duplicate should be merged.", + "confidence": 0.71, + "canonical_issue_reason": "Issue 44514 is the earliest and clearest report of the exact Qwen2_5_VLProcessor.apply_chat_template batched-input/padding=False crash, making it the best canonical issue for the confirmed duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "44514 is the best representative because it precisely captures the concrete failure mode and is directly duplicated by 44545.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same Qwen2_5_VLProcessor.apply_chat_template crash on batched input with padding=False; identical underlying bug." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Different subsystems and failures: torch.compile+SDPA on Bamba vs tokenizer special-token registration." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen3-family configs, but one is sliding_window behavior and the other is text_config unwrapping; not the same bug." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to BigBirdTokenizer mask-token decode output." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Both touch token/special-token handling, but one is runtime post-processor updates and the other is save/load of custom token IDs." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "Trainer token-count tracking and progressive generation with inputs_embeds/past_key_values are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A warning about tie_word_embeddings during LoRA fine-tuning is unrelated to incorrect visual encoder keys on save_pretrained." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver interpolation bug and bfloat16 dtype mismatch in SwitchTransformers/TimmWrapperModel are different issues." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading expectations do not match a T5 RMSNorm memory-leak issue." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are loading regressions, but for different models and likely different tokenizer code paths." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3 auto device mapping cuda assert is unrelated to GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "AddedToken constructor argument clash is a different failure from loading ScandiBERT." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Runtime special-token post-processor updates are unrelated to BigBirdTokenizer empty decode output." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both involve HF_HUB_OFFLINE, but 44843 is a specific _patch_mistral_regex/model_info regression while 42886 is a broader cache-load failure." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Loading physical-intelligence/fast and PIL-backend torchvision requirements are not the same bug." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention aux-state crash and Qwen multimodal text_config unwrapping are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL and progressive generation with inputs_embeds are unrelated topics." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the missing Float8 storage type error." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "TokenizersBackend special-token updates and LayoutLMv2 tokenizer NER/padding crashes are different code paths." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Eval-mode gradient checkpointing limitation is unrelated to gradient blow-up under HfDeepSpeedConfig + ZeRO-3." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 doc/example errors and OmDet-Turbo processor size mismatch are different model-specific issues." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "TRL SFT unpacking of Qwen3.5 embeddings is unrelated to trainer.evaluate failing after trainer.train()." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both mention fix_mistral_regex/tokenizer regression, but one is a hard crash in Mistral loading and the other is a Kimi-K2.5 codec-handling regression with a warning issue; not clearly the same bug." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Missing num_labels propagation in Qwen3.5 configs is unrelated to zero-loss single-label classification behavior across models." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Llama4Config pad_token_id missing and Qwen3-MoE sliding_window are different config bugs." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3VL weight_only loading and qwen2.5-vl video vision_position_ids are different multimodal bugs." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "SigLIP2 AutoModel/pipeline output mismatch and CamemBERT masked LM predictions are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping failures are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Gradient-checkpointing eval-mode behavior is unrelated to T5 apex.FusedRMSNorm memory leak." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "DeepSpeed ZeRO-3/BertModel index error and _torch_extract_fbank_features() are different failures." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 documentation/example errors are unrelated to quantization offloading behavior." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: it identifies only the clearly duplicated Qwen2_5_VLProcessor.apply_chat_template batched-input/padding=False pair (44514/44545) and rejects the rest as distinct or only loosely similar. No overstatement or mergeability issue is apparent." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 13, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:42915", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43575", + "issue:43577", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43873", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44448", + "issue:44488", + "issue:44561", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44756", + "issue:44811", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45381", + "issue:45479", + "issue:45704", + "issue:45759" + ], + "soft_pairs": [ + "issue:42915|issue:45759", + "issue:44220|issue:44661", + "issue:45183|issue:45479", + "issue:43618|issue:43697", + "issue:43540|issue:44008", + "issue:44077|issue:44625", + "issue:43720|issue:43819", + "issue:43575|issue:45704", + "issue:30064|issue:36010", + "issue:44756|issue:45759", + "issue:43716|issue:44008", + "issue:43335|issue:43756", + "issue:43653|issue:43720", + "issue:42915|issue:43746", + "issue:43746|issue:45381", + "issue:43746|issue:43873", + "issue:44843|issue:45081", + "issue:43550|issue:45072", + "issue:44186|issue:44898", + "issue:43421|issue:44811", + "issue:43550|issue:43819", + "issue:43577|issue:43818", + "issue:43643|issue:44877", + "issue:44062|issue:44488", + "issue:43531|issue:43643", + "issue:43540|issue:45381", + "issue:44448|issue:44671", + "issue:43653|issue:43819", + "issue:43782|issue:44977", + "issue:44561|issue:45020" + ], + "prepared_review_unit_hash": "efbfab781e704ddb17df5a177a2a93e46ff461c6a346818669fb1889e40e35c3", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36368, + "estimated_input_tokens": 9092, + "estimated_eval_tokens": 18440 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated model- or subsystem-specific bugs. A few are loosely adjacent (notably around tokenizer/Mistral helpers and remote_code regressions), but none of the soft pairs look like true duplicates of the same concrete bug/change.", + "confidence": 0.86, + "canonical_issue_reason": "If a canonical issue is needed, issue:45020 is the broadest umbrella-style report in the set (recent versions breaking remote_code models). It is not an exact duplicate of the others, but it is the closest general anchor for the cluster\u2019s theme of version-related regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue:45020 is the best representative issue because it is open, broadly scoped, and captures a recurring compatibility/regression class rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:45759", + "accept": false, + "reason": "Both mention Qwen configs, but one is FineGrainedFP8Config failure and the other is missing text_config unwrapping in composite multimodal configs; different code paths and fixes." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Different areas entirely: audio feature extraction vs tokenizer mapping/model registration logic." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "One is input validation/XOR error messaging, the other is a loss-function/label semantics bug; not the same defect." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIP output attentions regression and RTDetrV2 output drift are unrelated model bugs." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Video input handling in Qwen3OmniMoe is unrelated to the Gemma3n variable-name collision in forward()." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "PatchTSMixer post_init policy and Qwen3.5 num_labels propagation are unrelated configuration issues." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Packed-weight loading in BitNet and DAC latent/STE mismatch are different concrete bugs." + }, + { + "left": "issue:43575", + "right": "issue:45704", + "accept": false, + "reason": "TP OOM when loading a Qwen model and T5 apex RMSNorm memory leak are distinct memory problems in different paths." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Image segmentation map processing and a GenerationMixin import error are unrelated." + }, + { + "left": "issue:44756", + "right": "issue:45759", + "accept": false, + "reason": "Strix Halo mmap/OOM behavior is unrelated to Qwen multimodal config unwrapping." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Mistral image-preprocessor dtype mismatch and Gemma3n tensor attribute collision are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Sparse encoder layer creation and Smollm3 RoPE layer dropping are different model-configuration mistakes." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration and BitNet packed-weight loading do not share the same underlying bug." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Fine-grained FP8 config failure and GraniteSpeech PEFT checkpoint loading are separate issues." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "PEFT local checkpoint loading and Qwen2.5-VL video position ids are unrelated." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "GraniteSpeech checkpoint loading and quantization offloading behavior are different code paths." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve _patch_mistral_regex, but one is offline model_info access and the other is an AttributeError on backend_tokenizer; same helper, different failures and fixes." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Bamba torch.compile+SDPA and SwitchTransformers/TimmWrapper dtype mismatches are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes and Perceiver interpolation failure are different model-specific bugs." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token/post-processor updates and Whisper batch_decode skip_special_tokens handling are related to tokenization, but not the same concrete bug." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "torch.compile SDPA failure and DAC forward/from_latents mismatch are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing issues are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "trust_remote_code missing fields and strict granite_speech config loading are distinct configuration-loading problems." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken special-argument error and sleng-bert model loading failure are not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and trust_remote_code config field loss are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are v5 output regressions, but they affect different models and likely different changes." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Tokenizer special-token registration and DAC latent conversion mismatch do not share a concrete underlying defect." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL weight_only loading failure and Qwen3.5 flash-attention generation issues are separate multimodal/runtime problems." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Removal of is_torch_fx_available is one specific remote_code breakage, while 45020 is a broad umbrella report that likely covers multiple unrelated failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 14, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:42175", + "issue:43262", + "issue:43322", + "issue:43329", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:43994", + "issue:44060", + "issue:44186", + "issue:44368", + "issue:44442", + "issue:44485", + "issue:44509", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44821", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45538", + "issue:45600", + "issue:45685", + "issue:45701" + ], + "soft_pairs": [ + "issue:43322|issue:45685", + "issue:43825|issue:43994", + "issue:44821|issue:45084", + "issue:43825|issue:43827", + "issue:30064|issue:36331", + "issue:44485|issue:44509", + "issue:43577|issue:43582", + "issue:44186|issue:44442", + "issue:43606|issue:45072", + "issue:43452|issue:44991", + "issue:34634|issue:36010", + "issue:44805|issue:44936", + "issue:42175|issue:45081", + "issue:44610|issue:45072", + "issue:45081|issue:45406", + "issue:44060|issue:44368", + "issue:43650|issue:43906", + "issue:43720|issue:45072", + "issue:44671|issue:45701", + "issue:43404|issue:43782", + "issue:43582|issue:44857", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:45084|issue:45538", + "issue:43644|issue:43749", + "issue:43329|issue:45600", + "issue:43653|issue:44912" + ], + "prepared_review_unit_hash": "e613805d1a505ef1b774c3671c3e6432f2501f054f9c88849c7066afb63a15ce", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35991, + "estimated_input_tokens": 8998, + "estimated_eval_tokens": 18252 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a very noisy, mostly false-positive similarity cluster. The items span many unrelated bugs across processors, tokenizers, loading, quantization, training, and docs; none of the soft pairs look like the same underlying defect.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 43825 is the clearest representative of the only coherent subtheme in the set: v5 pipeline-removal behavior/error messaging. It is concrete and has inbound references, while most other items are unrelated point bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "43825 is the best single issue to anchor this cluster, but only as a loose representative of the v5 pipeline-removal/docs subgroup; the overall bucket is too heterogeneous for a true canonical duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Different subsystems and failure modes: Llava Next load-time segfault vs an MPS histogram op unsupported for Int in moe." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "One is a v5 pipeline error-message/docs issue; the other is incorrect SigLIP2 outputs. Same broad area, but not the same bug." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-node compilation are unrelated code paths." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Both mention removed pipeline tasks, but one is runtime error messaging and the other is documentation cleanup." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "ImageProcessor void segmentation maps and CustomTrainer compute_loss kwargs are unrelated issues." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to pipeline-removal documentation." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype loading bug and AppleSilicon allocator TypeError are separate problems." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Two tokenizer bugs, but with different models and failure mechanisms." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "CPU-offload device mismatch and bfloat16 dtype mismatch are different model-loading/runtime defects." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "gguf_file loading breakage and est-roberta tokenizer loading failure are not the same underlying issue." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset bug and GenerationMixin import error are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Mask-shape IndexError and trainer.evaluate() failure after train() do not share a concrete root cause." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Packaging/backend dependency issue and a Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "OmDet-Turbo input-size mismatch and dtype mismatches are different bug classes." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both involve tokenizer/processor internals, but one is a Mistral regex patch crash and the other is a Gemma4Processor attribute error." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weight warnings, but they refer to different models and different warning logic." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "'ADD THE DATA' is not a concrete duplicate candidate for the isolated reproduction issue." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight loading failure in BitNet and bfloat16 dtype mismatch are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT MLM regression and version-dependent tokenization changes are not the same bug." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Mistral3 tied-weight bug and Qwen3VL weight_only loading error are separate multimodal loading issues." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "AppleSilicon allocator TypeError and CUDA AMP loss crash are different platform-specific problems." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and DAC from_latents/STE mismatch are unrelated audio bugs." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and RTDetrV2 output differences are distinct vision bugs." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation TypeError and CLIPTokenizer model_max_length behavior are unrelated." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer initialization junk and FSDP CPU RAM-efficient loading are different low-level loading bugs." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Undefined variables in multimodal token counting and stale auto_mappings references are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and MXFP4 quantization loading are different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 15, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:41720", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43638", + "issue:43643", + "issue:43645", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:43638|issue:44936", + "issue:43746|issue:44811", + "issue:38175|issue:44610", + "issue:44589|issue:45042", + "issue:43854|issue:44977", + "issue:43454|issue:43577", + "issue:43526|issue:44554", + "issue:36010|issue:43645", + "issue:44568|issue:45488", + "issue:39692|issue:44912", + "issue:34634|issue:36331", + "issue:43257|issue:43329", + "issue:43819|issue:43927", + "issue:43720|issue:44610", + "issue:43749|issue:44291", + "issue:43550|issue:44912", + "issue:43262|issue:44811", + "issue:44568|issue:45356", + "issue:43531|issue:45042", + "issue:36010|issue:36331", + "issue:43643|issue:45759", + "issue:34567|issue:40990", + "issue:43329|issue:43450", + "issue:43329|issue:44479", + "issue:44849|issue:45701", + "issue:43257|issue:43931", + "issue:43697|issue:45357", + "issue:43452|issue:43582", + "issue:41720|issue:43540" + ], + "prepared_review_unit_hash": "efa187047fa892e688b66e665d351be5e263451715dcf1968e82788c51be2033", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36755, + "estimated_input_tokens": 9189, + "estimated_eval_tokens": 18634 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items form a loose collection of unrelated Transformers bugs. The suggested soft pairs share broad subsystems at best, but not the same concrete root cause, so none should be merged as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43749 is the strongest representative of the cluster because it is a broad, high-impact loading regression with multiple references and discussion, making it the best anchor issue if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43749 is the most central and widely impacted bug report in the set; it is the best issue to keep as the representative anchor, though it does not subsume the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Both mention trainer behavior, but one is a zero-size index error under ZeRO3 with a non-pretrained model and the other is evaluate() failing after train(); different failure modes and code paths." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Local checkpoint loading with PEFT adapters and Whisper batch_decode skip_special_tokens are unrelated features and bugs." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 zero probabilities and OmDet-Turbo processor/model size mismatch are different model-specific problems." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup failure and PIL backend requiring torchvision are separate runtime dependency issues." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "GLM-4.7 test loading failure and Qwen3.5 flash-attention generation issue do not share the same concrete defect." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision weight tying and BLIP2 dtype propagation are distinct model-loading bugs." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BEiT label reduction and an MPS attention correctness issue are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import breakage and notebook custom-model initialization failures are both v5 regressions, but not the same bug." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both are tokenizer regressions, but one is add_special_tokens/BOS-EOS handling and the other is tokenizer.json pre-tokenizer overriding; different root causes." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation/example problems for SigLIP2 and MXFP4 quantization fallback in git-oss are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice_preset and CustomTrainer.compute_loss kwarg handling are unrelated API bugs." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed and multimodal video token counting use different code paths and symptoms." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC from_latents/STE mismatch and DiaConfig save-load token ID loss are different model/serialization bugs." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading and OmDet processor output-size mismatch are not the same underlying issue." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both concern loading, but FSDP CPU RAM efficient loading and init_empty_weights/_is_hf_initialized are separate regressions." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile with SDPA on Bamba and MXFP4 fallback on git-oss are unrelated model/runtime bugs." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sample-rate defaults and Whisper batch_decode token skipping are separate processor behaviors." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and different parts of the tokenization pipeline." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window and PIL backend torchvision dependency are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin and passing num_items_in_batch to compute_loss are separate incompatibilities." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading and composite Qwen config unwrapping are both config-related, but not the same concrete defect." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token accounting and high perplexity on gpt-oss-20b are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Undefined video-token helper names and batched video processor shapes are different video pipeline bugs." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "The video-token helper bug and the v5.3 video-input regression overlap only at a high level; the concrete root causes differ." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 hidden-states output and version-dependent tokenization changes are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE accelerate/deepspeed weight conversion and Qwen3-VL weight-shape mismatch are different loading problems." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output drift and Qwen3.5 save_pretrained key mismatch are separate regressions." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "gguf_file/from_pretrained breakage and Apple Silicon caching_allocator_warmup TypeError are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Both involve Qwen3-family video/device issues, but one is CUDA assert under auto device mapping and the other is a video-input ValueError in Qwen3OmniMoe; not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 16, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43540", + "issue:43577", + "issue:43643", + "issue:43646", + "issue:43696", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43906", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44737", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44898", + "issue:44912", + "issue:44964", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45137", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45538", + "issue:45588" + ], + "soft_pairs": [ + "issue:42915|issue:43742", + "issue:44291|issue:45042", + "issue:33357|issue:34567", + "issue:43317|issue:45538", + "issue:44987|issue:45538", + "issue:44479|issue:45381", + "issue:43927|issue:44912", + "issue:43540|issue:44560", + "issue:42915|issue:44821", + "issue:43257|issue:43756", + "issue:43577|issue:45072", + "issue:42915|issue:45538", + "issue:43540|issue:44479", + "issue:43257|issue:43696", + "issue:45137|issue:45405", + "issue:38175|issue:44898", + "issue:44737|issue:45588", + "issue:44062|issue:44991", + "issue:43742|issue:44291", + "issue:43906|issue:45381", + "issue:43646|issue:43749", + "issue:43749|issue:44756", + "issue:36010|issue:42175", + "issue:44062|issue:45081", + "issue:34567|issue:36331", + "issue:43643|issue:45375", + "issue:43493|issue:43994", + "issue:42175|issue:43824", + "issue:43452|issue:44488", + "issue:43526|issue:45479", + "issue:44291|issue:44821", + "issue:44792|issue:44964" + ], + "prepared_review_unit_hash": "7a4afd73b2344db050c82714bcdb3496455ebeb3ea8d4f25666480d2fc2e0d36", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37440, + "estimated_input_tokens": 9360, + "estimated_eval_tokens": 18976 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous and does not look like a single duplicate family. I only found two soft-edge pairs that plausibly describe the same underlying bug; the rest are different models, different subsystems, or different failure modes.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue fits: most items are unrelated bugs across different models/subsystems, with only a couple of tight duplicate-style pairs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44964 is the clearest representative user-facing loading regression, with a specific model and reproducible failure in the current transformers version.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different models and failures: Qwen3Moe FP8 config vs MobileLLM key error." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Unrelated bugs: init_empty_weights arg handling vs PIL backend torchvision dependency." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS bus error in CLIP loading vs TrainerState token-count tracking bug." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Different areas: dequantized model offload failure vs tokenizer max_length constant." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Model-loading regression for physical-intelligence/fast vs CLIPTokenizer max_length issue." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Both describe the same Qwen video-input regression in transformers 5.3.0, centered on incorrect video/vision position handling." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig save/load corruption is unrelated to MXFP4 quantization fallback." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-related but on different Qwen model paths and different errors." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3Moe FP8 failure is unrelated to AutoImageProcessor URL loading." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model families and bugs: weight conversion with accelerate/deepspeed vs RoPE-layer omission." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype mismatches, but they affect different models and code paths." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Qwen3Moe quantization bug vs tokenizer max_length bug." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Similar domain, but different Qwen models and not clearly the same underlying bug." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Qwen3 MOE conversion issue is unrelated to GPT-oss OOM." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error vs PEFT version metadata problem." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision-model bugs, but they are different models and different failure modes." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU device bug is unrelated to flash-attention aux-state crash." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Tokenizer-related, but one is an AddedToken TypeError and the other is a model-specific tokenizer load failure without enough evidence they are the same bug." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Different failures: MobileLLM key error vs unexpected _is_hf_initialized argument." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Isolated reproduction of a different issue vs Qwen2.5-VL video-position regression." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model initialization breakage is unrelated to FSDP CPU RAM efficient loading." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Both concern loading/memory, but one is FSDP-specific and the other is mmap OOM on Strix Halo." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to missing TensorFlow in the torch extra." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer AddedToken error and Mistral regex patch crash are different code paths." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "TrainerState num_input_tokens_seen and custom compute_loss signature are separate trainer API regressions." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config fields, but the failures are different and model-specific." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Both are SigLIP2 correctness bugs on the same model; one reports JAX/HF discrepancy and the other nonsensical outputs from the same implementation." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Missing TensorFlow backend and missing Qwen2.5-VL export/import are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "gguf_file/from_pretrained breakage is not the same as a specific model failing to load." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to sequence-classification zero loss." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to AutoImageProcessor URL loading." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Janus test failure and Phi-4-multimodal load failure are different multimodal bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. It correctly treats the cluster as mostly heterogeneous, and the two accepted soft-edge pairs are plausible same-bug families based on the issue titles and version/model overlap. I don\u2019t see a clear overstatement in the rejected pairs." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 17, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:34689", + "issue:38175", + "issue:41762", + "issue:42175", + "issue:43295", + "issue:43452", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43819", + "issue:44361", + "issue:44442", + "issue:44466", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44977", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45381", + "issue:45405", + "issue:45600" + ], + "soft_pairs": [ + "issue:28282|issue:34689", + "issue:45042|issue:45081", + "issue:44484|issue:44704", + "issue:45405|issue:45600", + "issue:43756|issue:45325", + "issue:43742|issue:44589", + "issue:43697|issue:45216", + "issue:28282|issue:29127", + "issue:44514|issue:45381", + "issue:43643|issue:44561", + "issue:43531|issue:44821", + "issue:44625|issue:44877", + "issue:43582|issue:44977", + "issue:43452|issue:43577", + "issue:43720|issue:44898", + "issue:44514|issue:45290", + "issue:43452|issue:44843", + "issue:42175|issue:44488", + "issue:44466|issue:45005", + "issue:43819|issue:44811", + "issue:43295|issue:45356", + "issue:41762|issue:44936", + "issue:43653|issue:44568", + "issue:24643|issue:29127", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:43653|issue:44361" + ], + "prepared_review_unit_hash": "67fe28b40af45649a84f4e03bcd7c5dccd48987266bce7857149413edca7114d", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35540, + "estimated_input_tokens": 8885, + "estimated_eval_tokens": 18026 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated model-loading, tokenizer, config, and backend regressions. I only see one plausible duplicate edge around tied-weights serialization in v5; the rest should stay separate.", + "confidence": 0.74, + "canonical_issue_reason": "issue:45005 is the broadest statement of the tied-weights regression and best captures the shared underlying problem; issue:44466 looks like a more specific manifestation of the same v5 serialization bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45005 is the best representative issue for the only likely duplicate subgroup because it describes the core tied-weights problem at a higher level.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Both are model-loading failures, but one is a missing PyTorch dependency and the other is a specific Llama 3.2 Vision regression; different causes and fixes." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "These are unrelated: one is a torchvision dependency regression in PIL image processors, the other is a Mistral regex/tokenizer attribute crash." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "One is about the default `max_shard_size` in `save_pretrained`, the other about forwarding kwargs in `AutoProcessor.from_pretrained`; not the same bug." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "Different maintenance issues: PEFT version pinning versus stale auto-mapping references to removed configs." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both involve position/rope-related behavior, but they affect different models and different code paths; not the same concrete defect." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "A key error while loading MobileLLM is unrelated to the Float8 storage lookup failure." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions in different model families: RTDetrV2 output changes versus Qwen3.5 checkpoint saving." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Missing PyTorch in the environment is not the same as poor error messaging for LayoutLMv3 boxes." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both mention chat/processor pipelines, but one is a batched chat-template crash and the other is a Qwen2.5-VL video position-id bug." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "One is missing fields from `AutoConfig.from_pretrained` with `trust_remote_code`, the other is a v5 breakage from removing `is_torch_fx_available`." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "A Qwen3-MoE sliding-window bug and an AutoImageProcessor URL-loading issue are unrelated." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Different config propagation problems affecting different model families." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3.5 flash-attention generation behavior." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "One is a gguf/loader regression, the other is dtype propagation on BLIP-2; they do not share the same underlying bug." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "Packed-weight handling in accelerate loading is unrelated to Perceiver positional interpolation at non-default resolution." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Same general API area, but the failures are different edge cases: batched padding behavior versus assistant tool-call messages without content." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both involve loading helpers, but one is gguf loading and the other is an offline-mode regression in `_patch_mistral_regex`." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Packaging/backend selection and a specific model-load failure are not the same concrete issue." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": true, + "reason": "Both point to the same tied-weights/save_pretrained regression in v5 for translation models; one is the broad issue, the other a specific manifestation." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent conversion mismatch and Whisper batch_decode special-token handling are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Different regressions: processor/tokenizer access in custom model code versus codec and warning behavior in Kimi-K2.5 tokenization." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO-3 loading failure for Gemma3 is unrelated to `trainer.evaluate()` failing after training." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "BigBird special-token registration and mDeBERTa BOS/EOS insertion are different tokenizer bugs." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed `'weight' must be 2-D` is a training/runtime error, not a LayoutLMv3 error-message clarity issue." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP2 zero probabilities and the processor.tokenizer regression are unrelated." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-loading failures, but they affect different tokenizer classes and do not appear to share a single code path." