Datasets:
schema_version stringclasses 1
value | example_id stringlengths 64 64 | role stringclasses 2
values | variant stringclasses 1
value | split stringclasses 1
value | reviewer_id stringlengths 29 29 | target_id stringlengths 29 29 | trajectory_id stringlengths 64 64 | turn_index int64 1 20 | criterion_index int64 0 19 ⌀ | candidate_index int64 0 39 ⌀ | loss_mask_type stringclasses 1
value | messages listlengths 2 80 | metadata_json stringlengths 311 435 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
amazon-c11-adaptive-oracle-sft-row-v1 | 25f888ed024a821b8741ff492ba56db70cbb44326ed85fa0d22b7da8b06e93a2 | criterion_judge | non-diverse | train | amzd_0b838abd2ad0e1e6f46283a7 | amzt_9806656e37134ba3ba702941 | f4e4375924568226b6c231bf4047bbf4ecc896b10615183abd79efd2e12b4ad0 | 16 | 0 | 13 | qwen3_final_response | [
{
"role": "user",
"content": "Judge Amazon product reviews against exactly one weighted criterion for what this reviewer\nwould likely write about this product. Do not use any criterion not shown below and do not\nreward general review quality.\n\nProduct context:\n<|The Start of Context|>\n# Automatic Watc... | {"collection_fingerprint":"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52","history_reset":false,"lane_cache_key":"12de2b3b2bb9a629e4b330c593f2bd1002f06cf3a3b0b43dccb8f27febc3281c","oracle_turn":16,"rubric_sha256":"0ee3f01add60497e4c9174951e7ba94feb46d26c10e4996b7191dab666394afb","seed":267033248} |
amazon-c11-adaptive-oracle-sft-row-v1 | cdcd3b65e17cb5797a5baa4fb380cd19dbf0d44f4ef3b879537bd8078a4c12d7 | criterion_judge | non-diverse | train | amzd_76c64dddd4467a4b2ec1297b | amzt_7073f13107177b8b9d82e58a | 5222f3853f1055c67a396cfd6da982d077628e7b9171510911fcc95061a3bf88 | 11 | 8 | 15 | qwen3_final_response | [
{
"role": "user",
"content": "Judge Amazon product reviews against exactly one weighted criterion for what this reviewer\nwould likely write about this product. Do not use any criterion not shown below and do not\nreward general review quality.\n\nProduct context:\n<|The Start of Context|>\n# Pet Carrier: H... | {"collection_fingerprint":"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52","history_reset":false,"lane_cache_key":"dfb9896173b1427918fc79aba69518a0d6021cd0c52b2564ac2fd9357a669b2e","oracle_turn":11,"rubric_sha256":"c81a988feeeb5bce3aee0e55c7884623fdf008a8b335ea17540c354b942b68ec","seed":2123914081} |
amazon-c11-adaptive-oracle-sft-row-v1 | 014770cca55ab2f4ad21025940d24648432f42a7d04c8a62f650f1e52b94c47f | criterion_judge | non-diverse | train | amzd_fb8f48fd2f3f68302abef5ec | amzt_6d023f3a403cf146dcc90d61 | a26a781d13b9157f770ca0e2510512d438d650857ff4e7978ed385596659896e | 4 | 1 | 14 | qwen3_final_response | [
{
"role": "user",
"content": "Judge Amazon product reviews against exactly one weighted criterion for what this reviewer\nwould likely write about this product. Do not use any criterion not shown below and do not\nreward general review quality.\n\nProduct context:\n<|The Start of Context|>\n# Yunzhenbusines... | {"collection_fingerprint":"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52","history_reset":false,"lane_cache_key":"efe8514d23f116c80ca325f137de93219a2505147734a0f0668aa35ef6191809","oracle_turn":4,"rubric_sha256":"d332c8c47f45af7eb95a13779f9bcda2bdf12b1f5205a3e7f3e3de1f29be67b0","seed":510219251} |
amazon-c11-adaptive-oracle-sft-row-v1 | 136575653da366ea5b2ecf3564b84a3a7f62f1ba60fe225f80f80614b993c3bf | rubric_writer | non-diverse | train | amzd_fb8f48fd2f3f68302abef5ec | amzt_6d023f3a403cf146dcc90d61 | a26a781d13b9157f770ca0e2510512d438d650857ff4e7978ed385596659896e | 4 | null | null | qwen3_final_response | [
{
"role": "user",
