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 485 609 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
amazon-c11-nothink-distillation-sft-row-v1 | dd345cf30a161ea9de82c718887564a0d9f900f93293e00c1794a71b66364af9 | 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,"recovery_sanitized":false,"rubric_sha256":"0ee3f01add60497e4c9174951e7ba94feb46d26c10e4996b7191dab66639... |
amazon-c11-nothink-distillation-sft-row-v1 | a5a9283f1c4a66df9f158e20a19514eb94685806596e66bdbafa5d5e3c7d234a | 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,"recovery_sanitized":false,"rubric_sha256":"c81a988feeeb5bce3aee0e55c7884623fdf008a8b335ea17540c354b942b... |
amazon-c11-nothink-distillation-sft-row-v1 | 082e6c7de91c31d6f20186bc06aa04e2e935dca6dcd6aa3875e84b488a780f45 | 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,"recovery_sanitized":false,"rubric_sha256":"d332c8c47f45af7eb95a13779f9bcda2bdf12b1f5205a3e7f3e3de1f29be6... |
amazon-c11-nothink-distillation-sft-row-v1 | 2444a819dcfe83442817b7cbb81888d615191cbb60a0dc0ee4bc1ac0b03f0bd3 | 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","recovery_sanitized":false,"rubric_sha256":"d332c8c47f45af7eb95a13779f9bcda2bdf12b1f5205a3e7f3e3de1f29be67b0","source_... |
amazon-c11-nothink-distillation-sft-row-v1 | a16c11ee815ad9b121a0de8e42035e5dc70b030d57fd3ca6cf3cccba4993da3b | 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 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":15,"original_content_sha256":"8bbc6bda74a405c1a6085382e97a81cf60a8dfdc6f97f8260a28180edd74132c","recovery_sanitized":false,"rubric_sha256":"31bed42ccd0287089149f2f86d2d6b83cd95643a969f57dd7fcba8c55282679c","source... |
amazon-c11-nothink-distillation-sft-row-v1 | 3b2c411598e963853631d901111d809893934c64cb8b865a635a7c8a26fbc66b | 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 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":18,"original_content_sha256":"c16f23bd6871a69037819b968e374004ce951db3da62f49eef6331abfc3c87c9","recovery_sanitized":false,"rubric_sha256":"6e92fd71557ff1436bbb6413f505db71936096724492710b6075497daa1950ac","source... |
amazon-c11-nothink-distillation-sft-row-v1 | 16540d736aed2a94c1975e4c799f43776dbbb8749079e5b8e7e392afa0b45630 | 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 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":2,"original_content_sha256":"b01e4ef1e6d6f421c525a4e5ed3e2300f492664215ea4ed237cac9aa9ecf4563","recovery_sanitized":false,"rubric_sha256":"fa5ebed8bd7b12ab160f8cd20dba792f0be6ac1886ad1df68ec7c4aa2f394204","source_... |
amazon-c11-nothink-distillation-sft-row-v1 | 4ff14179bc67d6c9aaa8def396a2a71ea5f6a9dc0665ae84fede4a5ce9430589 | 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-nothink-distillation-sft-row-v1 | 37bdd3036f3f9147af96d0d5045194d8610dc96d61fa16142684872a392e54df | 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-nothink-distillation-sft-row-v1 | 7ec7ab0bee28a40fde2a316d2f5ee18e02743a92f2d0f8434f37997847342542 | 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 no-think quality-filtered distillation
This preserves the selected C11 writer/criterion-judge examples and their row geometry while discarding all teacher scratch reasoning. Membership follows the pinned C11 quality-filter policy. Signed aggregate filter provenance is under quality/<split>/; it is not exposed as another dataset configuration.
The six configurations cross the two candidate variants with the three frozen stopping objectives. Every
configuration exposes only its combined training view and preserves the native train, validation, and test
splits.
| Config | Train | Validation | Test |
|---|---|---|---|
latent-state-spearman |
66,012 | 582 | 694 |
latent-state-best32-norm-tr |
70,872 | 664 | 818 |
latent-state-harmonic32-norm-tr |
74,032 | 664 | 824 |
non-diverse-spearman |
69,180 | 812 | 672 |
non-diverse-best32-norm-tr |
78,876 | 842 | 844 |
non-diverse-harmonic32-norm-tr |
79,964 | 942 | 918 |
Provenance
asingh15/amazon-c11-distillation-filteredatf3cbaf3082ca95ba94db218810b8b3e4fa076e81(membership-and-combined; catalog1b756f6f8b6124b7682db6a65c4054265b034b3e530eb03558fa675fad0e6f98)- Derived catalog SHA-256:
002b43ccfa9cfd1ece0f398d4365c25e7ec19740379d338edf785eb6c92eef92 - Row schema:
amazon-c11-nothink-distillation-sft-row-v1
- Downloads last month
- 89