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "A special-token registration bug in BigBird and an AttributeError in MLukeTokenizer are different issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet and is appropriately conservative. The only accepted duplicate edge, issue:44466 \u2194 issue:45005, is plausibly the same tied-weights / v5 save_pretrained regression, while the other pair rejections avoid overstating similarity and mostly distinguish different model families or code paths." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 18, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:28282", + "issue:30064", + "issue:32090", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:41720", + "issue:43122", + "issue:43262", + "issue:43329", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43825", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44821", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45084", + "issue:45325", + "issue:45356", + "issue:45357", + "issue:45440", + "issue:45588" + ], + "soft_pairs": [ + "issue:44464|issue:44743", + "issue:30064|issue:33666", + "issue:43577|issue:43697", + "issue:44843|issue:44991", + "issue:41720|issue:43906", + "issue:44479|issue:44936", + "issue:44977|issue:45356", + "issue:43688|issue:45440", + "issue:43577|issue:45588", + "issue:43531|issue:43742", + "issue:43653|issue:43927", + "issue:44464|issue:44977", + "issue:43550|issue:43927", + "issue:43550|issue:44361", + "issue:43122|issue:43906", + "issue:43504|issue:43720", + "issue:32090|issue:34567", + "issue:43504|issue:43550", + "issue:32090|issue:33666", + "issue:28282|issue:35141", + "issue:43504|issue:44610", + "issue:43452|issue:44451", + "issue:43688|issue:43749", + "issue:43329|issue:45325", + "issue:43742|issue:44821", + "issue:43756|issue:44913", + "issue:33666|issue:36010", + "issue:43525|issue:43572", + "issue:41720|issue:44464", + "issue:43493|issue:43825", + "issue:44849|issue:45357", + "issue:43262|issue:45084" + ], + "prepared_review_unit_hash": "126633ec37d95f89458e6c23d746d96ba3f643a00c520b6ec7377784d4003c45", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37415, + "estimated_input_tokens": 9354, + "estimated_eval_tokens": 18964 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated Transformer bugs/regressions across different models and subsystems; I did not find any true duplicate pairs. I picked the broadest model-loading regression as the canonical issue.", + "confidence": 0.64, + "canonical_issue_reason": "issue:43452 is the broadest, most central regression report here: it affects both AutoTokenizer.from_pretrained and AutoModelForCausalLM.from_pretrained via gguf_file handling, making it a good cluster anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43452 is concrete, reproducible, and broadly scoped enough to represent the loading-path regressions in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/runtime behavior, but they describe different failures in different code paths: compiled forward inconsistency vs cache/reset behavior in modular_qwen3_5." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Completely different problems: segmentation-map preprocessing versus Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different models and symptoms: BLIP2 dtype propagation vs RTDetrV2 output mismatch in v5." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer/loading regressions, but the titles point to different concrete failures and models; not enough to treat as the same bug." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Different failures: Qwen3 auto device mapping CUDA assert vs an isolated reproduction of another issue." + }, + { + "left": "issue:44479", + "right": "issue:44936", + "accept": false, + "reason": "Video-input regression in VLMs versus trainer lifecycle failure; unrelated code paths." + }, + { + "left": "issue:44977", + "right": "issue:45356", + "accept": false, + "reason": "Flash-attention generation bug in Qwen3.5 versus tokenizer codec/regex regression in Kimi-K2.5." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related at a high level, but they target different models and different implementation mismatches." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "BLIP2 dtype issue and flash_attention crash on s_aux=None are unrelated bugs." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to the MobileLLM loading KeyError." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Tokenizer special-token registration versus config custom-token persistence; different underlying defects." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Different generation failures with different triggers: compiled forward versus flash-attention." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile/SDPA failure is unrelated to DiaConfig save/load token-ID loss." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Different subsystems and failures: compile-time SDPA issue versus tokenizer AttributeError on tasks." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Tokenization-difference regression and an isolated reproduction issue are not clearly the same bug." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy-field model-loading bug versus packed-weight handling in accelerate loading; different code paths." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast TypeError and num_input_tokens_seen not updating are distinct trainer bugs." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Unrelated model-loading preset bug versus compile/SDPA failure." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer NoneType broadcast error is unrelated to Qwen2-VL multi-GPU training." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "ImportError for missing PyTorch and embedding reinitialization after resize are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Different models and failure modes: legacy field on load versus processor/model input-size mismatch." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are loading issues, but one is gguf_file handling for AutoTokenizer/AutoModelForCausalLM and the other is a model-specific load failure." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Different MoE/train-loading issues: auxiliary-loss normalization versus FSDP CPU RAM efficient loading." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Both are multimodal token/position bugs, but they affect different branches and different concrete calculations." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Model KeyError on load versus AutoImageProcessor-from-URL failure; unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "RoPE-layer dropping in a specific model versus a config field resetting on reload." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training bug versus missing GenerationMixin import; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are missing config fields after 5.0, but they concern different models and different fields, so not the same underlying bug." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "CUDA assert in Qwen3 auto device mapping is unrelated to chunked generation with compiled forward." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and pipeline translation-message regression are unrelated." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3.5 hidden-states bug versus incorrect visual encoder keys on save_pretrained; different issues." + }, + { + "left": "issue:43262", + "right": "issue:45084", + "accept": false, + "reason": "Audio processor chat-template sampling-rate default bug is unrelated to template compilation TypeError." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 19, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:36331", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43575", + "issue:43577", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43716", + "issue:43720", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43927", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44554", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44843", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45405", + "issue:45520", + "issue:45701", + "issue:45704", + "issue:45759" + ], + "soft_pairs": [ + "issue:43540|issue:43716", + "issue:43720|issue:43927", + "issue:43606|issue:43927", + "issue:43334|issue:43572", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:43577|issue:44554", + "issue:43688|issue:45704", + "issue:39692|issue:43493", + "issue:33666|issue:36331", + "issue:43720|issue:44361", + "issue:43334|issue:45759", + "issue:44964|issue:45405", + "issue:44479|issue:44625", + "issue:43540|issue:44977", + "issue:44488|issue:44843", + "issue:43493|issue:43844", + "issue:43756|issue:45083", + "issue:45200|issue:45229", + "issue:43257|issue:43299", + "issue:43278|issue:43844", + "issue:43824|issue:44589", + "issue:43646|issue:44466", + "issue:44589|issue:45520", + "issue:39692|issue:43295", + "issue:43688|issue:45701", + "issue:33357|issue:33666", + "issue:43504|issue:43606", + "issue:44423|issue:44734", + "issue:43572|issue:44291", + "issue:43927|issue:44361", + "issue:43504|issue:43653", + "issue:43575|issue:45405", + "issue:44625|issue:45759" + ], + "prepared_review_unit_hash": "f6594de271c2ecde4c4f34328ada6d53608fd59986ce71910646e74a82dc2128", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 38212, + "estimated_input_tokens": 9553, + "estimated_eval_tokens": 19362 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues spanning Qwen multimodal loading, dtype/device regressions, tokenizers, training, and docs. I do not see a single underlying bug that unifies the set, and none of the soft-edge pairs look mergeable as true duplicates.", + "confidence": 0.9, + "canonical_issue_reason": "No strong canonical issue: the items cover many distinct code paths and model families, so one issue cannot represent the whole cluster cleanly.", + "canonical_pr_reason": null, + "best_issue_reason": "If a representative must be chosen, issue 43299 is the closest to a recurring theme around Qwen3/Qwen3-VL MoE loading regressions, but it is still only a partial fit for the mixed cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43540", + "right": "issue:43716", + "accept": false, + "reason": "Different bugs: Qwen3OmniMoe video-processing failure vs Mistral-3 image-preprocessor/model dtype mismatch." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Unrelated failures: BitNet packed-weight loading vs DiaConfig token-ID persistence." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU-offload device mismatch is unrelated to DiaConfig save/load token-ID loss." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both are config attribute issues, but for different models and different missing fields; not the same bug." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "ImportError for missing PyTorch is unrelated to Trainer GPU broadcast rejecting NoneType." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Different symptoms and code paths: missing PyTorch vs MacOS bus error on a CLIP model." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype propagation bug is unrelated to the MPS attention correctness issue." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization in MoE models is unrelated to T5/apex memory leak behavior." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Both touch SigLIP2, but one is a docs example problem and the other is an implementation discrepancy; not the same concrete bug." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Qwen2-VL multi-GPU training request is unrelated to the custom trainer compute_loss signature regression." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet packed-weight loading and MLukeTokenizer task failure are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal configs, but one is missing pad_token_id and the other is from_config not unwrapping text_config; distinct bugs." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal is unrelated to the PEFT version bump issue." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression and num_labels propagation are different issues." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Different Qwen models and different failures: video processing vs flash-attention generation." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Loading a specific model failing is unrelated to the offline-mode mistral regex patch issue." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient inflation are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Smollm3 RoPE-layer discrepancy is unrelated to the qwen3_omni_moe helper function behavior." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Defaulting mm_token_type_ids and a Gemma4 multi-GPU OOM are not the same bug." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both are Qwen3 MoE loading regressions, but they affect different paths and failure modes; too broad to treat as one duplicate." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift during eval is unrelated to the ZeRO-3 gradient issue." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Missing Qwen2_5_VL import and missing Float8 storage type are unrelated runtime errors." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage is unrelated to inconsistent lm_head.weight serialization." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage lookup failure and flash_attn KeyError on Python 3.13 are different compatibility issues." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Docs example errors are unrelated to the processor.tokenizer / image-to-tokenizer regression." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization is unrelated to tokenization changes." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS CLIP bus error and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field model loading failure and CPU-offload device mismatch are unrelated." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve crashes, but with different root causes and code paths; not mergeable as one PR." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig and unexpected _is_hf_initialized argument are separate regression types." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig token-ID persistence and MLukeTokenizer task AttributeError are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Beit legacy-field loading and BigBirdTokenizer special-token registration are different bugs." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "Tensor-parallel OOM and a release-version pin issue are unrelated." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and AutoModelForCausalLM.from_config text_config unwrapping are related only broadly, not the same concrete defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 20, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:15354", + "issue:29942", + "issue:30333", + "issue:37428", + "issue:38175", + "issue:39401", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43606", + "issue:43688", + "issue:43701", + "issue:43844", + "issue:43873", + "issue:43957", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44464", + "issue:44466", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44792", + "issue:44849", + "issue:44898", + "issue:44964", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45405", + "issue:45412", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45701" + ], + "soft_pairs": [ + "issue:44792|issue:45405", + "issue:43606|issue:44112", + "issue:44521|issue:45290", + "issue:43994|issue:44493", + "issue:29942|issue:30333", + "issue:44464|issue:45584", + "issue:45084|issue:45520", + "issue:43844|issue:44964", + "issue:44554|issue:45446", + "issue:44568|issue:45701", + "issue:43688|issue:43873", + "issue:43540|issue:45200", + "issue:15354|issue:38175", + "issue:45072|issue:45198", + "issue:43232|issue:44849", + "issue:39401|issue:44568", + "issue:43278|issue:43701", + "issue:44315|issue:44849", + "issue:44554|issue:45356", + "issue:45200|issue:45325", + "issue:43295|issue:44610", + "issue:43334|issue:43525", + "issue:44898|issue:45412", + "issue:44466|issue:45127", + "issue:43493|issue:43701", + "issue:37428|issue:43957" + ], + "prepared_review_unit_hash": "a523895b82e2194eef7029e3cfb6650db7ad33b16932b7880862f3cc31d8402c", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35090, + "estimated_input_tokens": 8773, + "estimated_eval_tokens": 17802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous; the soft links are only surface-level similarities across tokenizer/chat-template, attention, or loading regressions. I did not find any pair that clearly represents the same underlying bug or change.", + "confidence": 0.68, + "canonical_issue_reason": "Issue 45701 is the broadest umbrella-like report in the set and the best anchor if one must be chosen, but the cluster itself is not a clean duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "45701 is open, general, and has inbound references, so it is the most suitable representative issue despite weak evidence that the other items are true duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A test failure in Janus is unrelated to a PEFT version pin issue; no shared bug or code path." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Both mention device-related CI failures, but they affect different models and likely different execution paths." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both touch apply_chat_template, but one is about zero assistant masks for multimodal inputs and the other is a crash on tool-call messages." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "These are different correctness problems: one is SigLIP2 inference quality, the other is unexpected position-id keys." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention CI failures and MLFlow job-reporting issues are unrelated." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Chunked generation with compiled forward and Whisper empty-transcription handling are different failures." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "A compilation error in template nodes and a Python 3.13 import_utils KeyError are not the same bug." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient inflation and a model-loading regression are unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness and a PyTorch version-check bug in flex_attention are different issues." + }, + { + "left": "issue:44568", + "right": "issue:45701", + "accept": false, + "reason": "Both concern tokenization behavior, but one is a specific BOS/EOS regression and the other is a broad version-change complaint; not the same concrete bug." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization and quantization/offloading behavior are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Both are multimodal/model-input issues, but one is video processing in Qwen3OmniMoe and the other is Gemma 4 token-type defaults." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp support and SigLIP2 zero probabilities are unrelated." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "These are different regressions: dtype mismatch in inference versus Wav2Vec2 save/tokenization failure." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and Qwen3.5 hidden-states output are distinct generation bugs." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer issues, but offset_mapping and add_special_tokens are separate concrete behaviors." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "A dtype drift between train/eval and a resume_from_checkpoint key mismatch do not describe the same bug." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel application and Qwen3.5 hidden-states output are unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "Attention correctness on MPS and Kimi-K2.5 tokenizer codec handling are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Both involve multimodal metadata, but mm_token_type_ids defaults and RoPE position scaling are different code paths." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor/tokenizer regression and OmDet-Turbo image-size mismatch are not the same underlying bug." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "The errors look similar, but they affect different model configs and there is no evidence of a shared root cause beyond missing pad_token_id access." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver resolution handling and RT-DETR memory release are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Serialization of tied lm_head weights and LoRA merge collapse with extended vocab are different problems." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 HF-vs-JAX discrepancy and resume_from_checkpoint key mismatch are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "An import error for flash attention helpers and meta-device model loading failures are different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 21, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43653", + "issue:43819", + "issue:43824", + "issue:43825", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43957", + "issue:43975", + "issue:43994", + "issue:44112", + "issue:44206", + "issue:44360", + "issue:44442", + "issue:44464", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44792", + "issue:44857", + "issue:44936", + "issue:44987", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45245", + "issue:45290", + "issue:45381", + "issue:45412", + "issue:45563", + "issue:45584", + "issue:45593" + ], + "soft_pairs": [ + "issue:43572|issue:44987", + "issue:43572|issue:43957", + "issue:43873|issue:44464", + "issue:43824|issue:43975", + "issue:43295|issue:43450", + "issue:43844|issue:44936", + "issue:43295|issue:43873", + "issue:38175|issue:45412", + "issue:44514|issue:44521", + "issue:44442|issue:45198", + "issue:43278|issue:43856", + "issue:43295|issue:43994", + "issue:37428|issue:43824", + "issue:38175|issue:43493", + "issue:42915|issue:43824", + "issue:43827|issue:43901", + "issue:43653|issue:44112", + "issue:43450|issue:43493", + "issue:44360|issue:44561", + "issue:43450|issue:43575", + "issue:44792|issue:45563", + "issue:45127|issue:45245", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:43819|issue:44112", + "issue:43262|issue:43450", + "issue:37428|issue:43425", + "issue:44610|issue:44857", + "issue:44857|issue:45593", + "issue:43278|issue:43825", + "issue:45290|issue:45381", + "issue:43606|issue:45083" + ], + "prepared_review_unit_hash": "083439898bcdce58b3e1b29b202f19a931da9d9c9607dda6491ad41862fa064c", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36646, + "estimated_input_tokens": 9162, + "estimated_eval_tokens": 18580 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: it mixes unrelated bugs in import compatibility, model-specific inference regressions, processor/chat-template issues, training/memory problems, and docs/test cleanups. None of the soft pairs look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.94, + "canonical_issue_reason": "No single issue is a safe canonical: the items span unrelated regressions across import paths, processors, training, and documentation, and the proposed soft pairs do not describe the same underlying bug.", + "canonical_pr_reason": null, + "best_issue_reason": "If a representative is needed, issue 44521 is the closest umbrella for the chat-template/multimodal subset, but it should not be treated as a cluster-wide duplicate anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Both involve v5-related model/config loading regressions, but one is a missing StableLmConfig pad_token_idx and the other is a transformers>=5.1.0 load failure for a specific checkpoint; different bugs." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "These are separate v5 loading/config issues: missing pad_token_idx vs meta-device model loading breakage." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Quantization/offload behavior and chunked generation with compiled forward are different code paths and failure modes." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "ImportError for a missing Qwen2.5-VL symbol is unrelated to DeepSeek detokenization output corruption." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor.tokenizer/image handling regression is distinct from batched video processor shape errors." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "ZeRO-3 gradient explosion and trainer.evaluate() failing after train() are separate training-state problems." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor API regression and quantization/offloading failure are not the same underlying bug." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero probabilities and RT-DETR memory not being released are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both touch apply_chat_template on multimodal inputs, but one is a batched padding=False crash while the other is assistant_mask generation returning zeros; different concrete failures." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "FastSpeech2ConformerTokenizer loading failure and Wav2Vec2 save/tokenization failure are distinct tokenizer bugs." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift in evaluate() and Qwen3 MoE memory inefficiency are unrelated training/runtime issues." + }, + { + "left": "issue:43295", + "right": "issue:43994", + "accept": false, + "reason": "Processor/tokenizer regression is not the same as SigLIP2 nonsensical model outputs." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols in different modules and unrelated fixes." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 zero probabilities and HF-vs-JAX discrepancy are related by model family, but they are not the same concrete bug." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and missing Qwen2.5-VL import are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs around pipeline deprecations, but they cover different task pages and different stale references." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and GraniteSpeech device-override CI failure are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Batched video shape bug and SigLIP2 implementation discrepancy do not share the same underlying code path." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "A DSA indexer activation issue and the removal of is_torch_fx_available breaking remote-code models are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Video batch-shape handling and Qwen2-57B tensor-parallel OOM are different problems." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "A janus test failure and a stale paged-generate warning are not the same bug." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merge collapse with tied embeddings and a 2^24 category limit runtime error are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC from_latents/forward mismatch and a qwen3_omni_moe helper behavior issue are different model-specific bugs." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center arg in LasrFeatureExtractor and Whisper empty-transcription failure after token alignment are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC latent-path mismatch and GraniteSpeech CI device override issues have no common code path." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and batched video shape handling are unrelated processor bugs." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Flash-attention import breakage and Torch 2.10 incompatibility are separate compatibility issues." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch and LwDetrImageLoss AMP crash are different vision bugs." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP/CUDA loss crash and D-FINE auxiliary-loss omission are unrelated model-training issues." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype regression and pipeline error-message/docs mismatch are unrelated." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Chat-template crashes on tool-call messages and qwen2.5-vl vision_position_ids errors are different multimodal bugs." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch for bark-small and a qwen3_omni_moe helper function issue are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 22, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:40444", + "issue:43335", + "issue:43388", + "issue:43404", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43931", + "issue:44112", + "issue:44292", + "issue:44351", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45310", + "issue:45372", + "issue:45459", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45593", + "issue:45712" + ], + "soft_pairs": [ + "issue:44448|issue:44743", + "issue:45200|issue:45588", + "issue:43335|issue:43550", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:37428|issue:44351", + "issue:43611|issue:43931", + "issue:43388|issue:43526", + "issue:39692|issue:43526", + "issue:43819|issue:44493", + "issue:45310|issue:45478", + "issue:43335|issue:43653", + "issue:29942|issue:32090", + "issue:43404|issue:45200", + "issue:44855|issue:45083", + "issue:44292|issue:45520", + "issue:39692|issue:44493", + "issue:43335|issue:43504", + "issue:43550|issue:44112", + "issue:43335|issue:45083", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:43335|issue:45072", + "issue:44977|issue:45229", + "issue:43720|issue:44112", + "issue:45459|issue:45712", + "issue:43335|issue:45593", + "issue:44568|issue:45491", + "issue:44448|issue:44977", + "issue:29127|issue:32090", + "issue:43606|issue:44857", + "issue:40444|issue:43526", + "issue:44857|issue:45072", + "issue:45372|issue:45588", + "issue:34689|issue:35141", + "issue:44977|issue:45563" + ], + "prepared_review_unit_hash": "46f1592943c14f0202b34c0f0dace142d75a82c29ab3854622a93b1c5a12e0cd", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38872, + "estimated_input_tokens": 9718, + "estimated_eval_tokens": 19692 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a mix of unrelated issues across different models and subsystems. Only one soft pair looks like a true duplicate: the repeated Qwen3.5 MoE from_pretrained error report.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 45310 is the earlier, clearer report of the same Qwen3.5 MoE from_pretrained regression as 45478, and it already has inbound reference activity.", + "canonical_pr_reason": null, + "best_issue_reason": "45310 is the best representative issue because it is the earliest duplicate in the only true duplicate pair and has slightly stronger discussion/reference signals.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Different models and different failure modes: Pegasus output drift vs Qwen3.5 recurrent-state reset." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Both mention attention-related code paths, but the bugs are unrelated: Gemma4 token-type handling vs flash_attention.py handling of s_aux=None." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "Different architectures and bugs: SwitchTransformers config creates sparse layers incorrectly, while Bamba fails under torch.compile with SDPA." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer file resolution and removal of is_torch_fx_available are unrelated issues." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "One is a trust_remote_code break from a removed helper; the other is DeepSeek tokenizer behavior in v5." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different missing symbols and different code paths; not the same bug." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Both are loading failures, but one concerns base_model_prefix compatibility and the other a concrete Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Mask2Former metric gathering and BEiT label reduction are different components with different defects." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "Documentation example errors in SigLIP2 are unrelated to BEiTImageProcessorFast label reduction." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC latent decoding mismatch and unexpected position-id keys are different model behaviors." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same Qwen3.5 MoE from_pretrained error, same version range, same underlying regression." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to BigBirdTokenizer special-token registration." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and a Trainer GPU broadcast NoneType error are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45200", + "accept": false, + "reason": "Mistral3 lm_head tying and Gemma4 mm_token_type_ids are different model-specific issues." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 decorator parsing failure is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure and flash_attn import lookup on Python 3.13 are different problems." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 doc example errors are unrelated to the widespread unexpected position-id key issue." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers config and BEiT preset loading fail for different reasons and in different code paths." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba compile/SDPA failure and GraniteSpeech CI device-override flakiness are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "Sparse-layer config bug is unrelated to qwen3_omni_moe output-length helper behavior." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Different models and different regressions: Pegasus v4/v5 output drift vs DeepSeek tokenizer correctness in v5." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to the position-id key warning across many models." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers config bug is unrelated to dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Flash-attention generation bug and Gemma4 multi-GPU OOM are different failure modes." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "Packed-weight loading in BitNet and GraniteSpeech CI device override are unrelated." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Protobuf error masking in tokenizers and dummy_pt_objects cleanup are different maintenance bugs." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and D-FINE auxiliary-loss disabling are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token insertion and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Llama 3.2 vision loading breakage and embedding reinitialization after resize are different bugs." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Qwen3.5 flash-attention generation failure and a stale warning for num_return_sequences are not the same issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The selected duplicate pair (issue:45310, issue:45478) is well supported by the packet: identical titles, same model area, close timing, and asymmetric inbound reference activity. The rejected soft pairs are phrased conservatively and do not overclaim duplicate status. No PR-pair mergeability issue applies here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 23, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:25251", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:35141", + "issue:36010", + "issue:37428", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43381", + "issue:43412", + "issue:43421", + "issue:43550", + "issue:43653", + "issue:43701", + "issue:43873", + "issue:43927", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44493", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45083", + "issue:45198", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45698" + ], + "soft_pairs": [ + "issue:43701|issue:45083", + "issue:43927|issue:45698", + "issue:43550|issue:45083", + "issue:43066|issue:44462", + "issue:43412|issue:45588", + "issue:45245|issue:45563", + "issue:43873|issue:44493", + "issue:29942|issue:35141", + "issue:45372|issue:45459", + "issue:36010|issue:37428", + "issue:44448|issue:44466", + "issue:43065|issue:45412", + "issue:25251|issue:32090", + "issue:43278|issue:43381", + "issue:44857|issue:45588", + "issue:44451|issue:45520", + "issue:43653|issue:44743", + "issue:44186|issue:45198", + "issue:43976|issue:45440", + "issue:43994|issue:45412", + "issue:44265|issue:45198", + "issue:44361|issue:45198", + "issue:43421|issue:45491", + "issue:42915|issue:42994", + "issue:44871|issue:44977", + "issue:43065|issue:43994", + "issue:29942|issue:30064", + "issue:44206|issue:44479" + ], + "prepared_review_unit_hash": "90aeed0360823db087350b83d82d56c5663db1dc8f0c8b724e78ee75e8c50778", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36055, + "estimated_input_tokens": 9014, + "estimated_eval_tokens": 18284 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated singleton bugs spanning tokenizers, generation, quantization, vision, and import regressions. No soft pair looks like a true duplicate or the same fixable code-path change.", + "confidence": 0.22, + "canonical_issue_reason": "No clear duplicate cluster emerges, so the broadest and most central open report here is `issue:43873` (offloading/quantization), which has the most discussion and inbound references among the set.", + "canonical_pr_reason": null, + "best_issue_reason": "`issue:43873` is the best global representative only by breadth and activity; it is still not a duplicate sink for the other issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Resume-from-checkpoint key mismatch and Qwen3 Omni feature-length helper behavior are different failures in unrelated code paths." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load, but one is custom token IDs being lost in config while the other is loading the wrong custom module; different root causes." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "Torch.compile SDPA failure in Bamba-9B-v2 is unrelated to the Qwen3 Omni helper length bug." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder-type regression and ignoring tokenizer.json are both tokenizer-loading issues, but not the same concrete bug." