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 312 435 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
amazon-c11-adaptive-oracle-sft-row-v1 | 534fd7bb5d0fa93447139a7211ec975a1734543ef74aae23836dba9657aedc30 | rubric_writer | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 3 | 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":7,"original_content_sha256":"9e5a5280d85c36a4f832516242faaab4be1f810c68247bc092c9b2b0c05eaa1b","rubric_sha256":"c82572ff44cff8c2723c68a51d9da3985ec007ea4674396a0f6d09380061d56b","synthetic_submit":false,"transform... |
amazon-c11-adaptive-oracle-sft-row-v1 | 0421705fab9b161d43c5e4f6a2dc10c926900a886a55411528be462174c77e4a | criterion_judge | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 7 | 0 | 37 | 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# IPOW 14.4'' Ex... | {"collection_fingerprint":"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52","history_reset":false,"lane_cache_key":"daa93d69f0887ef797b6fde2b0db400b5ff2562b9c8f6772811c8001928b8105","oracle_turn":7,"rubric_sha256":"ca2ce8394b60eb324012ab52424d96eb05c1146b134f5fcfbf121c2929f6944b","seed":1783056152} |
amazon-c11-adaptive-oracle-sft-row-v1 | bc906970169c51de0f5206b2d5c7bbfdd2642b838ec33f7d9c83a46f3d222ba3 | criterion_judge | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 7 | 4 | 38 | 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 | ec69d0a23cab4dc4f6f2b902c34942290e516203e2f26e7d673449c399600299 | criterion_judge | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 7 | 2 | 10 | 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 | 3f81c329878c80e5495397d41e38203de98f7b1843ff588eaaeb9bc8cfecf4fe | rubric_writer | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 5 | 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 | 3b13238dff3ca00f8187945872012e263daca497a5ce5585dbee900a64ed7087 | rubric_writer | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 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 | 8fd49f783cd41a032ec2def6e0114ff74ce33a4b302232b5a4631ca96a35fd20 | rubric_writer | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 2 | 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 | c97ec56ff09c7c259474d9588a4db1ac6ca294875a474dd9397bd475cf89b79d | criterion_judge | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 7 | 0 | 21 | 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 | 3cbf69fcf175d3d04ab546ba6c363468b1e25dafbb00b7575545a27753f7e209 | rubric_writer | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 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 | 7567fe22794123b16b577f1759f9e82aa1e078977836675319f223de0089fb7b | criterion_judge | latent-state | train | amzd_7ef9cf5c3060766b17047f24 | amzt_8a055292db193a089d746184 | 5152cf41f45d3ed71221d85380279976dd7445da8e71b3aa574b4213595701a5 | 7 | 0 | 6 | qwen3_final_response | [{"role":"user","content":"Judge Amazon product reviews against exactly one weighted criterion for w(...TRUNCATED) | "{\"collection_fingerprint\":\"f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52\",\"(...TRUNCATED) |
End of preview. Expand in Data Studio
Amazon C11 adaptive-oracle distillation
Immutable backing data for the Amazon C11 Distillation Viewer.
- Collection:
amazon-c11-adaptive-oracle-v1 - Configuration SHA-256:
f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52 - Export manifest SHA-256:
36b335ad8f007b0dd4465c52a5b574d79be48a92b9913307298aa9d5c03b5736 - Source reviewers: 10,200
- Published panels: 19,432 / 20,400
- Filtered panels: 968
- SFT rows: 6,120,902
data/index.json contains the global index and data/reviewers/*.json.gz contains one independently loadable
reviewer shard. The viewer pins the exact Dataset commit rather than following main.
Six stopping-oracle SFT datasets
This revision adds the Cartesian product of two candidate-panel variants (latent-state and
non-diverse) and three stopping oracles:
spearman: Spearman rank correlation;best32-norm-tr: candidate-min/max-normalized tie-robust Best@32; andharmonic32-norm-tr: the tie-robust, random-to-oracle-normalized sum of Best@k / k for k=1..32.
Constant candidate-score vectors are excluded before maximization. Panels whose gold-score spread is at most 0.10 are filtered for every oracle, and the earliest maximum within 1e-12 is selected. This leaves 10,085 latent-state and 9,347 non-diverse panels; 968 of 20,400 source panels are filtered.
The six unsuffixed configurations are deterministic 1:1 writer/judge-balanced views. Append -writer
or -judge to a primary configuration name for the corresponding role-only view. Every configuration
has native train, validation, and test splits and uses the qwen3_final_response loss-mask contract.
| Primary config | Combined | Writer | Judge |
|---|---|---|---|
latent-state-spearman |
151,056 | 75,528 | 3,019,360 |
latent-state-best32-norm-tr |
155,984 | 77,992 | 3,117,600 |
latent-state-harmonic32-norm-tr |
156,614 | 78,307 | 3,130,040 |
non-diverse-spearman |
133,812 | 66,906 | 2,674,240 |
non-diverse-best32-norm-tr |
147,872 | 73,936 | 2,955,760 |
non-diverse-harmonic32-norm-tr |
141,482 | 70,741 | 2,827,400 |
- Derived catalog SHA-256:
faff332d2bf465d37c7d6e9c0bb068522d80e3ae1e5f777688ec6c607f99f1d2 - Collection:
amazon-c11-adaptive-oracle-v1 - Configuration SHA-256:
f0c8a1ee29cc3b2ad93d3ad14b55149da73d6920e496e26037ee984749b83c52 - Source materialization manifest SHA-256:
866c7bc6801f5fa8813a498c51eaa176ce6f5ff4042197a160f2e6162aa42d45 - Parent viewer-data commit:
51528a93fa3b8d4256873e3bafb2d52028609494
- Downloads last month
- 179