"content": "You are an expert at characterising how one specific person writes Amazon product reviews.\n\nYou will be shown 8 reviews written by ONE reviewer, each preceded by the corresponding product metadata. Using only these reviews, write a rubric that captures this reviewer's distinc... | {"collection_fingerprint":"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52","oracle_turn":4,"original_content_sha256":"57faa2c729b991a99529dcd81e9e20e4d641dc751ddd5054cb2806c0077be699","rubric_sha256":"d332c8c47f45af7eb95a13779f9bcda2bdf12b1f5205a3e7f3e3de1f29be67b0","synthetic_submit":true,"transforme... |
amazon-c11-adaptive-oracle-sft-row-v1 | dd511b7fa56f451d16a0932a8ec723f8831a489b17f5e28d5cfde9037fd893ef | rubric_writer | non-diverse | train | amzd_94802a49bb723a9be50376c9 | amzt_a4adeb5a83091d79c1a8f3f7 | 75a3b8d3a8f7bb52faa65a60cc7b8a39e74b26bfb65b4220604165b15090e9fb | 8 | null | null | qwen3_final_response | [{"role":"user","content":"You are an expert at characterising how one specific person writes Amazon(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
amazon-c11-adaptive-oracle-sft-row-v1 | f844e19a58d23c99b597e5d612d8cf2816ff46fb18ca54d560845f8cbdde7cf4 | rubric_writer | non-diverse | train | amzd_3d9c7eee44f96b94f794b92e | amzt_56fe7a63178a3e577cc26b1c | 93b81d953f62427e7d21431d3d1adb26f700009064a9487c09fba260eb8428d2 | 7 | null | null | qwen3_final_response | [{"role":"user","content":"You are an expert at characterising how one specific person writes Amazon(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
amazon-c11-adaptive-oracle-sft-row-v1 | 5476f52c6bb7faaa139a46ce6759c85db25cf3418cb066c457f645d296dc584d | rubric_writer | non-diverse | train | amzd_233a6004c555d99f01f4977d | amzt_debcf7a29b3dc1aa44f99f8c | 8a0fc71230fdae50b833361400580b90d715948b5516f22a5364c409740fcbc5 | 1 | null | null | qwen3_final_response | [{"role":"user","content":"You are an expert at characterising how one specific person writes Amazon(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
amazon-c11-adaptive-oracle-sft-row-v1 | 71d0a88b60a0cc882c603f868045eda5f3a5c59818c83ba9e6ab80f58dde2fd8 | rubric_writer | non-diverse | train | amzd_2b54411781ec873cc32dfe7d | amzt_4fb2753a12f764298bab22a0 | d97d327118ea72dce30c9d2b2c569ee478aaf27548ca7a7fa97dcb6a9f30225c | 4 | null | null | qwen3_final_response | [{"role":"user","content":"You are an expert at characterising how one specific person writes Amazon(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
amazon-c11-adaptive-oracle-sft-row-v1 | 0d754988d07fbb2e25f704312a9141f42385353eee54ba79673032909cdb8743 | criterion_judge | non-diverse | train | amzd_94802a49bb723a9be50376c9 | amzt_a4adeb5a83091d79c1a8f3f7 | 75a3b8d3a8f7bb52faa65a60cc7b8a39e74b26bfb65b4220604165b15090e9fb | 15 | 12 | 6 | qwen3_final_response | [{"role":"user","content":"Judge Amazon product reviews against exactly one weighted criterion for w(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
amazon-c11-adaptive-oracle-sft-row-v1 | af6c47bbd929a7e9882ee4fecb1eb12ce37fbfe7a042ebeb2466e9b82a5efd6b | rubric_writer | non-diverse | train | amzd_0b838abd2ad0e1e6f46283a7 | amzt_9806656e37134ba3ba702941 | f4e4375924568226b6c231bf4047bbf4ecc896b10615183abd79efd2e12b4ad0 | 4 | null | null | qwen3_final_response | [{"role":"user","content":"You are an expert at characterising how one specific person writes Amazon(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
End of preview. Expand in Data Studio
Amazon C11 quality-filtered distillation
This is a high-signal SFT view of asingh15/amazon-c11-distillation.
It contains six balanced rubric-writer/criterion-judge configurations. The original source remains unchanged.