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export with missing training guard/erfinv support is unrelated to flash-attention crashing on s_aux=None." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-cardinality runtime error and a stale warning for num_return_sequences are distinct behaviors." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior and unexpected position-id keys are different bugs in different parts of model handling." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Failing Flash Attention 2 tests and embedding reinitialization after resizing token embeddings are unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Mistral_common import error in Gemma 4 loading and hidden tokenizer protobuf errors are separate import/error-handling issues." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and different compatibility breakages." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Different output from a model and inconsistent lm_head.weight serialization are not the same bug." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory not being released are unrelated." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nested-list output and Trainer NoneType broadcast errors do not share a concrete code path." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Eval-mode dtype drift and gradient checkpointing being disallowed in eval are distinct eval-time behaviors." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "AMP/CUDA loss crash in LwDetrImageLoss is unrelated to flash-attention s_aux=None handling." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model load failure for ScandiBERT and a Python 3.13 flash_attn import key error are different loading/import issues." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "Tokenizer special-token registration and Qwen recurrent state reset are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "Both are tokenizer-related, but they affect different models and failure modes; not the same underlying bug." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python-version compatibility and DeepseekV3MoE divergence are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "Siglip2 nonsensical outputs and RT-DETR memory leaks are different classes of problems." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failures with torch_compilable_check are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save/tokenization failure are different tokenizer bugs." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processor updates and Gemma3 NaN embeddings on mixed-length batches are not the same issue." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Both mention quantization, but one is FP8 inference failure and the other is quantized model saving; separate code paths." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma3 eos_token_id inconsistency and Qwen3.5 flash-attention generation issues are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3PixelDecoder dummy layer and Siglip2 output regression are unrelated model bugs." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures and void segmentation-map preprocessing are different subsystems." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported center argument in a feature extractor and the Qwen2.5/3.5 VL video-input regression are separate input-processing bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 24, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43329", + "issue:43334", + "issue:43381", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43723", + "issue:43756", + "issue:43824", + "issue:43873", + "issue:43931", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44442", + "issue:44464", + "issue:44554", + "issue:44610", + "issue:44734", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45491", + "issue:45588", + "issue:45593" + ], + "soft_pairs": [ + "issue:44734|issue:45406", + "issue:33357|issue:39692", + "issue:44610|issue:45412", + "issue:29127|issue:34567", + "issue:45103|issue:45372", + "issue:43873|issue:45229", + "issue:43756|issue:45440", + "issue:45372|issue:45406", + "issue:43723|issue:44554", + "issue:43278|issue:43575", + "issue:43278|issue:43329", + "issue:43381|issue:43701", + "issue:43653|issue:44442", + "issue:41720|issue:45229", + "issue:45440|issue:45593", + "issue:29942|issue:36010", + "issue:43824|issue:44279", + "issue:32090|issue:33357", + "issue:43334|issue:43531", + "issue:43526|issue:44186", + "issue:44977|issue:45245", + "issue:43526|issue:44857", + "issue:42915|issue:43931", + "issue:43441|issue:45588", + "issue:44464|issue:45491", + "issue:43262|issue:44206", + "issue:44743|issue:44811", + "issue:43526|issue:44610", + "issue:44442|issue:45072" + ], + "prepared_review_unit_hash": "dd8bf60ae46b839da652151f4049d4f56f0205e93fa3911e49404b61079e531f", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36482, + "estimated_input_tokens": 9121, + "estimated_eval_tokens": 18498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster does not contain any strong duplicate pairs: the issues span unrelated models, processors, attention paths, tokenizer/import problems, and memory/loading regressions. All soft edges were rejected. There are no PRs in the set.", + "confidence": 0.97, + "canonical_issue_reason": "No real duplicate canonical stands out because the issues are unrelated; if one issue must be chosen as the anchor, issue #43873 is the broadest and most active item, but it is not actually representative of the others as a duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #43873 is the best single representative only because it is open, discussion-heavy, and broadly framed; however, it is not a true cluster canonical since the rest of the items do not describe the same bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Different subsystems and failures: KV-cache continuation indexing in serve vs Gemma4 processor initialization missing _tokenizer." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "Both are CLIP/SigLIP-adjacent only at a high level; one is a Mac bus error, the other is a doc example/model-processor mismatch and quantization failure." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor output size mismatch versus a model memory leak are unrelated bugs." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 box-content error messaging and TrainerState token counting are unrelated issues." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "Auto-docstring future-annotations crash is unrelated to Gemma4 processor loading/import failure." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Both mention memory/placement, but one is quantization offloading behavior and the other is multi-GPU OOM for a specific model; not the same bug." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different models and different correctness problems: RoPE layer selection versus DeepSeekV3 implementation divergence." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both involve Gemma4, but one is a mistral_common import dependency issue and the other is a serve-time processor attribute error." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading regression versus an MPS attention correctness issue; no shared code-path." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Embedding dtype drift in eval mode is unrelated to tensor-parallel OOM on Qwen2-57B." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Different bugs: dtype change in evaluate versus undefined video-token helper/merge_size in multimodal token counting." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Eval-mode gradient checkpointing restriction is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-related, but one is a BigBird special-token registration issue and the other is AutoTokenizer failing for a specific tokenizer class." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Different model families and symptoms: Qwen3 auto device mapping asserts on A800, while Gemma4 hits multi-GPU OOM." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeekV3 implementation divergence is unrelated to D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "FlashAttention test failures and GenerationMixin import errors are unrelated regressions." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific missing symbol import versus a vague dependency issue; not enough evidence of the same underlying bug." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer NoneType broadcast error and MacOS CLIP bus error are unrelated failures." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id attribute error and Qwen3-MoE sliding_window behavior are different code paths." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "BEiT label reduction bug and LayoutLMv2 NER padding/truncation crash are different processor/tokenizer issues." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention generation bug and category-count runtime limit are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BEiT label handling and LwDetrImageLoss AMP/CUDA crash are not the same defect." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are different loading/configuration problems." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both touch flash attention, but they describe different failures, models, and triggers; too broad to merge as one bug." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is unrelated to Gemma3 sliding-window NaN embeddings." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sample-rate default and a feature extractor unsupported argument are different audio-processing bugs." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset bug and Whisper batch_decode skip_special_tokens bug are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:44610", + "accept": false, + "reason": "Different image-processing/model-loading bugs; no shared underlying defect." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "AutoTokenizer loading failure for one tokenizer class is unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel inference." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 25, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:29127", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:42907", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43452", + "issue:43493", + "issue:43525", + "issue:43550", + "issue:43575", + "issue:43611", + "issue:43646", + "issue:43701", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:43994", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44387", + "issue:44442", + "issue:44479", + "issue:44568", + "issue:44743", + "issue:44898", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45216", + "issue:45229", + "issue:45290", + "issue:45440", + "issue:45479", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45698" + ], + "soft_pairs": [ + "issue:43452|issue:45588", + "issue:43575|issue:43701", + "issue:29127|issue:35141", + "issue:43646|issue:44077", + "issue:45072|issue:45229", + "issue:43575|issue:44387", + "issue:44977|issue:45584", + "issue:45588|issue:45600", + "issue:33357|issue:38175", + "issue:43316|issue:43525", + "issue:44479|issue:45290", + "issue:44964|issue:45440", + "issue:43761|issue:44079", + "issue:43931|issue:45216", + "issue:42907|issue:45698", + "issue:39692|issue:45491", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:44442|issue:44898", + "issue:43761|issue:44188", + "issue:43493|issue:43827", + "issue:43381|issue:43873", + "issue:44568|issue:45479", + "issue:43550|issue:44743", + "issue:43295|issue:45584", + "issue:43994|issue:44206" + ], + "prepared_review_unit_hash": "2ca1a459290b1ddaa6fab8ea4ea9168243f600346c9d47553a0b2db5dea573d6", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 26, + "serialized_chars": 35627, + "estimated_input_tokens": 8907, + "estimated_eval_tokens": 18070 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: it mixes unrelated regressions across models, loading, quantization, tokenization, and trainer behavior. No soft pair looks like the same underlying bug or change, so there is no clear duplicate set.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43873 is the most central/open item with inbound references, but the cluster is too mixed to treat it as a true canonical duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best available anchor because it is open and actively referenced, though it only represents one subtopic in an otherwise unrelated set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:45588", + "accept": false, + "reason": "Different bugs: gguf_file loading failures vs flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Different failure modes: tensor-parallel OOM for Qwen2-57B vs resume_from_checkpoint key mismatch." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "Both are about confusing initialization behavior, but one is LayoutLMv3 box validation and the other is token-embedding reinit on resize; not the same bug." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Custom model initialization breakage is distinct from patchtsmixer optional post_init validation." + }, + { + "left": "issue:45072", + "right": "issue:45229", + "accept": false, + "reason": "Different issues: dtype mismatch in CI vs multi-GPU Gemma4 CUDA OOM." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is TP loading of Qwen2-57B and the other is int4 quantization memory growth in Transformers 5.x." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 flash-attention generation regression is unrelated to Whisper empty transcription after align_special_tokens." + }, + { + "left": "issue:45588", + "right": "issue:45600", + "accept": false, + "reason": "flash_attention.py s_aux=None crash is unrelated to stale auto_mappings.py references to removed Sam3LiteText configs." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "Both involve SigLIP-like models, but one is a MacOS bus error on CLIP and the other is unexpected zero probabilities on siglip2-base; different symptoms and code paths." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3TextConfig API mismatch is not the same as Llama4Config missing pad_token_id." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video input regression in Qwen VL models is unrelated to chat-template crashes on assistant tool-call messages." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Phi-4 multimodal loading failure and DeepseekV3MoE divergence are different model families and different bugs." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression is unrelated to ModelOutput key assignment when a key was previously None." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3-VL weight shape mismatch is a loading issue, while Qwen3.5 save_pretrained corruption is a checkpoint-saving bug." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals is not the same as loading the wrong custom module after save_pretrained." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "SigLIP2 docs/example errors are unrelated to Gemma3 NaN embeddings from mixed-length sliding-window batches." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "Adafactor+deepspeed OOM and TrainerState.num_input_tokens_seen not updating are unrelated trainer/optimizer issues." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Llama 3.2 Vision loading regression is different from base_model_prefix handling in Transformers 5.0.0." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "FastSpeech2ConformerTokenizer loading failure is unrelated to Perceiver non-default resolution/interpolation failure." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression is unrelated to divergent attention kernels from allow_is_bidirectional_skip under torch.compile." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is unrelated to docs still referencing pipeline() after removals." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and quantization offloading behavior are different code paths and symptoms." + }, + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer special-token addition regression is unrelated to zero-loss classification behavior." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "torch.compile+SDPA failure in Bamba is unrelated to recurrent-state reset in modular_qwen3_5.py." + }, + { + "left": "issue:43295", + "right": "issue:45584", + "accept": false, + "reason": "processor.tokenizer regression is unrelated to Whisper empty transcription after align_special_tokens." + }, + { + "left": "issue:43994", + "right": "issue:44206", + "accept": false, + "reason": "SigLIP2 nonsensical outputs are unrelated to LasrFeatureExtractor passing an unsupported center arg." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 26, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:36010", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43550", + "issue:43606", + "issue:43643", + "issue:43701", + "issue:43720", + "issue:43742", + "issue:43825", + "issue:43856", + "issue:43873", + "issue:44077", + "issue:44162", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45137", + "issue:45200", + "issue:45372", + "issue:45584", + "issue:45656", + "issue:45759" + ], + "soft_pairs": [ + "issue:43316|issue:45759", + "issue:41628|issue:45372", + "issue:43720|issue:44442", + "issue:43643|issue:44913", + "issue:32090|issue:33290", + "issue:44190|issue:44496", + "issue:43873|issue:44871", + "issue:34689|issue:36010", + "issue:43381|issue:43856", + "issue:44077|issue:44479", + "issue:44855|issue:45137", + "issue:33290|issue:45656", + "issue:43540|issue:44514", + "issue:43316|issue:44877", + "issue:29127|issue:33357", + "issue:43381|issue:43742", + "issue:42175|issue:43316", + "issue:43404|issue:43441", + "issue:33290|issue:34689", + "issue:44162|issue:44792", + "issue:25251|issue:28282", + "issue:41950|issue:43475", + "issue:43232|issue:43388", + "issue:43295|issue:43825", + "issue:44871|issue:45584", + "issue:45127|issue:45200", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43295|issue:44871" + ], + "prepared_review_unit_hash": "5f37eb78e498b445b52d0d1600773fa0ed878f7d7bf8c4d3a8181fde4ab45350", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36559, + "estimated_input_tokens": 9140, + "estimated_eval_tokens": 18536 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: it mixes unrelated regressions in config loading, multimodal processors, generation, and distributed training. None of the soft edges look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.92, + "canonical_issue_reason": "If one issue must anchor the cluster, issue 43316 is the best fit because it is a concrete config/API mismatch and is the most central item among the few config-loading similarities in the set.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43316 is the strongest representative of the repeated config/model-loading theme and appears in multiple soft similarities, even though the overall cluster is not a true duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Related to multimodal config handling, but one is a Gemma3TextConfig API discrepancy and the other is a Qwen composite-config unwrap issue; different models and failure modes." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Both are import-related, but AutoImageProcessor import failure and missing ReasoningEffort in Gemma 4 processor loading are separate dependency/path problems." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "Packed-weight loading in accelerate versus AutoTokenizer failing to load a specific tokenizer are unrelated code paths." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "Both concern config objects, but missing fields with trust_remote_code and rotary_pct resetting on reload are different bugs." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "NoneType GPU broadcast in Trainer and OOM with Adafactor/DeepSpeed are distinct training failures." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "A local dataset loading script issue and an unrecognized model/config.json issue are not the same underlying bug." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior and Gemma eos_token_id config inconsistency are unrelated." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "One is a Llama vision model-loading regression; the other is a GenerationMixin import error. Same library area, different problem." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "Gradient checkpointing in eval mode and Qwen3 MoE memory inefficiency are different training/runtime issues." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "patchtsmixer post_init restrictions and Qwen video-input regression are unrelated." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 torch.jit parsing failure and DeepSpeed ZeRO3 deque pop error are separate defects." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both involve DeepSpeed/optimizers, but OOM with Adafactor and optimizer.step being called twice are different bugs." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Both hit multimodal/video processing, but Qwen3OmniMoe video-input ValueError and Qwen2_5_VL batched chat-template crash are different code paths." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Both are config-loading issues, but Gemma3TextConfig API mismatch and strict loading of granite_speech config are not the same bug." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 box-content error messaging and a MacOS CLIP bus error are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43742", + "accept": false, + "reason": "Gradient checkpointing eval-mode behavior and MobileLLM loading key error are separate issues." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Pip extras/backend packaging for TensorFlow versus Gemma3TextConfig API discrepancy are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Both are Mistral-family, but weight tying in Mistral3ForConditionalGeneration and FlashAttention failure in Ministral-3 are different concrete problems." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "DeepSpeed OOM with Adafactor and Llama 3.2 Vision model loading regression are unrelated." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage and janus test failure for image generation do not share the same underlying bug." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nesting bug and AutoModel missing PyTorch import are completely unrelated." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Both concern video/image processor behavior, but video-classification using image processors and missing fpn_position_embeddings in SAM3Video are different defects." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "update_model_kwargs_for_generation after sync_gpus and gather_for_metrics dropping labels are separate distributed-training bugs." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor.tokenizer/images regression and pipeline translation-task error messaging are unrelated." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma eos_token_id inconsistency and Whisper empty-transcription failure after align_special_tokens are different tokenization/generation issues." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge collapse with extended vocab and missing mm_token_type_ids default zeros are different multimodal/model-update bugs." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and resume_from_checkpoint key mismatch are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch and resume_from_checkpoint key mismatch are different issues." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "A processor/tokenizer regression and a Gemma eos_token_id config inconsistency do not describe the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 27, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:33290", + "issue:35141", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:43065", + "issue:43335", + "issue:43452", + "issue:43575", + "issue:43646", + "issue:43673", + "issue:43742", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44936", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45290", + "issue:45357", + "issue:45381", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45698" + ], + "soft_pairs": [ + "issue:43673|issue:44743", + "issue:43761|issue:44479", + "issue:33290|issue:35141", + "issue:33290|issue:36331", + "issue:43065|issue:44617", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:44936|issue:45698", + "issue:43646|issue:44913", + "issue:42617|issue:43575", + "issue:43761|issue:44242", + "issue:43575|issue:43873", + "issue:44077|issue:44534", + "issue:43931|issue:44060", + "issue:44464|issue:44871", + "issue:44479|issue:44734", + "issue:44617|issue:45584", + "issue:43065|issue:44610", + "issue:43827|issue:43994", + "issue:43906|issue:45290", + "issue:44792|issue:44977", + "issue:44534|issue:44913", + "issue:41720|issue:45245", + "issue:44190|issue:44964", + "issue:44792|issue:45600", + "issue:44855|issue:45588", + "issue:44521|issue:45381", + "issue:45127|issue:45357", + "issue:43335|issue:44855" + ], + "prepared_review_unit_hash": "04003b66e72897fde8018c127330958b5debe6cbb1ffcd0b732f71877076ef7b", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35846, + "estimated_input_tokens": 8962, + "estimated_eval_tokens": 18180 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the paired issues are mostly different regressions or unrelated model-loading/training bugs. I found no soft-edge pair that clearly represents the same underlying defect or change, so all candidate duplicate links should be rejected.", + "confidence": 0.86, + "canonical_issue_reason": "If a single issue must serve as the anchor, issue #43646 is the broadest and most central regression description, but the cluster overall does not form a coherent duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "#43646 is the best representative because it is the most general and can subsume several initialization/loading regressions, even though most items here are not true duplicates of it.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both involve cache-related behavior, but one is a missing GenerationMixin cache in chunked prefill while the other resets recurrent states in modular_qwen3_5; different code paths and symptoms." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Qwen video-input regression are unrelated model families with different failure modes." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "OOM with Adafactor/DeepSpeed is unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "Optimizer memory blowup and CustomTrainer compute_loss signature mismatch are distinct bugs." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is a model-implementation issue; Sam3Video OOM is a runtime memory issue, not the same defect." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both concern loading, but gguf_file handling and missing model_type in config.json are different root causes." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Qwen2 large-model OOM with tensor parallelism and a KeyError loading MobileLLM are separate loading failures." + }, + { + "left": "issue:44936", + "right": "issue:45698", + "accept": false, + "reason": "Trainer evaluate-after-train behavior is unrelated to from_pretrained choosing the wrong custom module after save_pretrained." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Generic custom model initialization breakage is not the same as GPTNeoXConfig rotary_pct not persisting on reload." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py execution failure and Qwen2 model-load OOM are different problems." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Hidden_states regression in CLIPVisionModel is unrelated to load-balancing loss omission when output_router_logits=False." + }, + { + "left": "issue:43575", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory, but tensor-parallel OOM and offloading/quantization misbehavior are not the same underlying bug." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "PatchTSMixer post_init policy and non-persistent buffer junk in v5 are unrelated regressions." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Shape mismatch when loading Qwen3-VL is different from an incorrect tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency and Gemma eos_token_id config mismatch are unrelated issues." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression in Qwen multimodal models is different from a KV-cache continuation indexing bug in transformers serve." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Sam3Video OOM and Whisper empty-transcription failure are unrelated model-specific bugs." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is not the same as OmDet-Turbo processor output-size mismatch." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() and a SigLIP2 model producing nonsensical outputs are different issues." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "A reproduction of issue #38071 is not the same as apply_chat_template crashing on assistant tool-call messages." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation issues do not match." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffers filled with junk and GPTNeoX rotary_pct reloading behavior are distinct bugs." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Auto device mapping CUDA assert and category-count limit runtime error are unrelated." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading in a training script and loading Phi-4 multimodal with latest transformers are not duplicates." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus generation test failure and stale auto_mappings references to removed Sam3LiteText configs are unrelated." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import/parsing failure in DebertaV2Model is unrelated to flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both involve multimodal chat/vision handling, but all-zero assistant masks and wrong vision_position_ids are different defects." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge collapse with extended vocab and incorrect visual encoder keys saved in Qwen3.5 are different save/load behaviors." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and DebertaV2Model Python 3.13 import error are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 28, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43643", + "issue:43644", + "issue:43650", + "issue:43761", + "issue:43976", + "issue:44077", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44464", + "issue:44466", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44743", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45362", + "issue:45375", + "issue:45406", + "issue:45446", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:44938|issue:45542", + "issue:44077|issue:44877", + "issue:43976|issue:44855", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:43761|issue:44743", + "issue:43540|issue:44734", + "issue:43650|issue:44220", + "issue:45276|issue:45584", + "issue:44112|issue:45600", + "issue:43116|issue:44190", + "issue:43295|issue:45276", + "issue:43335|issue:44190", + "issue:45245|issue:45584", + "issue:36246|issue:41628", + "issue:43404|issue:45216", + "issue:43479|issue:45375", + "issue:44933|issue:45362", + "issue:44734|issue:45632", + "issue:44464|issue:45563", + "issue:44186|issue:44734", + "issue:38175|issue:43065", + "issue:44561|issue:45632", + "issue:44683|issue:45446", + "issue:44466|issue:44913", + "issue:44246|issue:45003", + "issue:36246|issue:38617", + "issue:45406|issue:45632", + "issue:43643|issue:44496", + "issue:45563|issue:45584" + ], + "prepared_review_unit_hash": "5176cd372fc090325331bafb5ee6bb835457f4edc6a7b9f7b7bc667e647c0201", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36767, + "estimated_input_tokens": 9192, + "estimated_eval_tokens": 18640 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most items are unrelated Transformers bugs across different models, APIs, or runtime environments. No soft pair looks like the same underlying bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": "issue:44246 is the broadest, highest-activity issue in the set and best represents the cluster if a single issue must be chosen, but the group is not actually duplicate-heavy.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44246 is the best standalone issue candidate because it has the strongest discussion signal and concerns core import-time behavior, which is more central than the other narrowly scoped reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Both involve loading/runtime behavior, but one is a Python 3.14 import/load failure and the other is a TensorBoard-without-TF backend error; different code paths." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Both mention config validation, but they target different models and different misconfigurations; not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Both are Python-version-related import failures, but one is a broad version incompatibility and the other is a DebertaV2Model parsing error in Python 3.13." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "One is a serialization/buffer regression and the other is a config field silently reverting on reload; different failure modes." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "These affect completely different workflows: torch.compile/SDPA model inference versus loading a local dataset in an example script." + }, + { + "left": "issue:43761", + "right": "issue:44743", + "accept": false, + "reason": "Both are model-generation correctness issues, but they involve different models and unrelated cache/state logic." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "One is a Qwen3OmniMoe video-input processing error; the other is a transformers serve KV-cache indexing crash." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "The titles point to unrelated problems: missing data versus an fbank feature extraction issue." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "One is embedding weight propagation after resizing token embeddings; the other is Whisper empty-transcription generation after token alignment." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "Both mention CI, but one is a stale device-override test and the other is a broken auto_mappings reference; different root causes." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Different example scripts and different symptoms; no shared concrete bug." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "One is a processor/tokenizer regression; the other is a resize-token-embeddings model-weights issue." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction is unrelated to local dataset loading in an example script." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "A category-cardinality RuntimeError is unrelated to Whisper generation after align_special_tokens." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different symbols and different package exports; too broad to be duplicates." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Different model families and different symptoms: untied lm_head weights versus incorrect checkpoint saving." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Both are config-field issues, but they involve different models and different missing/defaulted fields." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "A missing image_utils import is not the same as Qwen3.5-35B crashing in chat." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve/KV-cache indexing and trust_remote_code cache-path collisions are unrelated problems." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "One is a correctness issue in chunked generation with compiled forward; the other is a stale warning in paged generate." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "A tokenizer crash on NER inputs is not the same underlying bug as a serve-side tensor indexing crash." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Siglip2 zero probabilities and a dummy Conv2d in Sam3PixelDecoder are unrelated model bugs." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Both involve trust_remote_code, but one is a removed utility breaking models and the other is a local cache-path collision." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both are in flex_attention, but one is a compiled-runtime failure on newer torch and the other is an incorrect version check for AuxRequest import; different concrete bugs." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Serialization of tied lm_head weights is unrelated to GPTNeoX rotary_pct reloading incorrectly." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness and unsafe sys.modules access are only vaguely related; the titles do not indicate the same bug or fix." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer in transformers serve is unrelated to trust_remote_code cache collisions." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "A trust_remote_code config object missing fields is not the same as an unrecognized model due to missing model_type." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation-related, but one is a warning bug and the other is an actual Whisper failure path." