{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/compute-score-data-source","entry":"compute_score_data_source","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":14,"n_papers_ran":14,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2608.24696","paper":"/paper/arxiv-2608-24696","title":"On-policy Distillation with Verifiable Reward","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LeapLabTHU/OPDVR","path":"verl/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/LeapLabTHU/OPDVR/blob/HEAD/verl/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2608.09836","paper":"/paper/arxiv-2608-09836","title":"Mismatch Matters: On-Policy Distillation Beyond Token Agreement","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"yzc-666/TIDE","path":"verl/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/yzc-666/TIDE/blob/HEAD/verl/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2606.19236","paper":"/paper/arxiv-2606-19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hp-luo/STARE","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/hp-luo/STARE/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2606.06021","paper":"/paper/arxiv-2606-06021","title":"OPRD: On-Policy Representation Distillation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"ShenzhiYang2000/OPRD","path":"verl/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/ShenzhiYang2000/OPRD/blob/HEAD/verl/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2606.02684","paper":"/paper/arxiv-2606-02684","title":"Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"YuYingLi0/FiRe-OPD","path":"verl/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/YuYingLi0/FiRe-OPD/blob/HEAD/verl/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2605.11739","paper":"/paper/arxiv-2605-11739","title":"Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"caiyuchen-ustc/EffOPD","path":"EffOPD/verl/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/caiyuchen-ustc/EffOPD/blob/HEAD/EffOPD/verl/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2604.17555","paper":"/paper/arxiv-2604-17555","title":"CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"snap-research/CoSearch","path":"verl/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/snap-research/CoSearch/blob/HEAD/verl/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2604.03993","paper":"/paper/arxiv-2604-03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ShenzhiYang2000/OLR","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/ShenzhiYang2000/OLR/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2603.20046","paper":"/paper/arxiv-2603-20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sikelifei/HeRL","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/sikelifei/HeRL/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2603.07079","paper":"/paper/arxiv-2603-07079","title":"Entropy-Aware On-Policy Distillation of Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"WLS04/EOPD","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/WLS04/EOPD/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2603.02938","paper":"/paper/arxiv-2603-02938","title":"Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"mysteriouslfz/GraphSSR","path":"reinforcement_learning/recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/mysteriouslfz/GraphSSR/blob/HEAD/reinforcement_learning/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2602.17550","paper":"/paper/arxiv-2602-17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"FlyTune/MASPO-RL","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/FlyTune/MASPO-RL/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"2601.21468","paper":"/paper/arxiv-2601-21468","title":"MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"meituan/MemOCR","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/meituan/MemOCR/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}},{"arxiv_id":"openreview_lbaBsu0CaY","paper":null,"title":"arXiv:openreview_lbaBsu0CaY","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Tunanzzz/Meerkat-VL","path":"recipe/open_math_reasoning/compute_score.py","file_url":"https://github.com/Tunanzzz/Meerkat-VL/blob/HEAD/recipe/open_math_reasoning/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05a86ccb0b3876dd","mcp_get_code":{"code_sha256":"05a86ccb0b3876dd"}}]}