Filter
A trajectory is retained only when its selected rubric has gold-score spread greater than 0.10 on both the selection panel and the paired held-out panel, non-constant proxy scores on both, positive Spearman correlation on both, positive random-to-oracle normalized tie-robust harmonic Best@1..32 on both, and no writer truncation or recovery. The source stopping rubric is never reselected using held-out results.
All writer-prefix rows are retained. An equal number of judge rows is selected deterministically per trajectory,
covering every final criterion first and then maximizing ICL-width and activation-label coverage. The native
train, validation, and test splits are preserved.
| Config | Train rows | Validation | Test | Train panels kept | Source-published retention |
|---|---|---|---|---|---|
latent-state-spearman |
66,012 | 582 | 694 | 4,688 | 47.4% |
latent-state-best32-norm-tr |
70,872 | 664 | 818 | 4,299 | 43.5% |
latent-state-harmonic32-norm-tr |
74,032 | 664 | 824 | 4,565 | 46.2% |
non-diverse-spearman |
69,180 | 812 | 672 | 5,241 | 57.2% |
non-diverse-best32-norm-tr |
78,876 | 842 | 844 | 4,869 | 53.1% |
non-diverse-harmonic32-norm-tr |
79,964 | 942 | 918 | 5,239 | 57.2% |
Gold-score spread audit
Gold spread is max(gold) - min(gold) over each frozen 40-answer panel. Raw covers all source reviewers,
Source reflects the original corpus's spread gate, and Filtered reflects this release. The filter raises mean
spread and therefore enriches for higher-signal panels; it is not a difficulty-representative benchmark sample.
The p10–p90 columns show that the retained data still covers a range of panel score spreads.
| Config | Side | Raw mean | Source mean | Filtered mean | Filtered p10–p90 |
|---|---|---|---|---|---|
latent-state-spearman |
own | 0.735 | 0.742 | 0.776 | 0.600–0.900 |
latent-state-spearman |
cross | 0.610 | 0.615 | 0.701 | 0.400–0.900 |
latent-state-best32-norm-tr |
own | 0.735 | 0.742 | 0.778 | 0.600–0.900 |
latent-state-best32-norm-tr |
cross | 0.610 | 0.615 | 0.703 | 0.450–0.900 |
latent-state-harmonic32-norm-tr |
own | 0.735 | 0.742 | 0.777 | 0.600–0.900 |
latent-state-harmonic32-norm-tr |
cross | 0.610 | 0.615 | 0.703 | 0.416–0.900 |
non-diverse-spearman |
own | 0.610 | 0.657 | 0.699 | 0.400–0.900 |
non-diverse-spearman |
cross | 0.735 | 0.751 | 0.774 | 0.600–0.900 |
non-diverse-best32-norm-tr |
own | 0.610 | 0.657 | 0.700 | 0.450–0.900 |
non-diverse-best32-norm-tr |
cross | 0.735 | 0.751 | 0.776 | 0.600–0.900 |
non-diverse-harmonic32-norm-tr |
own | 0.610 | 0.657 | 0.700 | 0.450–0.900 |
non-diverse-harmonic32-norm-tr |
cross | 0.735 | 0.751 | 0.776 | 0.600–0.900 |
Quality sidecar
Aggregate per-trajectory diagnostics are under quality/<split>/*.parquet. They include inclusion status and
exclusion reasons,
own/cross gold spread, proxy dispersion, Spearman, normalized harmonic Best@1..32, and role-row counts. Raw score
or activation vectors and private targets are not published. The signed aggregate report is
quality_audit.json.
Provenance
- Source dataset:
asingh15/amazon-c11-distillationat3f7302f2eb78cfa8a90110bd370237fd11e1638c - Source objective catalog SHA-256:
faff332d2bf465d37c7d6e9c0bb068522d80e3ae1e5f777688ec6c607f99f1d2 - Collection manifest SHA-256:
866c7bc6801f5fa8813a498c51eaa176ce6f5ff4042197a160f2e6162aa42d45 - Filter policy SHA-256:
3bafbdac25d0c745d75a44fa420ed647916ebf9f0ef64f26870c8690fe11d60c - Filtered catalog SHA-256:
1b756f6f8b6124b7682db6a65c4054265b034b3e530eb03558fa675fad0e6f98 - Loss mask:
qwen3_final_response
- Downloads last month
- 96