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 29, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43673", + "issue:43688", + "issue:43824", + "issue:43827", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44220", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44496", + "issue:44683", + "issue:44933", + "issue:44964", + "issue:45020", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45584", + "issue:45593", + "issue:45600", + "issue:45759" + ], + "soft_pairs": [ + "issue:41950|issue:44016", + "issue:44964|issue:45600", + "issue:42907|issue:43441", + "issue:43388|issue:43688", + "issue:43295|issue:45335", + "issue:44112|issue:44964", + "issue:44496|issue:45042", + "issue:43854|issue:44964", + "issue:44016|issue:44220", + "issue:43673|issue:44336", + "issue:43299|issue:45216", + "issue:43531|issue:45600", + "issue:42175|issue:44279", + "issue:43526|issue:43901", + "issue:45335|issue:45584", + "issue:44075|issue:44368", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:44496|issue:45759", + "issue:41950|issue:45020", + "issue:43901|issue:44496", + "issue:44016|issue:44062", + "issue:44242|issue:45200", + "issue:43577|issue:45216", + "issue:43976|issue:45405", + "issue:44351|issue:45278", + "issue:43824|issue:44933", + "issue:43388|issue:43827", + "issue:43479|issue:43525", + "issue:44683|issue:45542" + ], + "prepared_review_unit_hash": "bbf5891558fe2f0cb875d59460942d80c0b8712b3cf0fe873fdfa799328dcf79", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36067, + "estimated_input_tokens": 9017, + "estimated_eval_tokens": 18290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated Transformers regression reports that only share broad subsystem or model-family similarity. I found no soft-edge pair that clearly represents the same concrete bug or change, so I would not merge any of the candidates as duplicates.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 45020 is the best umbrella candidate: it is open, broad, and captures the recurring theme of recent-version regressions affecting model loading and remote-code paths better than the narrower one-off reports.", + "canonical_pr_reason": null, + "best_issue_reason": "45020 is the most representative issue for the cluster, but it is still too broad to serve as a true duplicate target for many of the more specific model/config regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Different bugs: one is a pipeline processor lookup problem, the other is a notebook syntax error." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Unrelated model-load failure vs stale auto-mappings reference; same repo area, different concrete issue." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Both involve Ministral, but one is save/export of dequantized models and the other is FlashAttention loading; not the same bug." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Distinct training/evaluation issues affecting different code paths and model families." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Both are regressions, but one is a processor/tokenizer API break and the other is a resize_token_embeddings bug in t5gemma." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI device-override test failure is not the same as a Phi-4 multimodal loading regression." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Different failures: generic model-type resolution vs PIL image processor torchvision dependency regression." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Both are model-loading issues, but they involve different models and different failure modes." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and fbank feature extraction bug are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache regression and ANSI output formatting are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both touch Qwen models, but one is MoE loading and the other is save_pretrained serialization." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to stale auto_mappings references." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Package/backend dependency complaints, but not the same dependency or code path." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "Label reduction in BeitImageProcessorFast is unrelated to a pipeline doc mismatch." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Token embedding resize bug and Whisper empty-transcription generation failure are different code paths." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer argument handling and a config warning about tied embeddings are not the same defect." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing eval-mode behavior and D-FINE auxiliary-loss handling are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Same model family, but the first is a load regression and the second is a save_pretrained key serialization bug; not clearly the same fix." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Both involve model/config resolution, but one is an unrecognized model error and the other is unwrapping text_config for multimodal configs." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Broad Transformers regressions, but one is a specific pipeline processor lookup bug and the other is a generic remote_code complaint." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Pipeline docs mismatch and model type recognition failure are unrelated." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken keyword conflict are unrelated." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Different model/training features: router-logit load-balancing loss vs Gemma 4 multimodal token type IDs." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP-2 dtype propagation and Qwen3.5 save_pretrained serialization are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python version compatibility and an unreleased dependency pin are different release-management problems." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "HybridCache missing import is a specific symbol regression; 45278 is a broad import-errors report, not the same concrete bug." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Specific Qwen2.5-VL import failure vs a different missing image_utils import; too different to merge." + }, + { + "left": "issue:43388", + "right": "issue:43827", + "accept": false, + "reason": "Metric gathering logic bug and docs referencing removed pipeline APIs are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Phi-4 multimodal config defaulting and Llama4 missing pad_token_id are different config bugs." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention on torch 2.9 and TensorBoard/TensorFlow backend packaging are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 30, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43295", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43650", + "issue:43653", + "issue:43723", + "issue:43784", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44297", + "issue:44361", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:44987", + "issue:45081", + "issue:45276", + "issue:45290", + "issue:45325", + "issue:45397", + "issue:45405", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45712" + ], + "soft_pairs": [ + "issue:44462|issue:45081", + "issue:44279|issue:45405", + "issue:43299|issue:43854", + "issue:39692|issue:43901", + "issue:41950|issue:43650", + "issue:32090|issue:35141", + "issue:44297|issue:44462", + "issue:43295|issue:44779", + "issue:38175|issue:44617", + "issue:43976|issue:44279", + "issue:44462|issue:44779", + "issue:44521|issue:45325", + "issue:43976|issue:44987", + "issue:45600|issue:45712", + "issue:43450|issue:44279", + "issue:43065|issue:44898", + "issue:42994|issue:43317", + "issue:44466|issue:45276", + "issue:44261|issue:44263", + "issue:43441|issue:44683", + "issue:43650|issue:45290", + "issue:43723|issue:44162", + "issue:44623|issue:45397", + "issue:43784|issue:45542", + "issue:44623|issue:44749", + "issue:44671|issue:44779", + "issue:43653|issue:45593", + "issue:44987|issue:45542", + "issue:43901|issue:43994", + "issue:43122|issue:43650", + "issue:44361|issue:45593" + ], + "prepared_review_unit_hash": "e3939c2da6e72935c928f81185ecef00ad12ad1047fea4b2f080bff2b2f5e883", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36959, + "estimated_input_tokens": 9240, + "estimated_eval_tokens": 18736 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of tokenizer-loading/regression, multimodal, quantization, and model-specific bugs. The only common thread is loose v5/tokenizer similarity, but the concrete failure modes differ, so no soft edges are accepted.", + "confidence": 0.34, + "canonical_issue_reason": "issue:44462 is the clearest concrete tokenizer-loading regression in this set and the best umbrella representative for the loose tokenizer/v5 cluster, though the overall group is still quite heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 has the most representative and actionable failure mode: AutoTokenizer ignoring repository tokenizer.json. It is specific enough to anchor the tokenizer-related subset better than the more generic or highly model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizers, but one is AutoTokenizer repository loading while the other is a Mistral regex patch crash; different code paths and fixes." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "Unrelated: generic dependency trouble vs a specific PEFT minimum-version bump." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Different models and failures: Qwen3VL loading regression vs GLM-4.7-Flash unit-test load issue." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both mention docs/examples, but one is a SigLIP2 example failure and the other is a pipeline docs mismatch; not the same bug." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "Video pipeline processor lookup vs an unrelated placeholder issue; no shared underlying defect." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error and embedding reinitialization are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Both are tokenizer-related, but one is save_pretrained metadata mismatch and the other is AutoTokenizer ignoring tokenizer.json; distinct root causes." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "A processor.tokenizer regression with image inputs is not the same as Deepseek tokenization drift." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated model/runtime issues." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python version compatibility break vs generic dependency issue; not the same concrete bug." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "Both concern tokenizers, but one is repository tokenizer selection/loading and the other is Deepseek tokenization correctness; too different to merge." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Both are multimodal-related, but assistant mask generation and rope index scaling are different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Different compatibility failures; one is Python support, the other is loading a specific model on transformers>=5.1.0." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "CI break from removed config references vs leftover dummy classes failing repo checks; separate maintenance issues." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batch-shape bug is unrelated to a dependency issue." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Sam3PixelDecoder dummy Conv2d and Perceiver non-default-resolution failure are different model bugs." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving and dequantized load/offload failure are both quantization-adjacent but different failure modes and fixes." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Both touch weights/embeddings, but serialization inconsistency and resize_token_embeddings behavior in gemma4 are not the same defect." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "MLA RMS norm precision and GlmMoeDsaIndexer split behavior are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both are attention-related, but one is Ministral FlashAttention and the other is compiled flex_attention on newer torch; different code paths." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "Placeholder/odd issue vs a real chat-template crash; no overlap." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Generic tokenizer loading in v5 vs an ESM2 regression; not the same underlying bug." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "processor.save_pretrained missing files and gemma-4 zero3 from_pretrained are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import NameError for sentence-transformers vs tf backend installation detection; different subsystems." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Missing processor save files and slow filtering after upgrade are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "CamemBERT masked LM regression and Deepseek tokenizer output regression are different model-specific bugs." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary loss behavior have no common root cause." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Model loading failure and TensorFlow/tensorboard backend detection are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for text-classification pipeline vs actual SigLIP2 inference malfunction; not duplicates." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenizer version drift and an unrelated placeholder issue." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer AttributeError and D-FINE auxiliary-loss behavior are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 31, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:43262", + "issue:43295", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43525", + "issue:43673", + "issue:43761", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44291", + "issue:44295", + "issue:44297", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44462", + "issue:44485", + "issue:44496", + "issue:44521", + "issue:44561", + "issue:44589", + "issue:44617", + "issue:44661", + "issue:44857", + "issue:44871", + "issue:44964", + "issue:45250", + "issue:45356", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45759" + ], + "soft_pairs": [ + "issue:44016|issue:44291", + "issue:43262|issue:44521", + "issue:43475|issue:44016", + "issue:44297|issue:45397", + "issue:43673|issue:43761", + "issue:43525|issue:45759", + "issue:44188|issue:44336", + "issue:43525|issue:43881", + "issue:44589|issue:45362", + "issue:43295|issue:44617", + "issue:42491|issue:43299", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:43352|issue:45250", + "issue:44336|issue:44373", + "issue:16998|issue:22355", + "issue:44242|issue:45593", + "issue:44295|issue:45397", + "issue:44661|issue:45542", + "issue:41950|issue:44220", + "issue:44246|issue:44496", + "issue:44462|issue:45356", + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:44336|issue:44485", + "issue:43673|issue:44561", + "issue:43824|issue:43976", + "issue:43976|issue:44964", + "issue:44246|issue:44871", + "issue:44242|issue:44857" + ], + "prepared_review_unit_hash": "d64743beb55d771774a776947a65ec6d7311044b1b20bce32a34604673e725da", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36530, + "estimated_input_tokens": 9133, + "estimated_eval_tokens": 18522 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous import/config/regression reports. None of the soft pairs look like the same underlying bug or change, so I would not merge any of them.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 43824 is the strongest anchor in the set: it has the highest inbound reference count and clearly describes a concrete, widely hit import regression for Qwen2.5-VL.", + "canonical_pr_reason": null, + "best_issue_reason": "43824 is the best representative issue because it is specific, high-signal, and has the most external references/discussion among the issues shown.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error vs. init_empty_weights TypeError; unrelated failures." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve chat templates, but one is sampling-rate defaulting and the other is assistant mask generation; different bugs." + }, + { + "left": "issue:43475", + "right": "issue:44016", + "accept": false, + "reason": "SAM 3 video attribute error vs. notebook syntax error; no shared code-path." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer_class save metadata mismatch vs. zero3 from_pretrained issue; distinct problems." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Cache/chunked-prefill regression vs. CLIP vision hidden_states return bug; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config vs. composite Qwen config unwrapping; similar area, different concrete defects." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention-kernel divergence vs. ANSI escape output in loading_report; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Llama4 config attribute error vs. GLM-4V loading failure; different root causes." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Float8 storage lookup TypeError vs. Qwen3.5 chat crash; not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:44617", + "accept": false, + "reason": "Processor/tokenizer regression vs. CUDA OOM; unrelated." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both are Qwen3 MoE-related, but one is LoRA incompatibility and the other is model loading regression; too different to merge." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Missing AutoImageProcessor import vs. Python version compatibility problem; unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs/behavior mismatch vs. slow import; different areas entirely." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Model-specific Flash Attention unsupported error vs. generic Flash Attention topic; not the same concrete issue." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "Terminal color output bug vs. docstring issue; unrelated." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "model_max_length question vs. missing transformers.onnx module; no overlap." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Mixture-of-experts load-balancing loss bug vs. D-FINE auxiliary-loss omission; different models and code paths." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "position_ids buffer access bug vs. zero3 model loading issue; unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45542", + "accept": false, + "reason": "Tokenizer-mapping failure in add-new-model-like vs. TensorFlow backend detection problem; different subsystems." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification pipeline processor selection bug vs. fbank extraction issue; different failures." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import slowness vs. unrecognized model/config error; not a duplicate." + }, + { + "left": "issue:44462", + "right": "issue:45356", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json vs. codec handling regression in Kimi-K2.5; distinct tokenizer bugs." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Qwen2.5-VL import error vs. huggingface_hub is_offline_mode import error; unrelated." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing symbols from different modules; not the same issue." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI code emission bug vs. GLM-5 RoPE implementation discussion; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache regression vs. trust_remote_code breakage from removed helper; different root cause." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Qwen2.5-VL import failure vs. Python version support issue; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "Python compatibility vs. Phi-4 multimodal loading failure; different bugs." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowness vs. Gemma-3 EOS token config mismatch; unrelated." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Aux-loss gating bug vs. float16 AMP crash in LwDetr; different symptoms and code paths." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import performance issue vs. model-type/config validation error; not a duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 32, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43441", + "issue:43475", + "issue:43526", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43673", + "issue:43901", + "issue:44162", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44368", + "issue:44466", + "issue:44496", + "issue:44734", + "issue:44749", + "issue:44779", + "issue:44877", + "issue:44977", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45656", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:45362|issue:45375", + "issue:44162|issue:45200", + "issue:43441|issue:43540", + "issue:44295|issue:44749", + "issue:44779|issue:45292", + "issue:45292|issue:45584", + "issue:44877|issue:45375", + "issue:36246|issue:43596", + "issue:44987|issue:45459", + "issue:45292|issue:45701", + "issue:41628|issue:41950", + "issue:45561|issue:45563", + "issue:44779|issue:45701", + "issue:43901|issue:45003", + "issue:45375|issue:45759", + "issue:43065|issue:43408", + "issue:43232|issue:44336", + "issue:43257|issue:45137", + "issue:43526|issue:45003", + "issue:44995|issue:45200", + "issue:44496|issue:45003", + "issue:43262|issue:44246", + "issue:42886|issue:45229", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:44995|issue:45588", + "issue:43653|issue:44162", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:45397|issue:45656", + "issue:43673|issue:44734" + ], + "prepared_review_unit_hash": "d04f88793b4ce9d93d6fd7a7aa50dcbd7089ae4b0d144aa169be609844911769", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37084, + "estimated_input_tokens": 9271, + "estimated_eval_tokens": 18798 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft edge looks like a true duplicate; the set is mostly unrelated bug reports across different subsystems, with only loose thematic overlap in a few tokenization/configuration issues.", + "confidence": 0.24, + "canonical_issue_reason": "issue:45701 is the broadest issue here and the closest thing to an umbrella tokenization-regression report, but the cluster does not contain a strong true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45701 is the most general and reusable representative among these issues; the others are mostly narrower, model-specific, or unrelated failures.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "Same Qwen family, but one is a chat crash and the other is a missing config field; different failure modes and code paths." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "Both are model/config bugs, but they affect different models and different inputs; not the same underlying defect." + }, + { + "left": "issue:43441", + "right": "issue:43540", + "accept": false, + "reason": "Different models and different symptoms: FlashAttention failure vs video-input validation error." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Both mention version-related regressions, but one is a buffer access issue and the other is a performance slowdown; not the same bug." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Both touch tokenization/embeddings, but the concrete problems and affected paths differ." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Resize-embedding behavior and empty-transcription handling are unrelated failures." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config handling, but they target different models and different missing/strict fields." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "An import/export issue and a DeepSpeed ZeRO3 indexing error are not the same bug." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Both are load-time failures, but one is a model loading regression and the other is tokenizer error handling without protobuf." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Tokenization-version regression and resize_token_embeddings mismatch are different code paths." + }, + { + "left": "issue:41628", + "right": "issue:41950", + "accept": false, + "reason": "One is an import error for AutoImageProcessor; the other is a pipeline selecting image processors for video." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "Testing-utils xdist file race and a stale generation warning are unrelated." + }, + { + "left": "issue:44779", + "right": "issue:45701", + "accept": false, + "reason": "Both concern tokenization, but they describe different models and different symptoms; not a single concrete bug." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mismatch versus unsafe sys.modules access are unrelated issues." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal configs, but one is a missing config field and the other is AutoModelForCausalLM config unwrapping." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Same SAM3 area, but one is a decoder implementation detail and the other is a model-type warning." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation-kwargs handling and ANSI logging output are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Both involve distributed training, but one is weight conversion and the other is a ZeRO3 deque underflow." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "A label-reduction bug and a sys.modules access bug are unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "A stale indexer-cache crash and missing default token-type IDs do not share the same root cause." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model config and unsafe sys.modules access are different loading-path problems." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and slow imports are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Tokenizer offline-cache loading and Gemma4 multi-GPU OOM are different classes of failure." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Both are video/multimodal issues, but they involve different models, objects, and errors." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both mention tied embeddings/resize behavior, but they affect different model structures and serialization paths." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale cache indexing and a FlashAttention s_aux=None crash are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer special-token registration and an ESM2 model breakage are not the same issue." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Different warnings in different subsystems; not a shared defect." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "A tie_word_embeddings warning and a flash-attention generation failure are unrelated." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Both mention DeepSpeed, but one is a from_pretrained loading bug and the other is a double optimizer-step issue." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation cache behavior, but one is chunked_prefill cache availability and the other is KV-cache continuation indexing." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 33, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42994", + "issue:43232", + "issue:43452", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43704", + "issue:43827", + "issue:43931", + "issue:44038", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44623", + "issue:44661", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:45003", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45230", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45459", + "issue:45478", + "issue:45561", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:44060|issue:44077", + "issue:45003|issue:45561", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44933|issue:45459", + "issue:44869|issue:45356", + "issue:44297|issue:44623", + "issue:43646|issue:44162", + "issue:44361|issue:44749", + "issue:43232|issue:43673", + "issue:28282|issue:30990", + "issue:44623|issue:45656", + "issue:43673|issue:43827", + "issue:43452|issue:45003", + "issue:42994|issue:43482", + "issue:44749|issue:45310", + "issue:43475|issue:43643", + "issue:44749|issue:45656", + "issue:45230|issue:45397", + "issue:42371|issue:45092", + "issue:44038|issue:44623", + "issue:43475|issue:45381", + "issue:45081|issue:45103", + "issue:41628|issue:44933", + "issue:45375|issue:45478", + "issue:43475|issue:44661", + "issue:42673|issue:43704", + "issue:42994|issue:43525", + "issue:45310|issue:45375", + "issue:42222|issue:45200" + ], + "prepared_review_unit_hash": "583a8e17b277b3dcbbce6013f1a48066c6a24e5789f325054339cd8882940e99", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36050, + "estimated_input_tokens": 9013, + "estimated_eval_tokens": 18282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are unrelated regressions or model-specific bugs; only two pairs look like true duplicates based on identical titles and the same concrete failure mode.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45310 is the clearest representative of a concrete, version-specific loading regression, and it has an exact duplicate in issue:45478 with the same title and failure context.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is a strong canonical issue candidate because it is specific, actionable, and appears to have an exact duplicate; the rest of the set is too heterogeneous to serve as a better global representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Different bugs: a tied-weights warning in Qwen3-Next versus a patchtsmixer post_init policy issue." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Different code paths: unsafe sys.modules access versus an xdist race in captured_info.txt." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "Unrelated failures: DeepSpeed ZeRO3 deque error versus stale Sam3LiteText references in auto_mappings.py." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Different model problems: Qwen3-VL shape mismatch versus a tie_word_embeddings warning during Qwen3.5 fine-tuning." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Different tokenizer/import issues: missing image_utils import versus protobuf decode error masking." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer/runtime bugs: Whisper timestamp decode crash versus Kimi-K2.5 codec handling regression." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained issues, but one is tokenizer_class mismatch and the other is processor file emission; not the same bug." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Different breakages: custom model initialization under v5 versus ESM2 being broken." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "Different problems: MLukeTokenizer AttributeError versus a performance regression during filtering." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Different generation regressions: sync_gpus update bug versus missing GenerationMixin cache in chunked_prefill." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "Different startup issues: missing PyTorch ImportError versus Sentence Transformers hanging while loading." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Different subsystems: processor.save_pretrained output bug versus DeepSpeed optimizer step being called twice." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Different scope: generation cache regression versus documentation still referencing removed pipeline() APIs." + }, + { + "left": "issue:43452", + "right": "issue:45003", + "accept": false, + "reason": "Different failures: gguf_file/from_pretrained loading breakage versus unsafe sys.modules access in modeling_utils." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Related to GGUF/quantization broadly, but one is saving quantized models and the other is loading Qwen2.5-GGUF; not the same concrete bug." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Different issues: data filtering slowdown versus Qwen3.5-Moe from_pretrained error." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Different failures: SAM3 vision output attribute error versus trust_remote_code causing missing fields in AutoConfig." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Too generic on the left and specific on the right; no evidence they describe the same Zero3 from_pretrained bug." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "Unrelated: TF32 settings guidance versus old InternVL2 remote-code/meta-init incompatibility." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Different problems: Qwen3-VL-Moe/v5 compatibility versus missing files in processor.save_pretrained." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Different multimodal bugs: SAM3 output attribute error versus qwen2.5-vl video position_ids issue." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Different crashes: Mistral regex patching versus auto_docstring handling of future annotations." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but they concern different missing symbols and different import paths." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen3.5/Moe issues: missing config field versus from_pretrained regression." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Unrelated: SAM3 vision encoder output bug versus add-new-model-like failure in TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same bug and same title: Qwen3ForCausalLM VRAM leak with multiple dataloader threads." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Different model/load/save issues: quantized model saving failure versus Llama4Config missing pad_token_id." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Different bugs: Qwen3.5-Moe loading error versus missing deepstack_visual_indexes in Qwen3_5MoeVisionConfig." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different model families and failures: vitpose breakage versus Gemma 4 token-type defaults." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Exact duplicate report of the same Qwen3.5-Moe from_pretrained error, with the same title and regression context." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet metadata, and the soft-edge verdicts stay conservative overall. The two accepted duplicate pairs both have identical titles, and the rejected pairs are reasonably distinguished by different titles/subsystems." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 34, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43479", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43901", + "issue:44038", + "issue:44060", + "issue:44079", + "issue:44164", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44295", + "issue:44351", + "issue:44373", + "issue:44448", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44792", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45561", + "issue:45600", + "issue:45656", + "issue:45712" + ], + "soft_pairs": [ + "issue:42831|issue:44222", + "issue:41628|issue:44351", + "issue:44222|issue:45310", + "issue:42994|issue:44164", + "issue:42175|issue:45712", + "issue:43377|issue:44242", + "issue:36010|issue:41628", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:45561|issue:45600", + "issue:44964|issue:45137", + "issue:42898|issue:44568", + "issue:30990|issue:35141", + "issue:43901|issue:45561", + "issue:43232|issue:44792", + "issue:43232|issue:44188", + "issue:43784|issue:43824", + "issue:43278|issue:45137", + "issue:44188|issue:44373", + "issue:44623|issue:45310", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:42898|issue:45356", + "issue:43723|issue:44568", + "issue:44060|issue:45125", + "issue:45405|issue:45712", + "issue:42898|issue:44779", + "issue:43874|issue:45092", + "issue:42898|issue:44448", + "issue:43479|issue:44079", + "issue:44188|issue:44964", + "issue:44295|issue:45656" + ], + "prepared_review_unit_hash": "f1eafe935c77f67c730dad1c977ccbc01fa5dc81718b23986af672b47ec1fc94", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37273, + "estimated_input_tokens": 9319, + "estimated_eval_tokens": 18894 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are separate Transformers regressions around imports, tokenizers, serialization, multimodal models, or DeepSpeed/FP8 behavior. I do not see a single underlying duplicate bug/change tying them together.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue: the items span unrelated failure modes (imports, tokenizer behavior, save/load, model-specific regressions, and training/runtime issues) rather than one duplicate thread.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a strong global representative. If forced, issue 42898 is the broadest v5 tokenizer regression, but it still does not explain the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Both mention FP8, but one is an accuracy regression and the other is a save_pretrained failure for MoE; different bugs and code paths." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols (AutoImageProcessor vs HybridCache) with no clear shared root cause." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen/MoE-ish loading or saving problems, but one is FP8 save_pretrained and the other is a from_pretrained error for a different model/version path." + }, + { + "left": "issue:42994", + "right": "issue:44164", + "accept": false, + "reason": "Both are save/load issues, but 42994 is about quantized model saving while 44164 is about extra_state handling; too different to merge." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Both touch packaging/backend availability, but one is torch extra installation missing TensorFlow backend and the other is dummy_pt_objects cleanup; different underlying problems." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "One is a batching/padding-mask correctness bug in MIMI Encoder; the other is an MoE load-balancing-loss condition. Not the same change." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Different missing imports for different classes; these are separate export/regression issues." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both concern Qwen models on v5, but one is a Qwen3-VL-Moe bug and the other is a Qwen3.5 MoE from_pretrained error; not the same concrete defect." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "An unrecognized model/config issue is unrelated to a pytest-xdist race on a captured_info.txt test artifact." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "One is a parallel test-file race; the other is stale auto_mappings references breaking CI. Different failures." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal is unrelated to the DeepSpeed ZeRO3 deque IndexError." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer behavior regressions in v5, but they concern different APIs and symptoms: cleanup spaces vs add_special_tokens/BOS-EOS." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence-Transformers loading hangs and token embedding reinitialization are unrelated bugs." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Pipeline doc mismatch is unrelated to the xdist captured_info.txt race." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and a janus image-generation test failure are not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Different generation/attention code paths: sync_gpus kwargs handling vs torch.compile branching in attention kernels." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors from latest transformers, but they break different downstream symbols and do not share a specific fix path." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in eval is unrelated to the ZeRO3 deque IndexError." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "A kernel divergence bug and a docstring issue are not the same underlying problem." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing files in processor.save_pretrained is unrelated to Qwen3.5 MoE from_pretrained failures." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serving KV-cache indexing crash and an auto_docstring annotations crash are completely different subsystems." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed jobs and DeepSpeed OOM with Adafactor are unrelated training issues." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but one is about cleanup_spaces behavior while the other is codec handling and a warning mismatch for Kimi-K2.5." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading in v5 and add_special_tokens BOS/EOS behavior are separate problems." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Incorrect tied-weights warning and missing _tp_plan for tensor parallelism are different Qwen3.5 MoE issues." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "A dependency version pin issue is unrelated to leftover dummy classes and dir(transformers) leakage." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and behavior changes; no single shared bug is evident." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing get_number_of_image_patches in GLM46V and InternVL2 meta-initialization incompatibility are distinct multimodal loading issues." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Tokenizer cleanup behavior and Pegasus output differences across v4/v5 are related only at a broad version level, not the same concrete bug." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Phi4 multimodal config initialization and ModelOutput key assignment are unrelated object-construction bugs." + }, + { + "left": "issue:44188", + "right": "issue:44964", + "accept": false, + "reason": "Attention kernel divergence under torch.compile is unrelated to a Phi-4 multimodal model loading failure." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "A position_ids buffer read error and an optimizer step being called twice under DeepSpeed are different training/runtime issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 35, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:30990", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:38175", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42898", + "issue:42994", + "issue:43295", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43824", + "issue:43873", + "issue:43976", + "issue:44206", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44869", + "issue:44871", + "issue:44913", + "issue:44933", + "issue:44945", + "issue:44977", + "issue:45092", + "issue:45103", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45459", + "issue:45656", + "issue:45712" + ], + "soft_pairs": [ + "issue:42898|issue:43295", + "issue:44933|issue:45712", + "issue:42175|issue:44933", + "issue:41628|issue:45459", + "issue:43976|issue:44933", + "issue:44222|issue:44297", + "issue:44297|issue:45656", + "issue:43479|issue:44869", + "issue:44206|issue:45103", + "issue:42831|issue:44623", + "issue:44222|issue:44623", + "issue:30333|issue:36331", + "issue:41628|issue:42757", + "issue:43723|issue:44977", + "issue:30333|issue:34689", + "issue:44297|issue:45310", + "issue:28282|issue:30333", + "issue:30333|issue:35141", + "issue:44483|issue:45406", + "issue:43873|issue:44945", + "issue:44222|issue:44484", + "issue:44263|issue:44360", + "issue:44263|issue:45092", + "issue:44514|issue:45103", + "issue:43479|issue:43644", + "issue:44373|issue:44485", + "issue:44295|issue:44623", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:44261|issue:45092", + "issue:43479|issue:44913", + "issue:30990|issue:38175", + "issue:41628|issue:43824", + "issue:42886|issue:42994" + ], + "prepared_review_unit_hash": "1aed5c76ca6ebca6657ea0edd2e27ba5f6ae0d5a487ff4f0ea4bc41460aab8ca", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37707, + "estimated_input_tokens": 9427, + "estimated_eval_tokens": 19110 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most items are unrelated Transformers bugs across imports, tokenization, saving/loading, quantization, and training. I do not see a single canonical duplicate target, and none of the soft pairs look like true duplicates.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42898", + "right": "issue:43295", + "accept": false, + "reason": "Different regressions: tokenizer cleanup behavior vs processor/tokenizer attribute access and batched image handling." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Both involve imports, but one is a missing import from image_utils and the other is dummy PT objects leaking into dir(transformers); not the same bug." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Backend extra installation problem vs a missing image_utils import; unrelated code paths." + }, + { + "left": "issue:41628", + "right": "issue:45459", + "accept": false, + "reason": "Importing AutoImageProcessor is a public API export issue; hidden tokenizer errors without protobuf is an error-handling bug." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility regression vs import exposure in image_utils; no shared underlying defect." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Both touch save_pretrained, but one is FP8 model saving and the other is tokenizer metadata serialization; different artifacts and fixes." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer config serialization bug vs optimizer stepping twice under deepspeed; unrelated." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Multimodal config initialization vs Whisper timestamp decoding crash; different subsystems and failures." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor argument mismatch vs auto_docstring annotation parsing crash; not the same code path." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FP8 accuracy issue vs missing processor save files; different symptom and fix surface." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Both mention saving, but one is model quantization save logic and the other is processor serialization; not the same bug." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "Training job/MLflow reporting failure vs trainer loss-signature TypeError; separate trainer concerns." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Different import failures from different dependencies/modules; no shared root cause." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression vs flash-attention generation bug; different inference stages." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLflow reporting on failed training jobs is unrelated to model loading regression for a vision model." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer class metadata mismatch vs Qwen3.5 from_pretrained regression; similar area, but not the same concrete bug." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "PyTorch import dependency error vs MLflow reporting behavior; unrelated." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Training telemetry issue vs embedding resize/post_init reinitialization bug; different code paths." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "OpenAI-style chat-completions API rejection vs Gemma4Processor server crash due to missing _tokenizer; different server failures." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization offloading bug vs pipeline-parallelism output correctness issue; unrelated inference behavior." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 serialization issue vs max_shard_size default question; no shared defect." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Same broad DSA indexer area, but one is torch.split return handling and the other is a missing ReLU; not the same underlying bug." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "GLM DSA indexer bug vs remote-code/meta-init incompatibility for InternVL2; unrelated." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Processor chat-template batching crash vs auto_docstring annotation crash; different components." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Config default initialization bug vs non-persistent buffer initialization corruption; different mechanisms." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring typo vs RoPE implementation bug; not duplicates." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Position_ids buffer access problem vs missing processor save files; unrelated serialization/runtime issues." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer cache/loading regression vs eos_token_id config inconsistency; distinct tokenizer/model config issues." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen/InternVL model-family regressions and different failure modes; not mergeable as one fix." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA layernorm epsilon precision issue vs meta-init incompatibility for old InternVL2 remote-code checkpoints; unrelated." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Loading hang vs unexpected zero probabilities; different runtime symptoms and likely causes." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they affect different symbols and modules; too broad to be the same bug." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading vs quantized model saving failure; separate features and fixes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 36, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:33357", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43475", + "issue:43576", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43937", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44485", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44743", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:45200", + "issue:45245", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45593", + "issue:45600", + "issue:45753" + ], + "soft_pairs": [ + "issue:22355|issue:28282", + "issue:42831|issue:45310", + "issue:44945|issue:45753", + "issue:44263|issue:44373", + "issue:42831|issue:44038", + "issue:42757|issue:45278", + "issue:43576|issue:43784", + "issue:42886|issue:43066", + "issue:43232|issue:45593", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:42371|issue:44263", + "issue:44704|issue:45290", + "issue:43756|issue:44060", + "issue:42907|issue:44945", + "issue:43122|issue:44514", + "issue:44295|issue:44297", + "issue:43232|issue:45245", + "issue:43723|issue:44779", + "issue:43408|issue:43475", + "issue:43723|issue:44442", + "issue:43122|issue:44521", + "issue:43784|issue:45600", + "issue:42907|issue:43937", + "issue:41628|issue:45278", + "issue:44360|issue:44485", + "issue:44261|issue:44373", + "issue:43232|issue:44743", + "issue:43116|issue:45200", + "issue:44625|issue:44829" + ], + "prepared_review_unit_hash": "4b26a9501599cc0e4f3aeafce773862cb48fb58200650947bfcf5b13dff6647e", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36295, + "estimated_input_tokens": 9074, + "estimated_eval_tokens": 18404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: most items are distinct issue reports, and none of the soft pairs looks like a true duplicate or one concrete fixable bug/change. The closest shared theme is v5-era import/loading regressions, but the individual reports still target different symbols and code paths.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45278 is the broadest umbrella report in the set, explicitly summarizing multiple import failures after a version upgrade, so it is the best representative issue for this mixed cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most general, high-signal issue here and the closest thing to a cluster representative, even though the surrounding reports are not true duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Different import errors in different areas: ONNX module missing vs PyTorch dependency detection." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "Unrelated bugs: FineGrainedFP8 accuracy regression vs Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Different problem types and code paths: pipeline-parallel output corruption vs image-specific infinite loop." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "Different fixes: DSA indexer torch.split behavior vs a docstring issue for position_ids." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Distinct model-specific issues with no clear shared underlying bug." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related, but one is a specific missing hub symbol and the other is a broad migration report; not the same concrete bug." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Unrelated: broken env CLI command vs sentence-transformers import NameError." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Different tokenizer bugs: offline cache loading vs wrong decoder type in v5." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation cache handling is unrelated to D-FINE denoising/auxiliary loss behavior." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES fallback bug vs AutoProcessor kwargs passthrough bug are separate code paths." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "A loading hang is not the same as a MacOS bus error." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 API guidance vs DSA indexer split semantics are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "Processor kwargs forwarding is unrelated to chat template crashes with tool-call messages." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Different model architecture concerns: RoPE layer handling vs tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized models is not the same bug as incorrect pipeline-parallel outputs." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenization differences across versions vs batched apply_chat_template padding crash are distinct." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading a registered buffer is unrelated to tokenizer_class metadata written by save_pretrained." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation kwargs update logic is unrelated to the categories limit runtime error." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer loading failure vs incorrect Deepseek tokenization are related only broadly, not the same underlying bug." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Model-type mismatch warning and missing attribute in SAM3 are different failures." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both involve tokenizer loading, but they are different tokenizers and different failure modes." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Different chat-template bugs: tokenization inconsistency vs all-zero assistant masks." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Sentence-transformers import NameError is unrelated to Sam3LiteText auto-mapping references." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Dequantization save behavior is unrelated to invalid GenerationConfig." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Although both mention import problems after upgrade, one is a single missing symbol and the other is a broad bundle of failures; not one concrete duplicate." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA indexer missing ReLU is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A precision/config issue in MLA is unrelated to a docstring correction." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Different generation bugs: sync_gpus kwargs handling vs recurrent state reset with cache." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example script multi-label output bug is unrelated to mm_token_type_ids defaults." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation and flash_attention_3 degenerate training are separate issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 37, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:29127", + "issue:30990", + "issue:33453", + "issue:36296", + "issue:39401", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42907", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43441", + "issue:43452", + "issue:43493", + "issue:43673", + "issue:43784", + "issue:43824", + "issue:43825", + "issue:43874", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44485", + "issue:44488", + "issue:44521", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45216", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45753" + ], + "soft_pairs": [ + "issue:29127|issue:30990", + "issue:43122|issue:44779", + "issue:42907|issue:44964", + "issue:44038|issue:44297", + "issue:42907|issue:43452", + "issue:44038|issue:44295", + "issue:39401|issue:44488", + "issue:36296|issue:43116", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:43066|issue:44779", + "issue:39401|issue:44521", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:43122|issue:44977", + "issue:43992|issue:44704", + "issue:42907|issue:44222", + "issue:43784|issue:45446", + "issue:43937|issue:44485", + "issue:42222|issue:43441", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:43493|issue:45753", + "issue:42831|issue:45753", + "issue:44075|issue:44936", + "issue:43116|issue:43825", + "issue:44222|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43493", + "issue:43064|issue:43673", + "issue:45083|issue:45446", + "issue:42175|issue:44938", + "issue:43937|issue:45563", + "issue:33453|issue:39401", + "issue:39401|issue:44779" + ], + "prepared_review_unit_hash": "3029b93a2fd762a3667154c3d6b7f3e91890d9f56a3ebfe07c54225266ddd4ec", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37060, + "estimated_input_tokens": 9265, + "estimated_eval_tokens": 18786 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This looks like a heterogeneous grab-bag of Transformers issues, with a few tokenization/loading/version-regression themes but no strong evidence that any pair is the same underlying bug. The soft links are mostly topic-level similarity, not true duplicates.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43122 is the broadest tokenizer-regression report in the set and is the closest thing to a representative issue, but the overall collection is still too mixed to treat as one duplicate family.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43122 is the best single representative of the tokenization-regression subgroup because it is generic and not tied to one specific model family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "Different subsystems and symptoms: LayoutLMv3 error messaging vs Sentence Transformers loading hang." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they concern different models and concrete failure modes; not enough to call the same bug." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "One is a save/dequantization problem, the other is a model load failure; unrelated code paths." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe from_pretrained failure vs tokenizer save_pretrained metadata mismatch are different bugs." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Dequantized model saving and gguf_file loading breakage are distinct loading/saving paths." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Model loading failure and position_ids buffer read error are not the same underlying issue." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer offset_mapping regression vs a specific model load failure; too different to merge." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training optimizer bug vs example-script multi-label output issue are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Importing a specific model class and importing HybridCache are separate API-export problems." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe from_pretrained error and FP8 save_pretrained moe issue affect different paths." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenizers in v5, but one is decoder type selection and the other is incorrect Deepseek tokenization; not clearly the same bug." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Wrong offset_mapping and all-zero assistant_masks are different tokenizer/template behaviors." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5/Moe save/load regressions, but one is checkpoint saving and the other is from_pretrained loading; not the same concrete bug." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Missing huggingface_hub symbol vs missing transformers symbol are separate import regressions." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Both are tokenizer regressions, but they are model-specific reports with different symptoms and no evidence of a shared root cause." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight in UMT5Encoder vs AutoProcessor kwargs forwarding are unrelated loading behaviors." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Saving dequantized models and FP8 save_pretrained are different serialization bugs." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Importing sentence-transformers fails because of nn, while AuxRequest has a PyTorch version check issue; unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig validation error vs RoPE implementation discussion are not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Broken vitpose model loading and Ministral FlashAttention failure are distinct model-specific regressions." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance issue and missing image-patch method in GLM46V are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility problem vs a flex_attention version check bug are different compatibility issues." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and Qwen3_5 infinite-loop behavior are unrelated model bugs." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FineGrainedFP8 accuracy regression and a Qwen3_5 generation loop are different failure modes." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer argument handling and evaluate-after-train behavior are not the same training bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Example-script multi-label output bug vs pipeline translation-task error messaging are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both mention FP8/moe or Qwen3.5-related failures, but one is save_pretrained and the other is from_pretrained loading; not enough for duplication." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Same broad model family, but different versions and failure surfaces; likely separate regressions." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example script classification output vs SigLIP2 implementation discrepancy are unrelated." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Optimizer-state mismatch under FSDP2/PEFT vs missing GenerationMixin cache in chunked_prefill are different training/generation paths." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Feature-extraction helper behavior in qwen3_omni_moe and a PyTorch version check issue are not the same problem." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Missing tensorflow backend in pip install vs Python 3.14 load failure are separate environment/packaging issues." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig validation vs stale num_return_sequences warning are different generation issues." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Tokenizer loading regression and wrong offset_mapping are related at a high level, but the available evidence is too weak to merge them." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and report different concrete wrong outputs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 38, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:43012", + "issue:43066", + "issue:43122", + "issue:43381", + "issue:43408", + "issue:43421", + "issue:43450", + "issue:43577", + "issue:43742", + "issue:43827", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44291", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44496", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45405", + "issue:45446", + "issue:45459", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45588", + "issue:45656" + ], + "soft_pairs": [ + "issue:38617|issue:45278", + "issue:44117|issue:45588", + "issue:22355|issue:29127", + "issue:43827|issue:45446", + "issue:43381|issue:44945", + "issue:43937|issue:44977", + "issue:43450|issue:43986", + "issue:45405|issue:45446", + "issue:39401|issue:43421", + "issue:44117|issue:45081", + "issue:42673|issue:45072", + "issue:38617|issue:41628", + "issue:44829|issue:45216", + "issue:43408|issue:43742", + "issue:44410|issue:45310", + "issue:42222|issue:45542", + "issue:44291|issue:45071", + "issue:42175|issue:42222", + "issue:44484|issue:45310", + "issue:43937|issue:44496", + "issue:44483|issue:45464", + "issue:44075|issue:45656", + "issue:43066|issue:43122", + "issue:44964|issue:45278", + "issue:43012|issue:43577", + "issue:38617|issue:44220", + "issue:42371|issue:44261", + "issue:42222|issue:45459", + "issue:44484|issue:45478", + "issue:44410|issue:45478" + ], + "prepared_review_unit_hash": "37066426244f58d96b08b68e51c5c6c29abdd9497575f8445137f363547512a3", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36622, + "estimated_input_tokens": 9156, + "estimated_eval_tokens": 18568 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous: the soft pairs share broad themes like import errors, tokenizer bugs, or model regressions, but they do not look like the same concrete underlying bug/change. I would not merge any of the provided soft edges.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45310 is the clearest representative issue in this batch: it names a specific Qwen3.5 MoE from_pretrained regression with a concrete version boundary, and it appears to have a later near-identical duplicate (issue:45478).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best single issue to anchor this set because it is specific, reproducible, and clearly tied to a distinct regression; it is also the most obviously duplicate-prone report here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-error reports after upgrades, but they fail on different symbols and different symptoms; not the same bug." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenization mapping fallback logic and a flash-attention crash are unrelated code paths." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "A missing module import and a layoutlmv3 validation message issue are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Documentation references to pipeline() and a flex_attention version-check bug are different issues." + }, + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Gradient checkpointing in eval mode and incorrect output under pipeline parallelism are different behaviors." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig validation and flash-attention generation failure are not the same concrete defect." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor output shape and AutoProcessor without torchvision are separate problems." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "A dependency version bump and a PyTorch import version check are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Wrong offset mappings and runtime post-processor updates are both tokenizer-related but not the same bug." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "A None entry in TOKENIZER_MAPPING_NAMES and a Mistral regex patch crash are different failure modes." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "A VRAM leak in threaded inference and bfloat16 dtype mismatches are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and different affected APIs." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Flash-attention training degeneration and a save_pretrained checkpoint regression are not the same issue." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "A model-type mismatch warning and a key error while loading a model are different problems." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Missing projections in qwen3next and Qwen3.5 MoE from_pretrained loading failure are distinct defects." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "Vitpose model breakage and a TensorFlow backend availability issue are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "These are both v5 compatibility regressions, but they affect different APIs and code paths." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Missing TensorFlow in a torch-only install and broken vitpose models are not the same bug." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "save_pretrained shard-size behavior and Qwen3.5 MoE loading failure are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "GenerationConfig invalidity and an unrecognized model/config error are different loading paths." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "A /v1/chat/completions request-shape issue and a streaming inference failure on Qwen3.5 are not clearly the same defect." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "SGD arguments being ignored and deepspeed calling optimizer.step() twice are different optimizer bugs." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Wrong decoder type and changed tokenization output are related to tokenizer regressions but not the same concrete issue." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "A specific Phi-4 multimodal load failure and a broad set of import errors after upgrade are not the same bug." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A warning about bfloat16 compilation and a model remaining float32 on load are different dtype-related issues." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "An import error and an fbank feature-extraction issue are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 control API guidance and an rms_norm_eps precision problem are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "Vitpose breakage and protobuf-related tokenizer error masking are different subsystems." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "max_shard_size behavior and Qwen3.5 MoE from_pretrained loading failure are unrelated." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Missing qwen3next projections and Qwen3.5 MoE loading failure are different model bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 39, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42371", + "issue:42673", + "issue:42757", + "issue:42831", + "issue:43012", + "issue:43064", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43502", + "issue:43577", + "issue:43873", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44464", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44704", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45341", + "issue:45375", + "issue:45542", + "issue:45588" + ], + "soft_pairs": [ + "issue:43097|issue:44493", + "issue:43874|issue:44261", + "issue:44263|issue:44485", + "issue:43012|issue:43408", + "issue:43441|issue:44829", + "issue:41628|issue:45071", + "issue:45071|issue:45542", + "issue:42673|issue:44977", + "issue:42371|issue:42831", + "issue:42673|issue:43906", + "issue:43986|issue:44484", + "issue:44117|issue:44987", + "issue:43097|issue:43452", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43976|issue:44945", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:44829|issue:45245", + "issue:38617|issue:42757", + "issue:43064|issue:44315", + "issue:44464|issue:45071", + "issue:44410|issue:45375", + "issue:44062|issue:44117", + "issue:43097|issue:45588", + "issue:42673|issue:43577", + "issue:38617|issue:44351", + "issue:44704|issue:45103", + "issue:44038|issue:44410", + "issue:43931|issue:44410", + "issue:43986|issue:44117", + "issue:44261|issue:44485", + "issue:44964|issue:45341", + "issue:43502|issue:43992", + "issue:43097|issue:43873" + ], + "prepared_review_unit_hash": "a664ae640b2f15f54679694acf367432a9607c616c76425102cbca83f8780b0e", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38164, + "estimated_input_tokens": 9541, + "estimated_eval_tokens": 19338 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: it mixes import errors, model-loading regressions, flash-attention bugs, config warnings, and unrelated model-specific failures. I did not find any soft-edge pair that looks like the same underlying bug/change.", + "confidence": 0.96, + "canonical_issue_reason": "issue:43097 is the most cluster-central release-regression report by linkage/activity, so it\u2019s the best triage anchor among these unrelated issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43097 is the best representative issue for this cluster because it is a concrete, user-facing v5 regression and has the strongest evidence of being a hub among the listed items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Both are transformer regressions, but one is about a removed config warning and the other is about unexpected position-id keys; different bug classes and code paths." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Different models and failures: missing image-patch helper in GLM46V vs a missing rms_norm_eps config field affecting MLA precision." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "One is a torch.split/indexing bug in GlmMoeDsaIndexer; the other is a GLM-5 RoPE implementation discussion. Not the same concrete defect." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "A PyTorch precision warning during bfloat16 compilation is unrelated to a model-type mismatch warning between sam3_video and sam3_tracker." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both mention flash attention, but they target different symptoms, models, and training/inference paths; too broad to merge." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Importing AutoImageProcessor and PretrainedConfig type checking are unrelated issues." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Type-checking regression in PretrainedConfig is unrelated to the TensorFlow/tensorboard backend detection issue." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "VRAM leak in multi-threaded dataloaders is a different problem from Qwen3.5 flash-attention generation failures." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 API guidance and FineGrainedFP8 accuracy loss are distinct numeric/configuration issues." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "The second is only an isolated reproduction of another issue, but the titles don\u2019t indicate the same concrete bug as the VRAM leak report." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor crash without torchvision is unrelated to save_pretrained max_shard_size behavior." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "A tokenizer mapping None-handling bug is not the same as loading failures for physical-intelligence/fast." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed tie_embeddings API behavior is unrelated to gguf_file loading failures." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Both involve Qwen3-VL family loading, but they describe different model variants and failure modes; not enough to treat as one bug." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation bug is unrelated to a typing regression in PretrainedConfig." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version compatibility and incorrect output under pipeline parallelism are different issues." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Model-type warning for SAM3 is unrelated to a tie_word_embeddings warning during Qwen3.5 LoRA fine-tuning." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM subcomponents and different symptoms; one is an AttributeError in an image processor path, the other a torch.split/indexing issue." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention training degeneration is unrelated to a categorical cardinality runtime limit." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they concern different symbols from different packages and different missing APIs." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Wrong optimizer states under FSDP2/PEFT is not the same underlying bug as Liger Kernel not being applied with model_init." + }, + { + "left": "issue:44464", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Different Qwen configuration bugs affecting different fields and model families; not the same defect." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken argument duplication is unrelated to tokenizer mapping returning None." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Both are v5-era regressions, but one is about removed tie_embeddings guidance and the other is a flash_attention.py crash on sink-less models." + }, + { + "left": "issue:42673", + "right": "issue:43577", + "accept": false, + "reason": "VRAM leak in threaded dataloading is unrelated to dtype handling for BLIP2 loading." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports from different modules; no shared underlying bug." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Passing kwargs to cached_file is unrelated to auto_docstring crashing with future annotations." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Two different Qwen model issues with different missing/mismatched components; not one concrete bug." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "A shape-mismatch loading error for Qwen3-VL-30B-A3B is unrelated to missing projections in qwen3next layer 0." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "AutoProcessor/torchvision crash is unrelated to tokenizer mapping fallback behavior." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Missing rms_norm_eps in MLA q_a_layernorm is unrelated to GLM-5 RoPE implementation questions." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal is unrelated to a testing_utils bug." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Offline-mode network requests are unrelated to missing embed_tokens.weight in UMT5Encoder loading." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Removed tie_embeddings behavior is unrelated to quantization/offloading not working as expected." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 40, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:36683", + "issue:38617", + "issue:42617", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43381", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43531", + "issue:43550", + "issue:43618", + "issue:43761", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43901", + "issue:43906", + "issue:43937", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44220", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45381", + "issue:45561", + "issue:45588", + "issue:45753" + ], + "soft_pairs": [ + "issue:43066|issue:43906", + "issue:43986|issue:45372", + "issue:43825|issue:44655", + "issue:43986|issue:45290", + "issue:45341|issue:45561", + "issue:43986|issue:45341", + "issue:43097|issue:43901", + "issue:42617|issue:45341", + "issue:43992|issue:44484", + "issue:45341|issue:45588", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:43012|issue:43550", + "issue:43208|issue:43550", + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:43531|issue:45341", + "issue:44483|issue:44514", + "issue:43208|issue:43526", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:43618|issue:43761", + "issue:44483|issue:45290", + "issue:43064|issue:44380", + "issue:44038|issue:44230", + "issue:43299|issue:43867", + "issue:38617|issue:43502", + "issue:44483|issue:45381", + "issue:43901|issue:44655", + "issue:36683|issue:43475", + "issue:44220|issue:44655", + "issue:43867|issue:45216", + "issue:43352|issue:43937", + "issue:42994|issue:44655", + "issue:43066|issue:45381" + ], + "prepared_review_unit_hash": "1c000879755fb7155722934f96720f7c08f6c268a489ddab48768d44f069b6bc", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37888, + "estimated_input_tokens": 9472, + "estimated_eval_tokens": 19200 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly near-misses across different Transformers regressions; the only somewhat central item is the broad testing_utils report, but the cluster is too heterogeneous for duplicate merging. No PRs are present.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45341 is the broadest and most central-looking issue in this set, but it still appears to be just a loose representative rather than a true duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45341 is the best general anchor only because it is the most generic/open report and appears in the most soft-similarity candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Different failures: tokenizer decoder type mismatch vs an isolated reproduction of a separate import/path issue." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Both are import/load-time crashes, but they involve different missing symbols and different model/processor paths." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Error-message regression in pipeline task support is unrelated to saving Pipeline objects." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor/torchvision dependency crash is unrelated to chat-template handling with tool-call messages." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Same testing-utils area, but one is a vague bug note and the other is a specific xdist file-race bug." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "One is a processor-loading dependency crash; the other is a generic testing-utils bug." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "Removed API warning and stale docs entry are different kinds of changes with different targets." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "3d_parallel execution failure is unrelated to testing_utils behavior." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing embed_tokens.weight during model load is unrelated to the save_pretrained shard-size question." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Testing-utils bug and flash_attention crash on s_aux=None are different code paths and symptoms." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but they come from different APIs and different configuration checks." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading and eval-mode gradient checkpointing are unrelated runtime behaviors." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "Precision warning during compile is not the same bug as Bamba compile failing with SDPA." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training blockers and Bamba torch.compile+SDPA failure are different model-specific issues." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models is unrelated to an infinite-generation loop on a specific image." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Quantized/dequantized save failure is not the same as saving Pipeline objects." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to testing_utils." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Chat/completions API rejection and processor chat-template batching are distinct failures." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs do not match a BeitImageProcessorFast label-reduction bug." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "A warning about bfloat16 precision is not the same as compiled flex_attention failing on torch>=2.9." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are ImportErrors, but they concern different missing symbols in different modules." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Related CLIP regressions, but one is missing attentions and the other is missing hidden_states." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Different layers of the stack: an endpoint validation failure vs a tokenizer/template crash." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Optimizer-state corruption under FSDP2+PEFT is unrelated to GPT2 attention scaling being ignored." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Qwen3-VL/MoE loading regression and fp8 inference support are separate feature/regression reports." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL model loading breakage is unrelated to a sorted-state_dict load error." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Importing a removed utility is unrelated to API requests happening despite local_files_only=True." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "Chat/completions request rejection is unrelated to wrong video vision_position_ids." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mentioning return_all_scores are unrelated to Pipeline save_pretrained behavior." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config missing vocab_size and SAM3 VisionEncoderOutput missing fpn_position_embeddings are different model attribute bugs." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Fbank feature extraction bug is unrelated to saving Pipeline objects." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Sorted state_dict load failure and Qwen3.5 save_pretrained checkpoint regression are different directions of the serialization path." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Flash-Attention-2 unsupported error is unrelated to invalid GenerationConfig for GLM-5." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model save failure and Pipeline save_pretrained failure are different object types and code paths." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Tokenizer decoder type regression is unrelated to Qwen2.5-VL video position-id issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 41, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36010", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42757", + "issue:42890", + "issue:43064", + "issue:43097", + "issue:43299", + "issue:43352", + "issue:43441", + "issue:43525", + "issue:43575", + "issue:43618", + "issue:43756", + "issue:43867", + "issue:43881", + "issue:43906", + "issue:43976", + "issue:43992", + "issue:44077", + "issue:44117", + "issue:44242", + "issue:44246", + "issue:44263", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44485", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44977", + "issue:45216", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45561", + "issue:45588", + "issue:45753" + ], + "soft_pairs": [ + "issue:36010|issue:42757", + "issue:44263|issue:45440", + "issue:43756|issue:44485", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:43906|issue:45753", + "issue:36683|issue:44242", + "issue:36683|issue:43881", + "issue:43299|issue:45753", + "issue:43352|issue:43976", + "issue:43992|issue:45310", + "issue:41669|issue:44246", + "issue:43441|issue:44380", + "issue:43352|issue:44380", + "issue:44380|issue:45479", + "issue:43867|issue:45375", + "issue:43064|issue:44492", + "issue:43618|issue:44380", + "issue:43352|issue:45478", + "issue:44355|issue:44855", + "issue:36683|issue:44117", + "issue:42890|issue:45561", + "issue:43097|issue:43352", + "issue:43867|issue:45357", + "issue:43976|issue:44938", + "issue:43992|issue:45478", + "issue:44360|issue:45440", + "issue:43064|issue:44655", + "issue:36296|issue:43575", + "issue:44077|issue:44380", + "issue:43618|issue:44857", + "issue:43618|issue:45588", + "issue:43867|issue:44484", + "issue:28282|issue:33453", + "issue:43618|issue:44977" + ], + "prepared_review_unit_hash": "ef64ac19bc4746fa4d3a1a7ad237943eeffd0f92a02030f911bdfbc1acc85b44", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37796, + "estimated_input_tokens": 9449, + "estimated_eval_tokens": 19154 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a grab-bag of unrelated Transformers bug reports; the only strong duplicate-like link is an import-time slowdown report and its concrete root-cause issue.", + "confidence": 0.66, + "canonical_issue_reason": "issue:41669 is the most concrete statement of the import-performance regression, naming the likely cause (import * in models) and the observed slowdown; it can absorb the vaguer symptom report in issue:44246.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41669 is the best representative because it is specific, actionable, and likely explains the broader import-slowdown symptom better than the generic performance complaint.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols from different packages, so they are not the same underlying bug." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "Different model paths and failure modes; one is a DSA indexer tensor-splitting issue, the other is a DeepseekV3MoE implementation divergence." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Both mention RoPE, but they concern different models and different implementation concerns, not one shared bug." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Both are missing-config-attribute reports, but for different configs and different fields, so they are not the same defect." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "Unrelated issues: CLIP attentions not being assigned versus a Qwen3.5 checkpoint save regression." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "The reproduction issue is too generic to equate with the Qwen3_5 image infinite-loop report; no clear same bug is shown." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Different MoE-related bugs: a missing config field versus a load-balancing loss condition." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Different models and failures; a missing Gemma3Config field is not the same as a GLM-4V loading problem." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Both involve Qwen3.5-family models, but one is a MoE loading regression and the other is an image-generation infinite-loop bug." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "These are unrelated: a FlashAttention support error for one model versus a Python-version compatibility issue." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different problems: missing UMT5 encoder weights versus a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both describe the same import-time slowdown in Transformers; 41669 identifies the likely cause while 44246 reports the symptom." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Both touch attention backends, but one is a model-specific FlashAttention crash and the other is an attention-scaling config mismatch." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "A model-specific FlashAttention support limitation is not the same as GPT-2 attention scaling being ignored under backend changes." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Different bugs: backend-specific attention scaling versus a zero-loss classification edge case." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "A generic state-dict loading failure is not the same as a missing Qwen3_5MoeVisionConfig field being dropped by strict handling." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Completely unrelated: distributed optimizer-state corruption versus a cache-strategy typo." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "Different model/output regressions; CLIPOutput attentions missing is unrelated to GPT-2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Same broad flash-attention area, but different models and different concrete failures; not one mergeable fix." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Both are import/runtime failures, but one is about compiled Python files and the other is a Python 3.13 TorchScript parsing issue." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "Different loading bugs: a missing config attribute versus TOKENIZER_MAPPING_NAMES returning None." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Both are test-related, but one is flaky seed usage in integration tests and the other is an xdist race on a captured-info file." + }, + { + "left": "issue:43097", + "right": "issue:43352", + "accept": false, + "reason": "Unrelated: an API removal in 5.0.0 versus a FlashAttention support error for Nemotron." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "A generic sorted-state-dict load error is not the same as incorrect Qwen3.5 visual encoder keys being saved." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both are Python-version compatibility reports, but they target different version ranges and likely different root causes." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Different loading failures affecting different models and fields; no shared underlying bug is evident." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "These are different MoE/DSA issues; one is a missing ReLU in the indexer, the other is a DeepseekV3MoE implementation mismatch." + }, + { + "left": "issue:43064", + "right": "issue:44655", + "accept": false, + "reason": "Completely different problems: distributed training optimizer state corruption versus saving Pipeline objects." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both mention tensor parallelism, but one is a training bug and the other is an OOM during model loading." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "Unrelated model/config validation issue versus an attention-backend scaling bug." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Different failures in different subsystems: CLIP attentions assignment versus AMP/CUDA crash in LwDetrImageLoss." + }, + { + "left": "issue:43618", + "right": "issue:45588", + "accept": false, + "reason": "Both mention attention-related code, but one is missing CLIPOutput attentions while the other is a flash_attention.py crash on sink-less models." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "A load-model state_dict ordering issue is unrelated to save_pretrained shard-size behavior." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Different import/load failures: missing PyTorch for AutoModel versus a tokenizer-loading regression." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different model-specific regressions; CLIPOutput attentions missing is not the same as Qwen3.5 flash-attention generation failure." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays mostly conservative. The only accepted soft edge, issue:41669 vs issue:44246, is supported by the titles and is phrased cautiously. The remaining negatives generally rely on clear title-level mismatches in model, subsystem, or failure mode, without overstating duplicate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 42, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43299", + "issue:43502", + "issue:43576", + "issue:43723", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:43976", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44222", + "issue:44230", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44485", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44938", + "issue:44961", + "issue:44964", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45341", + "issue:45375", + "issue:45468", + "issue:45478", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:43901|issue:44938", + "issue:42890|issue:44964", + "issue:44655|issue:44938", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:42890|issue:45341", + "issue:43010|issue:44075", + "issue:44222|issue:45125", + "issue:42548|issue:44351", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:30990|issue:31795", + "issue:45125|issue:45478", + "issue:45125|issue:45375", + "issue:43010|issue:45278", + "issue:44387|issue:44556", + "issue:43723|issue:44556", + "issue:30333|issue:33453", + "issue:43010|issue:44368", + "issue:43502|issue:44222", + "issue:44315|issue:44360", + "issue:43502|issue:44961", + "issue:44355|issue:44655", + "issue:30333|issue:36296", + "issue:42831|issue:43874", + "issue:44355|issue:45071", + "issue:44222|issue:44230", + "issue:43827|issue:44961", + "issue:43010|issue:45656", + "issue:33453|issue:34689", + "issue:43299|issue:44556", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43576|issue:45071", + "issue:43576|issue:43824", + "issue:43010|issue:43976", + "issue:44961|issue:45468", + "issue:38617|issue:43576", + "issue:31795|issue:38617" + ], + "prepared_review_unit_hash": "adcb3e7dfeb46384e5096478d8d76f74e478bd7d64bfd2aa296b1b96ee5feb78", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 39162, + "estimated_input_tokens": 9791, + "estimated_eval_tokens": 19838 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of Transformers v5 regressions (imports, model/tokenizer loading, FP8, CLI, docs, tests, and training/runtime bugs). The soft links are generally too broad or only vaguely similar; none look like the same concrete underlying bug/change.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45278 is the best representative umbrella issue: it summarizes broad import breakage after upgrading to 5.5.0, which matches the cluster\u2019s dominant v5-regression theme.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the strongest global representative because it is broad, version-specific, and captures the common import/load regression pattern better than the narrower or more isolated reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43901", + "right": "issue:44938", + "accept": false, + "reason": "Docs for TextClassificationPipeline return_all_scores and a Python 3.14 load failure are unrelated symptoms and code paths." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "A flaky integration test missing set_seed is unrelated to a Phi-4 multimodal model loading failure." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "Pipeline save_pretrained support and Python 3.14 import/load failure do not describe the same bug." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Missing set_seed in tests is unrelated to a stale device-override CI failure." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "Test seed flakiness and auto_mappings.py CI breakage are different issues in different paths." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only network leakage and AddedToken keyword handling are distinct bugs." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A test flake and a bug in testing_utils.py are not the same concrete failure." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "@torch.no_grad decoration for cache updates is unrelated to SGD optimizer arguments not being used." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "Both mention MoE/FP8/tensor-parallel areas, but one is FP8 save_pretrained and the other is missing _tp_plan for tensor parallelism; not the same fix." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Missing PreTrainedModel and missing HybridCache are separate import-export regressions." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Unexpected network requests and a GLM-5 RoPE discussion are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled-Python-file errors and slow filtering after upgrade are different issues." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers loading stuck and documentation confusion about model.forward arguments are unrelated." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is a tensor-parallel plan omission and the other is a broader from_pretrained error; too little evidence they share one concrete fix." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Missing _tp_plan for tensor parallelism and a missing config field silently dropped by @strict are different model config bugs." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache/layer update decoration and broad import errors after upgrade are not the same code-path problem." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 CUDA reserved-memory OOM and checkpoint reload breakage across versions are different failure modes." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading regression and checkpoint reload incompatibility are both load-related but not the same underlying issue." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow reporting after training failure and tokenizer loading regression are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "@torch.no_grad on cache updates and tie_word_embeddings warning noise do not share a concrete bug." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Network requests despite local_files_only and FP8 save_pretrained issues are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel not applied in model_init and a missing ReLU in the DSA indexer are unrelated subsystems." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "API requests despite local_files_only and an unrelated 'racoon' issue have no overlap." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Errors with compiled Python files and Pipeline save_pretrained are different problems." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLFlow reporting on failed training jobs and tensor-parallel training bugs are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy issues and a missing get_number_of_image_patches method are separate model bugs." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file errors and PretrainedConfig type-checking breakage are distinct." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8/MoE, but one is save_pretrained and the other is inference support; not the same change." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() and an unrelated 'racoon' issue are not duplicates." + }, + { + "left": "issue:43010", + "right": "issue:45656", + "accept": false, + "reason": "Cache update no_grad decoration and optimizer.step being called twice with deepspeed are different runtime bugs." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 model loading breakage are both loading-related but not the same concrete issue." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Qwen3VL MoE loading failure and checkpoint reload incompatibility across versions are not clearly the same root cause." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "A missing huggingface_hub symbol import and a broken transformers env command are unrelated." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are different failures." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken env CLI and PretrainedConfig type-checking are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env CLI and Qwen2_5_VL import failure are not the same bug." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update no_grad decoration and Python-version compatibility issues are unrelated." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "'racoon' and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "layer_type_validation import failure and env CLI breakage are distinct regressions." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion and an ImportError from configuration_utils are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 43, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:36296", + "issue:41628", + "issue:41669", + "issue:42371", + "issue:42548", + "issue:42890", + "issue:43010", + "issue:43232", + "issue:43352", + "issue:43408", + "issue:43526", + "issue:43576", + "issue:43673", + "issue:43827", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44261", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44393", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45341", + "issue:45478", + "issue:45542", + "issue:45753" + ], + "soft_pairs": [ + "issue:41628|issue:42548", + "issue:43576|issue:44351", + "issue:44908|issue:44961", + "issue:43010|issue:43232", + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:44261|issue:44360", + "issue:44273|issue:45003", + "issue:44273|issue:45542", + "issue:44623|issue:45230", + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:41669|issue:43673", + "issue:44393|issue:45071", + "issue:44038|issue:45125", + "issue:44556|issue:45092", + "issue:44961|issue:45092", + "issue:44704|issue:44908", + "issue:42890|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:43576|issue:44908", + "issue:44297|issue:45230", + "issue:43673|issue:44492", + "issue:44908|issue:45071", + "issue:44295|issue:45230", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:41669|issue:44492", + "issue:44393|issue:45478", + "issue:44315|issue:44829", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:42371|issue:44492", + "issue:43576|issue:44273", + "issue:44655|issue:44861" + ], + "prepared_review_unit_hash": "47e58838d3571a7cc2d7a74f78a1d000cae58939c1a40204402838eb8eb4b90e", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 41, + "serialized_chars": 39327, + "estimated_input_tokens": 9832, + "estimated_eval_tokens": 19920 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Loose heterogeneous cluster of Transformers issues spanning import/lazy-loading, generation/cache, docs, and model-specific bugs. No PRs are present, and none of the soft edges look like the same concrete fix.", + "confidence": 0.39, + "canonical_issue_reason": "issue:41669 is the broadest and most connected import/lazy-loading/performance report in the set, with inbound references and overlap with several import-related artifacts.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41669 is the best representative triage anchor because it sits near the center of the cluster\u2019s import-related subtheme and has the strongest evidence of cross-issue relevance.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import failures, but for different symbols and different root causes." + }, + { + "left": "issue:43576", + "right": "issue:44351", + "accept": false, + "reason": "One is the v5 env command, the other is a missing import; not the same bug." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs and an unrelated placeholder issue." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Different generation/cache code paths and different symptoms." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug versus a documentation mismatch." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Missing AutoImageProcessor import is unrelated to compiled-file execution errors." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Different model-specific bugs: tensor parallel training versus BeitImageProcessorFast label reduction." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "Precision/eps configuration issue versus a DSA indexer activation complaint." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading and sys.modules access are related themes, but not the same underlying defect." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading is unrelated to the TensorFlow backend dependency error." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Processor save_pretrained missing files is not the same as a generic bug report." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Same model family, but different failure modes: bad bbox output versus infinite looping." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Both mention v5 regressions, but one is the env command and the other is checkpoint reload compatibility." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star cleanup/performance is unrelated to chunked_prefill cache handling." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Model output hallucination versus a PretrainedConfig typing break." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Different Qwen3-family issues with different code paths and fixes." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both are v5 compatibility complaints, but they concern different models and different breakages." + }, + { + "left": "issue:44961", + "right": "issue:45092", + "accept": false, + "reason": "Unrelated placeholder issue versus remote-code checkpoint incompatibility." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor cached_file kwargs and inverse_sqrt scheduler kwargs are unrelated." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing seeds is unrelated to scheduler kwargs." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import slowdown and lazy-loading breakage are adjacent but distinct bugs." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model-type warning and Liger Kernel application are different concerns." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility and Qwen3-VL output bugs are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention support gating is unrelated to the Qwen3-VL bbox issue." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "v5 env-command breakage is unrelated to scheduler kwarg handling." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save metadata mismatch is unrelated to the generic bug report." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked-prefill cache missing and a typo in cache strategies are not the same defect." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs issue versus type-checking regression." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "position_ids buffer handling is unrelated to the generic bug report." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star removal/performance and missing HybridCache import are different import issues." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import performance issue versus a testing_utils bug." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-star cleanup and cache-strategy typo are unrelated." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen3.5/Moe regression than the bbox hallucination report." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel model_init behavior and flash_attention_3 training degeneration are distinct issues." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Optional post_init validation and tied-weight key crashes are different code paths." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() is unrelated to inverse_sqrt scheduler kwargs." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Model.forward docs confusion and tokenizer-loading regression are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import-star cleanup/performance is unrelated to scheduler kwarg handling." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 settings guidance and a cache-strategy typo are unrelated." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Pipeline save_pretrained failure and tied-weight-key AttributeError are different bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 16, + "review_unit_index": 44, + "review_unit_count": 44, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-384", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43606", + "issue:43704", + "issue:43827", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44315", + "issue:44360", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468" + ], + "soft_pairs": [ + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:43827|issue:44492", + "issue:44273|issue:44908", + "issue:43519|issue:44485", + "issue:41669|issue:43704", + "issue:43519|issue:44908", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:43704|issue:44485", + "issue:44485|issue:45468", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468", + "issue:44261|issue:45468", + "issue:43704|issue:45341", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:41669|issue:44998", + "issue:43704|issue:44998", + "issue:43525|issue:44861", + "issue:43066|issue:44998", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44360|issue:44998", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "da7980170dcebc6f57633fa387326e973a55caf918940764a24aa8167660d519", + "component_budget": { + "node_count": 384, + "item_count": 384, + "soft_pair_count": 1442, + "serialized_chars": 743103, + "estimated_input_tokens": 185776, + "estimated_eval_tokens": 371808 + }, + "budget": { + "node_count": 38, + "item_count": 38, + "soft_pair_count": 37, + "serialized_chars": 32374, + "estimated_input_tokens": 8094, + "estimated_eval_tokens": 16444 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is largely heterogeneous: most items are unrelated bugs, docs, model-loading, or training issues. There is a small tokenizer/v5 subgroup, but no soft pair is close enough to treat as the same underlying change or bug.", + "confidence": 0.95, + "canonical_issue_reason": "issue 43066 is the most concrete and actionable standalone report in the cluster; it describes a specific tokenizer v5 regression rather than a broad symptom or unrelated subsystem issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue 43066 is the best global issue candidate because it is specific, user-facing, and likely to attract/organize related tokenizer-v5 reports more cleanly than the broader alternatives.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "Different model/component bugs: DSA indexer ReLU behavior vs Gemma4 audio positional encoding." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "One is a generic bug report; the other is a specific Qwen3.5-MoE from_pretrained regression. Not the same issue." + }, + { + "left": "issue:43827", + "right": "issue:44492", + "accept": false, + "reason": "Docs referencing removed pipeline APIs and a cache-strategy typo are unrelated." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading failure and inverse_sqrt scheduler kwarg handling affect different code paths." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp calculation vs GLM-5 RoPE implementation are different model-specific bugs." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import * cleanup/performance issue is unrelated to VRAM leakage in multithreaded dataloaders." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp math and scheduler kwargs are unrelated subsystems." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion about forward args is unrelated to a Llama 3.2 model-loading regression." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Forward-doc clarification and flash-attention import failure are different problems." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Both involve model creation/loading, but one is Liger Kernel application with model_init and the other is remote-code/meta-init incompatibility; not the same bug." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in threaded inference and RoPE implementation are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different model components: RoPE implementation vs audio relative positional encoding." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 configuration guidance is unrelated to a memory leak in dataloader threads." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Local-files-only network access and Qwen3VL timestamp errors are different bugs." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Timestamp calculation in a processor and missing processor save files are separate issues." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Processor timestamp bug and multithreaded VRAM leak do not share a concrete code path." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "A torch.split return-value issue in one indexer is unrelated to Gemma4 audio positional encoding." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch for bark-small is unrelated to Gemma4 audio positional encoding." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Layernorm epsilon/config precision discussion is unrelated to Gemma4 audio positional encoding." + }, + { + "left": "issue:43704", + "right": "issue:45341", + "accept": false, + "reason": "VRAM leak in dataloader threads and a testing_utils bug are unrelated." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both mention tokenizer v5 behavior, but one is broad behavior drift and the other is a specific decoder-type mismatch; not enough evidence of the same underlying bug." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs handling and an unrelated placeholder issue are not the same." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight-key handling and chat template crashes involve different code paths." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import cleanup/performance issue is unrelated to the placeholder issue." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "VRAM leak bug is unrelated to the placeholder issue." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config and tied-weight-key attribute handling are different failures." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Tokenizer decoder-type regression is unrelated to the placeholder issue." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression and tied-weight-key handling are different issues." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading and an ImportError for layer_type_validation are not the same bug." + }, + { + "left": "issue:44360", + "right": "issue:44998", + "accept": false, + "reason": "DSA indexer behavior is unrelated to the placeholder issue." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support for Qwen models and processor save_pretrained missing files are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLFlow job-status reporting and slow from_pretrained checkpoint loading are different problems." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Slow checkpoint loading is unrelated to a tensor-parallel training bug." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Loading performance and forward-API documentation confusion are not the same issue." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "FP8 inference support and Qwen3.5-MoE from_pretrained failure are separate Qwen-related reports with different concrete failures." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading and tokenizer loading regression are distinct bugs." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching for audio models and Qwen fp8 inference support are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "2770400a9e467b8f30b6d6d65fa3cd3d0a8edbfab7eb4a7129a90ad1be3ca6ee", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate community feature requests, not duplicates: one asks for Flash Attention 2 support for more architectures, the other for GGUF support for more architectures. The soft similarity signal is too broad to treat them as the same underlying issue.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature areas and codepaths (Flash Attention 2 vs GGUF); they share only a broad \u2018more architectures\u2019 theme, so they are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-4", + "nodes": [ + "issue:27088", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "6ce48d1491b884fcc9c0ee1936c7fddc7cc03167a8eb6addbd4efed853a5a838", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4454, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4454, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are issue-template style requests for translating docs, but they appear to target different languages rather than the same underlying task. No PRs are present.", + "confidence": 0.79, + "canonical_issue_reason": "issue:27088 is the only specific, fully named request (Turkish) and is the most concrete representative of the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:27088 is the clearest issue to keep as the representative because it is specific and not a placeholder-style template title.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Both are translation-request issues, but they do not indicate the same target language or the same concrete change; this looks like template similarity only." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Same broad i18n-docs theme, but no evidence they refer to the same language or duplicate request." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "The titles suggest different language-specific translation requests, so they should not be merged as duplicates." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "Highly similar template structure, but no proof they are the same translation task rather than separate language requests." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "These look like repeated template issues, not the same underlying bug/change." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "No concrete overlap beyond the generic translation-docs template; reject as duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-14", + "nodes": [ + "issue:36817", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:37015|issue:42503", + "issue:37015|issue:45027", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:45322", + "issue:43837|issue:43909", + "issue:43909|issue:44205", + "issue:43671|issue:43909", + "issue:44121|issue:45322", + "issue:43837|issue:44121", + "issue:43837|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "19087cc10efede8e85b35f9957c304b1f327961cbb2b15e296c0015728584579", + "component_budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 28, + "serialized_chars": 17649, + "estimated_input_tokens": 4413, + "estimated_eval_tokens": 9082 + }, + "budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 28, + "serialized_chars": 17649, + "estimated_input_tokens": 4413, + "estimated_eval_tokens": 9082 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All items are distinct model-request issues spanning different architectures, model families, or modalities. There is no true duplicate cluster here; the closest pair is Qwen3-TTS vs Qwen3-ASR, but those are separate code paths and should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different model families (EuroBert vs DEIMv2); same broad request type only." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config request vs Qwen3-TTS support; unrelated models." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are different model requests and code paths." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT vs weight-sparse transformer; different architectures." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT vs LFM2.5 Audio; unrelated model families." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are separate model additions." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT vs Voxtral TTS; different model targets." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture request vs Qwen3-ASR support; not the same change." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 vs sparse-transformer request; different concrete model work." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are distinct model requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 vs Voxtral TTS; unrelated model families." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 vs Qwen3-TTS; separate model additions." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT vs Qwen3-ASR; different model targets." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT vs Qwen3-TTS; distinct requests." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT request vs a generic BERT-like RoPE proposal; not the same issue." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "Generic BERT-like RoPE discussion vs Voxtral TTS support; unrelated." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Same Qwen3 family, but TTS vs ASR are different modalities and likely separate code paths." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS vs Voxtral TTS; different model families." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS vs DeepSeek-OCR2; unrelated model requests." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS vs weight-sparse transformer; different changes." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR support vs LFM2.5 Audio; separate audio model requests." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR vs sparse-transformer request; not the same bug/change." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR vs Voxtral TTS; different models and tasks." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR vs DeepSeek-OCR2; unrelated." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR vs EUPE; different model families." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio vs SAM3-LiteText; distinct model support requests." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS vs LFM2.5 Audio; different audio models and code paths." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse transformer request vs EUPE; unrelated model additions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-37934-6", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031" + ], + "soft_pairs": [ + "issue:37934|issue:43668", + "issue:42936|issue:43240", + "issue:42936|issue:44031", + "issue:42936|issue:43813", + "issue:42936|issue:43668", + "issue:43240|issue:43668", + "issue:43668|issue:44031", + "issue:43668|issue:43813" + ], + "prepared_review_unit_hash": "04e2237cec87510ce1e840ce44f7f7109d957411609a42436a0b0b5f7864c5a4", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "No duplicate cluster here: the issues span unrelated bugs across different models and tokenizer/config code paths. All soft links look like false positives from superficial wording overlap.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical duplicate stands out; these six issues describe different problems in different components rather than the same underlying bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44031 is the broadest and most impactful report in the set, with the most discussion and the clearest user-facing regression, so it is the best representative issue if one must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different problems: one questions Llama4TextL2Norm semantics, the other is a ModernBERT config type-hint issue." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former's ignore_value handling and missing kwargs in loss calculation are separate training bugs with different code paths." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Unrelated areas: model-specific ignore_value usage versus a tokenizer regex warning regression." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former ignore_value handling is unrelated to a quantization typo in a different component." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Different subsystems and bug types: Mask2Former behavior versus a ModernBERTConfig annotation error." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Missing kwargs in loss computation is not the same as an incorrect config type hint." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A config type-hint bug and a tokenizer regex warning are distinct issues affecting different paths." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERTConfig typing and a typo in orig_conversion.quantization_operation are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "72dd3f4e2809d48ad23ef35083a350e95413d8ad40a0658e58ddd96f64918f47", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated feature requests: one about block decoding and the other about DeepSeek v3.2 support. They do not describe the same underlying bug or change, so this cluster should not be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different requests affecting different areas: block decoding vs model support. No shared code-path, explicit target, or concrete duplicate behavior." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "f8cd2e0d1413e2e4edde95a4a79432b7ed2b2e8c11921d12706e9f32cfb3388e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are related to custom trainer support, but they describe different problems: one is about `remove_unused_column` customizability, the other about FLOPS estimation for custom trainers. I would not merge them as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": "No true canonical issue: the reports point to separate fixes in Trainer behavior, so they should remain distinct.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #43598 is the broader customizability discussion and is the better representative of the cluster theme, if one must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "They share a general Trainer/custom-trainer theme, but the underlying bugs are different: column removal behavior vs FLOPS estimation logic." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "ac7721c472cca869f1db6fc83d974a20f8a39fba28d7bf51c8e9960e043276fd", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are related only by the Qwen ecosystem, but they request different capabilities: one is about registering Qwen3-Omni with AutoModel/AutoModelForConditionalGeneration, while the other asks for AutoModelForSequenceClassification support for Qwen3.5. They are not duplicates of the same underlying bug or change.", + "confidence": 0.96, + "canonical_issue_reason": "issue:43684 is the broader, more central request around model registration and auto-class support, making it the best representative issue in this small cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43684 is the strongest issue to keep as the cluster representative because it targets a core registration gap rather than a narrower task-specific addition.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model variants and different auto-class targets: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs Qwen3.5 sequence-classification support. They do not look like the same underlying fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "fc28462ff87a90654ab3fe0d45e8016496c6df5db65099ad863a74bbfe5f6ed0", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4266, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4266, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three issues share the exact title \"huggingface \" and appear to be duplicates; the \"Fett\" issue is unrelated by title and should remain separate.", + "confidence": 0.78, + "canonical_issue_reason": "Issue #43845 is the earliest of the identical-title \"huggingface \" issues, making it the best representative for the duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #43845 is the cleanest canonical choice because it is earliest and matches the other near-identical issues exactly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles with no shared target or code evidence; not enough to treat as the same issue." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles with no shared target or code evidence; not enough to treat as the same issue." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles with no shared target or code evidence; not enough to treat as the same issue." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same exact title and very close timing strongly suggest the same underlying issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same exact title and same topic strongly indicate a duplicate report." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same exact title and same topic strongly indicate a duplicate report." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: three issues have the exact same title, and #43845 is the earliest among them. The soft-edge decisions are conservative enough given the limited evidence, and the unrelated 'Fett' issue is correctly kept separate." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "188c3a1f9cc64a40eff79ff8f53f947ffeebfa5859770ac13a8bc48440c4b596", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly unrelated low-information spam/issues. The only plausible duplicates are the three exact \"\" reports; the documentation suggestion and \"Google LLC\" post look separate.", + "confidence": 0.77, + "canonical_issue_reason": "issue:44371 is the best representative of the exact \"\" trio: it is one of the identical spam-style reports, appears earliest, and sits at the center of the strongest soft matches.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44371 is the best issue to anchor the cluster because it matches the other two exact spam items and is the earliest of that duplicate-like set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": true, + "reason": "Same exact spam-style issue: identical title pattern and strongest token overlap; likely the same duplicate report." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": true, + "reason": "Same exact spam-style issue as the other \"\" reports; no meaningful distinction is visible." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "Different subject matter: one is spam-like, the other is a documentation enhancement request." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Different titles and apparent intent; \"Check out \\\"Google LLC\\\"\" is a separate promotional/spam-like post, not the same report." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Documentation enhancement and spam placeholder are not the same underlying issue." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Documentation enhancement and spam placeholder are not the same underlying issue." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": true, + "reason": "Both are identical \"\" reports with matching high similarity, so they look like duplicates." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Both may be low-quality posts, but they are not the same concrete issue or report." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Both may be low-quality posts, but they are not the same concrete issue or report." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet: the three \"\" issues are the only clearly duplicate-like items, and the documentation/\"Google LLC\" entries are conservatively treated as separate. The soft-edge accepts/rejects are appropriately cautious given the available evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "6efd60e378117c5052bbd8ed701f0af63c471165fe99f0ac392aaba79fbb3375", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two closed issues look highly similar from metadata alone: identical titles, close body lengths, and a soft-similarity signal. That supports treating them as likely duplicates, but the available evidence is not strong enough to confidently say they are the same underlying issue without body text, targets, or file-level detail.", + "confidence": 0.74, + "canonical_issue_reason": "#45145 is the better canonical anchor because it has the inbound reference, so it appears to be the more linked of the two otherwise similar issues.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue candidate for the cluster because it is the referenced thread and serves as the most visible anchor among the two similar issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "The metadata suggests a likely duplicate, but we do not have the actual body content, targets, or filenames. With only identical titles, similar body sizes, and a soft-similarity signal, the evidence is too thin to accept this edge deterministically." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The duplicate-cluster conclusion is directionally reasonable, but the analyst is a bit too confident for the evidence available. The packet only shows identical titles, similar body lengths, and a soft-similarity signal; it does not expose the actual body content, targets, or filenames, so calling them the same underlying issue is stronger than the metadata alone supports. The canonical choice for #45145 is grounded by its inbound reference, but the soft-edge acceptance should be more conservative given deterministic_accept=false." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45672-2", + "nodes": [ + "issue:45672", + "issue:45674" + ], + "soft_pairs": [ + "issue:45672|issue:45674" + ], + "prepared_review_unit_hash": "51149c8c814def8804a0702c4e49d266c1cafa1343b015421b5a4e293a42c355", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1669, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate 4-bit inference bugs: one in Gemma4 audio modules hitting `torch.finfo()` on `uint8` weights, and another in `BitsAndBytesConfig` where `llm_int8_skip_modules` drops the default `lm_head` exclusion and triggers an `AssertionError`.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #45674 is the more general, configuration-specific regression with a clear failure mode and likely broader user impact.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45674 is the clearest and most actionable representative of the cluster, with a concrete repro path tied to a specific config interaction.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different bugs and code paths: Gemma4 audio-module dtype handling vs. BitsAndBytes skip-module exclusion logic. They both occur in 4-bit inference, but the failure mechanisms are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "c2430bfebdc0033abdd26da99f9057562eeb68dc08c6234293e49755150b6481", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two closed issues appear unrelated; their similarity is only superficial (personal names plus dates), with no shared context or technical content.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Different names and dates, no shared problem description, and no evidence they refer to the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 16, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "2a07fe28106928ab5482f27604446a3b309f13fad86abb40dfc1e559409f7bf1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues are not duplicates; they appear to be unrelated personal-name/date entries with no shared problem statement or actionable issue content.", + "confidence": 0.99, + "canonical_issue_reason": "No clear canonical issue: the titles refer to different people and different dates, with no evidence of the same underlying report.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good global representative of a duplicate cluster because there is no real cluster here; if one must be picked, issue 45764 is only marginally simpler/earlier.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "Reject: these are different named entries with different dates and no indication they describe the same bug or request." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-13", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:45770" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:41855|pull_request:43424", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45770", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:45770", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45655", + "pull_request:43823|pull_request:44827", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:45655|pull_request:45770", + "pull_request:44827|pull_request:45770", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "9326002ff67b9751f2c06facb98e4abe8010b6dc7f8185dc2f78a5cc6d62875b", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 22, + "serialized_chars": 36419, + "estimated_input_tokens": 9105, + "estimated_eval_tokens": 18466 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 22, + "serialized_chars": 36419, + "estimated_input_tokens": 9105, + "estimated_eval_tokens": 18466 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Only one soft edge looks like a true duplicate: the two `fixed_cross_entropy` PRs both implement the same kwargs/label_smoothing/weight pass-through on the same function and target the same issue. The rest are unrelated model additions, refactors, or test/documentation changes in different code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43251 is the better canonical representative: it has the explicit issue link, broader/clearer wording of the same `cross_entropy` fix, and the same code path as #43254.", + "best_issue_reason": null, + "best_pr_reason": "PR #43251 is the best global representative because it is the clearest, issue-linked version of the shared `fixed_cross_entropy` fix; the only other true duplicate (#43254) is a near-identical variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Unrelated PRs: VideoPrism model addition vs ExecuTorch dynamic-shape test coverage." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Different changes: Mistral tokenizer method additions vs adding a new MobileLLM model." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API fix vs ExecuTorch export test; no shared underlying bug." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor robustness refactor is unrelated to MobileLLM model implementation." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "`fixed_cross_entropy` kwargs bugfix is unrelated to adding MobileLLM." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Different code paths: loss utility fix vs Mistral4 test/integration changes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch dynamic-shape test and Mistral4 test fixes are not the same underlying change." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "ExecuTorch export test vs MobileLLM model addition; no duplicate bug/change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45770", + "accept": false, + "reason": "New MobileLLM model vs AutoModel `text_config` unwrap logic; different functionality." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "MobileLLM model addition is unrelated to `cls.config` resolution order fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "New model implementation vs Falcon output-collection refactor; distinct changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:44827", + "accept": false, + "reason": "MobileLLM model addition and Mistral4 test fix do not address the same bug." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45770", + "accept": false, + "reason": "Falcon refactor and AutoModel `text_config` unwrap are different code paths." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon model refactor is unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output interface refactor vs Mistral4 test fix; no shared concrete fix." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test/integration work is unrelated to the `layrnorm` spelling correction across CLIP-like models." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test fixes and `cls.config` resolution order are separate issues." + }, + { + "left": "pull_request:43823", + "right": "pull_request:44827", + "accept": false, + "reason": "MobileLLM model addition and Mistral4 test fix are different changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 test fixes are unrelated to the model-creation skill/meta PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "New model implementation vs meta skill/doc PR; not the same underlying change." + }, + { + "left": "pull_request:45655", + "right": "pull_request:45770", + "accept": false, + "reason": "Both touch config handling, but one fixes `cls.config` resolution order while the other unwraps `text_config`; not the same concrete bug." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45770", + "accept": false, + "reason": "Mistral4 test fixes are unrelated to AutoModel `text_config` unwrapping." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs fix the same `fixed_cross_entropy` API gap in `src/transformers/loss/loss_utils.py` by passing supported kwargs (`weight`, `label_smoothing`) through to `nn.functional.cross_entropy`." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analyst output is well grounded in the packet and stays conservative on the soft edges. The only accepted duplicate pair, PR #43251 and #43254, is supported by the shared file, same function, and shared issue target 43240. The other verdicts are consistently limited to unrelated model additions, refactors, or tests, with no overstatement of duplicate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40546-2", + "nodes": [ + "pull_request:40546", + "pull_request:42781" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781" + ], + "prepared_review_unit_hash": "745c6dc5e0c79b23001ad329081e4a080b55a68f260b4138da889ead134beb79", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7226, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7226, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two VibeVoice PRs overlap on the base model/docs/auto-registration scaffolding, but they target different deliverables: a full VibeVoice implementation vs. a later VibeVoice Realtime extension. They are related, not duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 40546 is the broader foundational VibeVoice implementation and is the better representative of the base feature work. PR 42781 is a separate realtime follow-up with additional tokenizer/generation changes, not the same change set.", + "best_issue_reason": null, + "best_pr_reason": "PR 40546 is the stronger cluster representative because it is the original, more complete implementation and is not marked draft. PR 42781 appears to be a distinct extension rather than a duplicate of the base VibeVoice PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Both touch VibeVoice infrastructure, but 42781 adds realtime-specific components and extra generation/tokenizer work; it is a follow-up feature, not the same concrete fix/change as 40546." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40755-2", + "nodes": [ + "pull_request:40755", + "pull_request:41224" + ], + "soft_pairs": [ + "pull_request:40755|pull_request:41224" + ], + "prepared_review_unit_hash": "71de2fd1b4c153e5fc1784e73f43a94f41e6a55f77db4c96906f17dc3915fb61", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two unrelated pull requests: one adds TimesFM covariate forecasting support, the other adds DINOv3 image-classification support. They share only a broad \u201cmodel feature addition\u201d similarity, not the same code path or fix.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Reject: they modify different models, different files, and different functionality. TimesFM covariate forecasting and DINOv3 classification support are separate feature additions, not the same underlying change or bug fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-2", + "nodes": [ + "pull_request:41797", + "pull_request:45186" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186" + ], + "prepared_review_unit_hash": "aa039cd1adc9376a7cb012028955f19db45c1e3361eeb05bd6d5a40a65b87cc8", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6722, + "estimated_input_tokens": 1681, + "estimated_eval_tokens": 3618 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6722, + "estimated_input_tokens": 1681, + "estimated_eval_tokens": 3618 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one PR adds DeepSeek OCR, the other adds Isaac. They share framework scaffolding for new model integrations, but the actual model code, docs, tests, and behavior are for different underlying models and code paths.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the two pull requests implement different model additions (DeepSeek OCR vs Isaac), not the same fix/change.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a global best duplicate candidate because they are unrelated model-integration PRs rather than alternate solutions to the same problem.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Shared boilerplate for model registration/docs is incidental; the PRs add different models with different configs, processors, modeling code, and tests, so they do not fix the same underlying bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42975-2", + "nodes": [ + "pull_request:42975", + "pull_request:42976" + ], + "soft_pairs": [ + "pull_request:42975|pull_request:42976" + ], + "prepared_review_unit_hash": "1b52a3839903aacf2d143dbf9bc7cc626d09c592886d9dc7a23c7e49cace8e78", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related only at a broad maintenance level: both update GitHub Actions versions, but they target different action families and different upgrade goals. They should not be deduplicated.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42975 is the broader and more specific workflow-maintenance change: it explicitly targets Node 24 compatibility and updates many GitHub Actions usages across workflows.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the best representative of the cluster because it covers the main GitHub Actions compatibility upgrade theme more comprehensively than PR 42976, which is a separate action-version bump focused on docker/build-push-action and a few related workflows.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Both PRs update workflow action versions, but they change different actions and solve different upgrade needs. PR 42975 is about Node 24 compatibility for multiple actions; PR 42976 is about bumping docker/build-push-action and similar workflow dependencies. They are not the same concrete fix and would not plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-5", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:45490", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:42978|pull_request:43448", + "pull_request:42978|pull_request:43451", + "pull_request:42978|pull_request:45490", + "pull_request:43448|pull_request:43451", + "pull_request:43448|pull_request:45490", + "pull_request:43451|pull_request:45490", + "pull_request:45490|pull_request:45630" + ], + "prepared_review_unit_hash": "82bc1568491a1571e6796e975027e0581ccf49ebd7fc949a99843cca377e319b", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 7, + "serialized_chars": 17617, + "estimated_input_tokens": 4405, + "estimated_eval_tokens": 9066 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 7, + "serialized_chars": 17617, + "estimated_input_tokens": 4405, + "estimated_eval_tokens": 9066 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All five items are separate model-addition pull requests for different models (ViT NEPA, Molmo, Molmo2, CTSM, Kimi2_6). They share only boilerplate integration files and docs patterns, not the same underlying change or code path.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "If one PR must represent the cluster, 43451 (Molmo2) is the most complete standalone integration, with the broadest implementation surface (modeling, processing, docs, tests, and auto-mapping updates).", + "best_issue_reason": null, + "best_pr_reason": "43451 is the strongest representative for triage because it is the most substantive single integration; the others are distinct model ports and should not be collapsed into it.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different models and different change goals: ViT NEPA vs Molmo. Shared auto/docs wiring is boilerplate, not the same bug or feature." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model integrations (ViT NEPA vs Molmo2). They touch some of the same framework files, but the concrete code paths and artifacts are unrelated." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA and CTSM are distinct model additions with no evidence of a shared underlying fix or mergeable single change." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are separate model ports. Similar filenames only reflect shared registration/docs scaffolding, not duplicate work." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM are unrelated integrations; they do not fix the same concrete problem or overlap beyond generic framework registration." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are different model additions with distinct implementations and tests, so they should not be merged as duplicates." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45630", + "accept": false, + "reason": "CTSM and Kimi2_6 are separate model additions; shared auto/modeling file edits are broad subsystem overlap, not the same code-path change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-5", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815", + "pull_request:45747", + "pull_request:45749" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815", + "pull_request:43665|pull_request:45747", + "pull_request:43665|pull_request:45749", + "pull_request:44815|pull_request:45747" + ], + "prepared_review_unit_hash": "94fc491d0cc10075d0bbae640e0eb4346224bae0e8255efe481e77302e21284b", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 6, + "serialized_chars": 10367, + "estimated_input_tokens": 2592, + "estimated_eval_tokens": 5440 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 6, + "serialized_chars": 10367, + "estimated_input_tokens": 2592, + "estimated_eval_tokens": 5440 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates: they span unrelated areas (Whisper decoding/tests, CLIP/ViT test edits, FP8 dequant/model-loading, continuous batching docs, and an unrelated split-batch-size fix). The only substantive code change is the FP8/dequant PR; the others look like test-only or cosmetic changes, or lack enough evidence to connect them to the same bug/change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the strongest representative because it makes the only clearly substantive production-code changes across multiple source files and includes a real bug-fix theme (FP8/dequant/model loading), unlike the others which are test-only, cosmetic, or too underspecified.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the best standalone PR in the set: it has concrete code-path changes, touches relevant runtime files, and appears to address an actual functional issue rather than test noise or a spelling/doc cleanup.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Both are labeled as fixes, but they target different models and different kinds of changes: Whisper tokenizer/runtime behavior versus CLIP/ViT test edits. No shared code path or same underlying bug is evident." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decoding/tokenization changes are unrelated to FP8 dequant/model-loading fixes. Different subsystems, different failure modes." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "This is test-only CLIP/ViT churn versus a concrete FP8/runtime bug fix. They do not look like the same underlying change and would not plausibly merge as one PR." + }, + { + "left": "pull_request:43665", + "right": "pull_request:45747", + "accept": false, + "reason": "The CLIP/ViT test edits are unrelated to a split-batch-size fix; no shared code path or concrete bug is visible." + }, + { + "left": "pull_request:43665", + "right": "pull_request:45749", + "accept": false, + "reason": "Test-file edits in vision models and a docstring spelling correction in continuous batching are clearly separate cosmetic changes." + }, + { + "left": "pull_request:44815", + "right": "pull_request:45747", + "accept": false, + "reason": "FP8 dequant/model-loading work is unrelated to an unspecified split-batch-size PR; there is not enough evidence of the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 9, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "237bb86038e7c63be626a66b75af36fe9c836a44964ecd16a4db74503714532b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4562, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4562, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two open PRs are not duplicates: one is a setup/version-bump + test dependency change, while the other is a workflow/testing-utils change around CI/comment handling. They only overlap on a shared Vit test file, which is not enough to indicate the same underlying fix.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43532 is the broader and more representative change in this pair, but it is not a duplicate of #43488; the two PRs address different code paths and should not be merged into one canonical change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43532 is the better standalone representative of the cluster because it contains the more substantial multi-file behavior change, whereas #43488 looks like a narrow bot/version-format check.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Reject: the diffs touch different concerns. #43488 updates setup/versioning and test dependencies, while #43532 rewires GitHub workflows and testing utilities. A shared test filename alone does not mean they fix the same concrete bug or should be merged together." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43612-2", + "nodes": [ + "pull_request:43612", + "pull_request:43613" + ], + "soft_pairs": [ + "pull_request:43612|pull_request:43613" + ], + "prepared_review_unit_hash": "9eb3f17e054b4dc20d017e73b3ab71edafbb818b76396ba5a1f9d957eec25c1f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate PRs add adjacent but distinct pipeline features: one for Promptable Concept Segmentation and one for Promptable Visual Segmentation. They share scaffolding and docs plumbing, but they target different tasks and model integrations, so they should not be deduplicated.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: these are parallel feature additions for different segmentation tasks, not the same underlying change.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a true duplicate of the other. If forced to pick a representative, PR #43613 is slightly broader in model/test coverage, but it still represents a different feature than PR #43612.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Both add segmentation-related pipelines and share some docs/metadata files, but they implement different concrete features with different pipeline names, model backends, and test suites. They are related, not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43651-2", + "nodes": [ + "pull_request:43651", + "pull_request:43663" + ], + "soft_pairs": [ + "pull_request:43651|pull_request:43663" + ], + "prepared_review_unit_hash": "67fee8ffee0ab63772978e41931e57141d029424ac932c4f6dd74874efe22a6e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two open PRs both touch trainer.py and add extension hooks, but they address different behaviors: gradient-accumulation loss scaling vs. signature-column filtering. They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: 43651 adds a GA-loss-scaling hook, while 43663 adds a signature-column override hook; they solve separate trainer extensibility problems.", + "best_issue_reason": null, + "best_pr_reason": "If a representative is needed, 43651 is slightly more central because it changes the core training-step loss-scaling path, but it is still not a substitute for 43663.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different underlying changes and code paths: 43651 controls loss normalization during gradient accumulation, while 43663 exposes signature-column filtering for model inputs. They are related only by file/subsystem, not by the same bug or fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-3", + "nodes": [ + "pull_request:43656", + "pull_request:43836", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842", + "pull_request:43836|pull_request:43842" + ], + "prepared_review_unit_hash": "27686481e71678a329faa06c384b48a860f2015dc3f059bcc1987fa7c8a071be", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three PRs target the same CLI serve.py TypeAdapter annotation NameError class of bug; 43842 is the most focused fix, while 43656 is a similar variant and 43836 appears to include the same fix alongside broader cleanup/refactor work.", + "confidence": 0.81, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the clearest, most narrowly scoped fix for the concrete TypeAdapter NameError when pydantic is absent; it directly addresses the runtime annotation problem in serve.py with minimal unrelated churn.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 best represents the cluster because it fixes the exact NameError path with the smallest, most explicit change set and is easiest to reason about as the canonical duplicate target.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": true, + "reason": "Both PRs fix the same runtime TypeAdapter annotation NameError in src/transformers/cli/serve.py; the edits are different implementations of the same underlying bug and could plausibly be merged into one fix." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "Despite 43836 showing broader file churn, its title and touched file indicate the same TypeAdapter string-literal/annotation NameError fix in the same code path, so it is close enough to treat as the same underlying change." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is adequately grounded in the packet: all three PRs touch the same file and are tied by titles/diffs to TypeAdapter/annotation NameError fixes in `serve.py`, with 43836 clearly broader than 43842. The soft-edge accepts are conservative enough, especially since 43836 and 43842 share an issue target and 43656 is at least plausibly the same annotation-related bugfix family." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44024", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44071", + "pull_request:44066|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44059|pull_request:44068", + "pull_request:44056|pull_request:44101", + "pull_request:44018|pull_request:44059", + "pull_request:44073|pull_request:44161", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44010|pull_request:44073", + "pull_request:44018|pull_request:44129", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:44071|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154", + "pull_request:44024|pull_request:44076" + ], + "prepared_review_unit_hash": "f3eb77e844e532f8eef743d71efd201a378d2630cb18b6cfdc66cda45021a458", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84498, + "estimated_input_tokens": 21125, + "estimated_eval_tokens": 42506 + }, + "budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 72, + "serialized_chars": 76931, + "estimated_input_tokens": 19233, + "estimated_eval_tokens": 38722 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The packet contains two separate duplicate subclusters, not one: a GPT-J/CodeGen family centered on 44722, and a distinct GPT-Neo pair around 44018/44068. Most other PRs are model-specific output-tracing refactors and should stay separate.", + "confidence": 0.82, + "canonical_issue_reason": null, + "canonical_pr_reason": "44722 is the best canonical PR for the GPT-J/CodeGen subcluster because it spans both model files, explicitly targets the tracking issue, and is the broadest overlapping implementation. The GPT-Neo duplicates form a separate family and should not be folded into this canonical choice.", + "best_issue_reason": null, + "best_pr_reason": "44722 is the strongest single PR in the packet, but only for the GPT-J/CodeGen family; 44068 is the better representative for the separate GPT-Neo family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families and code paths; same output-tracing theme is too broad." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different backbones and implementations; not the same concrete change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same code path and could plausibly be merged into one PR." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet/ResNet-style tracing work vs EfficientNet are unrelated model paths." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen and EfficientNet are different code paths." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa are unrelated models." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are unrelated model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Same GPT-Neo output-tracing refactor on the same file; these look like duplicate/superset variants." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are different models; shared decorator migration is not enough." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are separate model families." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are different concrete code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated changes." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are unrelated models." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are unrelated implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are unrelated models." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT are unrelated code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are unrelated models." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo is a separate duplicate family from GPT-J/CodeGen." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are unrelated models." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo and GPT-J are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated models." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44085", + "accept": false, + "reason": "MPT and GPT-J are unrelated." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR are unrelated." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are unrelated model paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are unrelated." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are unrelated models." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are unrelated implementations." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "SegFormer and LongT5 are unrelated models." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert and Flaubert/XLM are different code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 and MPT are unrelated models." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are unrelated." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBert and LongT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and SegFormer are different backbones." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet and MPNet are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are unrelated model implementations." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are unrelated." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated model code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44071", + "accept": false, + "reason": "RegNet and MPT are unrelated." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are unrelated." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT and VisualBert are unrelated." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are unrelated." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are unrelated." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44129", + "accept": false, + "reason": "RegNet and SpeechT5 are unrelated." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBERT and GPT-Neo are unrelated." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are unrelated." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are unrelated." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and SegFormer are different backbones." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBERT and DeBERTa are unrelated models." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa and TextNet are unrelated." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet and ImageGPT are unrelated model implementations." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The pair-level verdicts are mostly conservative, but the cluster summary overstates the evidence. The packet supports two separate duplicate subclusters: GPT-J/CodeGen (44066, 44085, 44722) and GPT-Neo (44018, 44068). Saying there is \u201conly real duplicate family\u201d and collapsing GPT-J/GPT-Neo into one family is not grounded. 44722 is a plausible canonical PR for the GPT-J/CodeGen subcluster, but the overall summary should acknowledge the second GPT-Neo duplicate pair as well." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 26, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44129" + ], + "soft_pairs": [ + "pull_request:44073|pull_request:44074", + "pull_request:44056|pull_request:44073", + "pull_request:44056|pull_request:44074", + "pull_request:43997|pull_request:44010", + "pull_request:44010|pull_request:44129" + ], + "prepared_review_unit_hash": "6a2ba859ba3645c59dd92b1424f0673e181fb14fc8ce0774852f9dfad307c8a8", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84498, + "estimated_input_tokens": 21125, + "estimated_eval_tokens": 42506 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 5, + "serialized_chars": 13067, + "estimated_input_tokens": 3267, + "estimated_eval_tokens": 6790 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All items are model-specific PRs that migrate different architectures to the same output-tracing/capture pattern, but they are not duplicates of one another; they touch different code paths and would not be merged into a single PR.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the strongest representative because it has an explicit issue target and a clearly scoped refactor to standardized output capture.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 best captures the cluster theme while remaining a concrete, self-contained change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Same refactor pattern, but different models and files; these are separate model-specific changes, not one concrete bug fix." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "Both standardize output tracing, but MPNet and VisualBert have distinct implementations and code paths; too broad to merge as duplicates." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "Shared helper migration theme only; the PRs modify different model internals and are not the same underlying change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model implementations; similar decorator/capture refactors do not make them duplicates." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "Different architectures and different forward paths; the overlap is only in output-tracing cleanup, not the same fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44028", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "5d987a5a3454e225355b4972891993c9df239f47f625858a8e17c6f269882b55", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40176, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40176, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are thematically similar output-tracing refactors, but they target different model implementations and code paths, so they are not duplicates of one another. No issue artifacts are present.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "44025 is the best representative PR in this set: it applies the output-tracing refactor to a model plus its prompt variant, which captures the cluster\u2019s core pattern without being the same change as the other model-specific PRs.", + "best_issue_reason": null, + "best_pr_reason": "44025 is the most suitable cluster representative for triage because it shows the common refactor pattern cleanly and spans a related pair of files, but it still is not a duplicate of the other PRs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Same refactor theme, but different model code paths (`timm_backbone` vs `upernet`); not the same underlying change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Both are output-tracing refactors, but they affect unrelated models and forward paths." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different architectures (`timm_backbone` vs `univnet`) and different forward logic; only the pattern matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "`timm_backbone` and `falcon_mamba/mamba` are separate implementations with different output handling, so this is not one duplicate fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Both touch tracing-like behavior, but they are distinct model families and code paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "`mobilenet_v1` and `univnet` are unrelated models; shared refactor wording is not enough to merge them." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model subsystems and different forward signatures; not the same bug/change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Both are refactors around output tracing, but they target different model code paths and cannot plausibly be one PR." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "`mobilenet_v1` vs `vision_encoder_decoder` are unrelated implementations; no shared concrete fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Same general refactor pattern, but distinct encoder-decoder wrapper code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "`vision_text_dual_encoder` and `univnet` do not share the same underlying output-tracing bug." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models and different forward implementations; only the refactor theme is shared." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "`vision_text_dual_encoder` and `falcon_mamba/mamba` are separate code paths, so they are not duplicates." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "`vision_text_dual_encoder` and `codegen` change different model logic; same broad subsystem does not imply same change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Both are output-tracing refactors, but they are for different models and different runtime behavior." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "`univnet` and `upernet` are unrelated model families with distinct output semantics." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different architectures and different forward/capture behavior; not mergeable as one fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "`univnet` and `codegen` touch different code paths and different output shapes." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Same theme, but the actual change is model-specific and not the same underlying bug." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "`upernet` segmentation forward logic and `codegen` causal LM tracing are different concrete changes." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "`upernet` and `rwkv` do not share the same code path or fix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model internals; the overlap is only in the refactor pattern." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "`falcon_mamba/mamba` and `superpoint` are unrelated implementations and cannot be merged as one PR." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "`falcon_mamba/mamba` and `codegen` change different model code paths and output conventions." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "`timm_backbone` and `codegen` are separate model implementations; not the same underlying fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "`depth_anything` and `vision_encoder_decoder` share a refactor motif, but they are different model wrappers and different forward code." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "`depth_anything` and `speech_encoder_decoder` are distinct code paths; no single duplicate PR here." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Different models and different output-tracing implementations; not the same bug/change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "`depth_anything` and `rwkv` modify unrelated forward logic." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "`depth_anything` and `dpr` are different model families; only the refactor style is similar." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "`vision_encoder_decoder` and `rwkv` are unrelated code paths and not a duplicate fix." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Both are encoder-decoder wrappers, but they are different model families and separate changes." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "`vision_encoder_decoder` and `superpoint` do not share the same underlying code change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model implementations and different output semantics; not mergeable as one PR." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated models; same broad tracing theme is insufficient." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different architectures and different forward paths; not a duplicate." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "`speech_encoder_decoder` and `dpr` change different model code and output handling." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "`superpoint` and `rwkv` are unrelated model implementations with no shared concrete bug." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different models and different output logic; only the refactor pattern matches." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "`rwkv` and `dpr` are distinct code paths with no evidence of the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44662-3", + "nodes": [ + "pull_request:44662", + "pull_request:45075", + "pull_request:45401" + ], + "soft_pairs": [ + "pull_request:44662|pull_request:45401", + "pull_request:44662|pull_request:45075", + "pull_request:45075|pull_request:45401" + ], + "prepared_review_unit_hash": "dc9d3f85e75d98aa8c3e8a257b74d02c72e8deca7bb00a537be74a82e15a48f7", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three items are separate model-addition PRs for different models (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share Transformers boilerplate and auto-registration files, but they do not describe the same code-path bug or the same feature change, so none are duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is a true duplicate-canonical candidate because each adds a different model. If one representative must be chosen for the cluster, PR #45075 is the best anchor since it is the most complete/established model-addition PR and also links an explicit issue target.", + "best_issue_reason": null, + "best_pr_reason": "PR #45075 is the most representative of the cluster only in the sense that it has the clearest scope and explicit issue linkage; however, it is still not a duplicate of the others because the model, files, and implementation are distinct.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "PenguinVL implementation vs Voxtral TTS support are unrelated model additions. Shared docs/auto-registry files are expected boilerplate, not evidence of the same underlying change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "Both are model implementation PRs, but for different models with different configs, processors, and tests. They do not fix or add the same concrete code path." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model integrations. Overlap in shared registration and documentation files is too broad to treat them as the same PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44979-2", + "nodes": [ + "pull_request:44979", + "pull_request:45363" + ], + "soft_pairs": [ + "pull_request:44979|pull_request:45363" + ], + "prepared_review_unit_hash": "78d8311b9302eff1d60754b0ae5793baaa0313470dc9281a558135942402c868", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Related but distinct PRs: one adds a generic module-fusion API, while the other implements KernelConfig-driven n-to-1 kernel fusion plus integration plumbing and an example. They overlap conceptually, but they are not the same underlying change.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "45363 is the clearer representative of the set because it delivers the concrete KernelConfig-based fusion workflow and integration points, whereas 44979 is broader foundational API scaffolding.", + "best_issue_reason": null, + "best_pr_reason": "45363 is the most end-user-facing and concrete PR here: it wires fusion through model loading, integration helpers, and a working example, so it best summarizes the cluster theme.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Reject: 44979 introduces a generic module-fusion API, while 45363 adds a specific n-to-1 kernel-fusion implementation via KernelConfig and related integration code. Similar area, but not the same concrete change and not plausibly one merged PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45086-2", + "nodes": [ + "pull_request:45086", + "pull_request:45317" + ], + "soft_pairs": [ + "pull_request:45086|pull_request:45317" + ], + "prepared_review_unit_hash": "e3005195c7cb66424c7400ec40f5a0b8b77ef2a654964c71948c34c7f431d8ce", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4413, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4413, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests fix the same _patch_mistral_regex AttributeError in the Mistral tokenizer patch path and target the same issue; 45317 is the more complete variant with tests.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45317 is the better canonical representative because it contains the same core fix as 45086 plus a test update and a clearer, more specific title.", + "best_issue_reason": null, + "best_pr_reason": "PR 45317 is the strongest overall representative of the cluster: same bug fix, same file, and it includes validation coverage.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same concrete AttributeError fix in _patch_mistral_regex on the same code path; 45317 is essentially the tested refinement of 45086, so these look mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "16032a8c74bdf26305b4cbf8ec8470130c8855d0e81db4387316ee16bd694695", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests are about NemotronH model refactoring, but they target different concrete changes: one is a conversion/mapping and inheritance cleanup, the other introduces separate dense/sparse model implementations and docs updates. They are related, but not the same underlying change set.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the broader, more complete NemotronH restructuring: it adds the dedicated dense/sparse model split plus auto-mapping, docs, and tests, while 45115 is a narrower conversion/inheritance refactor.", + "best_issue_reason": null, + "best_pr_reason": "PR 45569 is the best overall PR candidate for this cluster because it represents the main user-facing architecture change and subsumes more of the NemotronH work than the narrower mapping-focused PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Related NemotronH work, but not the same concrete bug/change: 45115 focuses on checkpoint conversion and class renaming/inheritance, while 45569 splits NemotronH into dense/sparse variants with docs/tests. They would not naturally merge into one PR as a single fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 20, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45332-2", + "nodes": [ + "pull_request:45332", + "pull_request:45333" + ], + "soft_pairs": [ + "pull_request:45332|pull_request:45333" + ], + "prepared_review_unit_hash": "12a2dcf035a6dbaa361e70043a7ef3db7560976af018ae0cb944407ac9bdaa08", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are closely related feature PRs for heterogeneous model support, but they are not duplicates: 45333 adds per-layer config plumbing, while 45332 adds the downstream modeling/cache/masking changes that consume that plumbing.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "45332 is the broader representative PR because it covers the end-to-end heterogeneous modeling path, not just config scaffolding.", + "best_issue_reason": null, + "best_pr_reason": "45332 is the best overall PR to represent the cluster since it includes the more complete change set; 45333 is narrower groundwork for the same feature area.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related but not the same concrete change: 45333 adds heterogeneous config support, while 45332 adds modeling/cache handling that depends on that config. They are complementary, not duplicate fixes, and would not naturally collapse into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45415-2", + "nodes": [ + "pull_request:45415", + "pull_request:45425" + ], + "soft_pairs": [ + "pull_request:45415|pull_request:45425" + ], + "prepared_review_unit_hash": "4fee7047114a985ccf633afd33d0422cc5ee0319096c46a692b227271d747ffc", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related typing-focused PRs, but they are not duplicates: one is a broad repo-wide type-checking cleanup, while the other adds/adjusts typing protocols and helpers in specific code paths.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45415 is the broader, more representative typing cleanup across many `src/transformers/*` files and the type-checking config, so it fits best as the cluster\u2019s canonical PR.", + "best_issue_reason": null, + "best_pr_reason": "PR 45415 is the strongest overall representative because it covers the widest scope of the typing work and is closer to the cluster\u2019s apparent theme than the narrower helper-type refactor in PR 45425.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Both are typing-related, but they address different changes: 45415 is a broad type-checking sweep, while 45425 introduces specific typing protocol/helper definitions. They do not look like the same concrete bug or change and would not plausibly merge as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-2", + "nodes": [ + "pull_request:45487", + "pull_request:45615" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45615" + ], + "prepared_review_unit_hash": "e0368674c8d01752fcef3010dab830c751cb9885c1eb9648addb11c5d4cf9fcc", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5159, + "estimated_input_tokens": 1290, + "estimated_eval_tokens": 2836 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5159, + "estimated_input_tokens": 1290, + "estimated_eval_tokens": 2836 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two pull requests: one fixes a real model-parallel device placement bug in AltCLIP/ChineseCLIP-related model code; the other only adds XPU test expectations for Qianfan OCR. They are not the same underlying change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45487 is the stronger canonical PR because it contains the substantive code fix across model implementations, not just test-data updates.", + "best_issue_reason": null, + "best_pr_reason": "PR 45487 is the best representative of the cluster since it addresses the actual bug in model forward logic and has broader functional impact than the test-only PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45615", + "accept": false, + "reason": "Different subsystems and different change types: 45487 fixes device placement in AltCLIP/ChineseCLIP model code, while 45615 only adds XPU expectations to Qianfan OCR tests. They do not appear mergeable into one PR or to address the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "d980997f34a5a13858a7d7bcb1e998c652b53d4e79a484adda636ef444c61fbe", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both items are expert-parallelism loading fixes, but they address different failure modes: one removes `distributed_config` from serialization and adds `has_ep` for DeepSpeed ZeRO-3/accelerate loading, while the other prevents expert parameters from being overwritten during FSDP2 loading by post-shard wrapping. The shared `modeling_utils.py` touch is superficial, not evidence of the same bug.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: these are distinct EP-loading bugs with different code paths and fixes, so neither PR is a duplicate of the other.", + "best_issue_reason": null, + "best_pr_reason": "PR 45662 is the stronger representative of an EP-loading bug because it fixes a concrete parameter materialization issue in the loader path, but it still does not subsume 45548.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Different underlying problems: 45548 is about config serialization and EP detection for ZeRO-3/accelerate, while 45662 is about FSDP2 load-time overwriting of experts and shard wrapping. They are related but not the same fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "d03f85e9194c61794d0f0bd1f6cd16c7f1b2537c16740dd04f65fcebfb20afaa", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4589, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4589, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same xdist-related captured_info collision problem, with 45645 effectively extending the core fix from 45639 into CI log collection and related cleanup.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "45645 is the more complete representative: it includes the xdist-safe output-file change plus the CI workflow update to collect multiple captured_info artifacts.", + "best_issue_reason": null, + "best_pr_reason": "45645 is the best standalone representative because it covers the underlying bug fix and the downstream CI handling needed to preserve those logs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Both PRs fix the same concrete captured_info/xdist collision path in testing_utils, and 45645 appears to build on the same fix rather than introduce a separate change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 25, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45683-2", + "nodes": [ + "pull_request:45683", + "pull_request:45734" + ], + "soft_pairs": [ + "pull_request:45683|pull_request:45734" + ], + "prepared_review_unit_hash": "5bf556c48e00ed86e4c03ceb7e01f11cf4b18f29c45b12a017e905cb44e456f3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3891, + "estimated_input_tokens": 973, + "estimated_eval_tokens": 2202 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3891, + "estimated_input_tokens": 973, + "estimated_eval_tokens": 2202 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates: 45683 adds audio-module skips for multimodal quantization crashes, while 45734 fixes skip_modules semantics so auto-detected defaults remain skipped and adds tests.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "45734 is the stronger standalone fix: it patches the skip_modules regression, includes tests, and has the explicit issue link; 45683 addresses a different audio-specific crash.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45683", + "right": "pull_request:45734", + "accept": false, + "reason": "Shared file and issue target are incidental; 45683 skips audio_tower/embed_audio to avoid a uint8 crash, whereas 45734 changes the skip_modules/default-skip control flow to keep lm_head and tied embeddings excluded and prevent a bitsandbytes AssertionError. Different bugs and not mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 26, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/manifest.json b/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..24357bc224fa80cf89ea32fb736cd0363c0b5ce7 --- /dev/null +++ b/snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260505t000047z", + "artifacts": { + "hybrid": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-05T00:04:58Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260505T000047Z", + "variant": "hybrid" +} diff --git a/snapshots/20260505T000047Z/manifest.json b/snapshots/20260505T000047Z/manifest.json index cc2349363cfa184b511fde7555e4dcd6e71072ee..f373e5076bcd4e32107137911607fd16c6373bf5 100644 --- a/snapshots/20260505T000047Z/manifest.json +++ b/snapshots/20260505T000047Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 473 }, "extracted_at": "2026-05-05T00:00:47Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260505t000047z", + "runs": { + "hybrid-model-20260505t000047z": { + "analysis_id": "hybrid-model-20260505t000047z", + "artifacts": { + "hybrid": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260505T000047Z/analysis-runs/hybrid-model-20260505t000047z/manifest.json", + "model": null, + "published_at": "2026-05-05T00:04:58Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260505T000047Z", "watermark": {