{"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/accuracy-reward","entry":"accuracy_reward","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":6,"n_papers_ran":1,"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":7,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":6},"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":"2608.18096","paper":"/paper/arxiv-2608-18096","title":"MAVEN: A Macro-Societal Value Evaluation Framework of Multimodal Content with Compact Aligned Evaluators","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"zzzzzzzzjj/MAVEN","path":"src/train/reward_funcs.py","file_url":"https://github.com/zzzzzzzzjj/MAVEN/blob/HEAD/src/train/reward_funcs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e256f12f2abca51d","mcp_get_code":{"code_sha256":"e256f12f2abca51d"}},{"arxiv_id":"2603.04597","paper":"/paper/arxiv-2603-04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"LuckyyySTA/GOLF","path":"golf/verl/verl/adaptive_mix_src/reward_with_format.py","file_url":"https://github.com/LuckyyySTA/GOLF/blob/HEAD/golf/verl/verl/adaptive_mix_src/reward_with_format.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b7250010ea994bcd","mcp_get_code":{"code_sha256":"b7250010ea994bcd"}},{"arxiv_id":"2602.10635","paper":"/paper/arxiv-2602-10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"MIT-MI/human_behavior_atlas","path":"training/rl/reward_function/human_behaviour.py","file_url":"https://github.com/MIT-MI/human_behavior_atlas/blob/HEAD/training/rl/reward_function/human_behaviour.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5caf0cb66b1b555f","mcp_get_code":{"code_sha256":"5caf0cb66b1b555f"}},{"arxiv_id":"2602.10635","paper":"/paper/arxiv-2602-10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"MIT-MI/human_behavior_atlas","path":"training/rl/reward_function/human_behaviour_harpo.py","file_url":"https://github.com/MIT-MI/human_behavior_atlas/blob/HEAD/training/rl/reward_function/human_behaviour_harpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f51f42f2c57d4d52","mcp_get_code":{"code_sha256":"f51f42f2c57d4d52"}},{"arxiv_id":"2601.14044","paper":"/paper/arxiv-2601-14044","title":"Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Marcowky/Weather-R1","path":"src/weather_r1/weather_r1_reward.py","file_url":"https://github.com/Marcowky/Weather-R1/blob/HEAD/src/weather_r1/weather_r1_reward.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MPL-2.0","inline_ok":false,"code_sha256_prefix":"2b341266a0ba0ce0","mcp_get_code":{"code_sha256":"2b341266a0ba0ce0"}},{"arxiv_id":"2505.12434","paper":"/paper/videorft-incentivizing-video-reasoning","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","date":"2025-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qiwang98/videorft","path":"src/r1-v/src/open_r1/grpo.py","file_url":"https://github.com/qiwang98/videorft/blob/HEAD/src/r1-v/src/open_r1/grpo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d5ae7b1b53efaacf","mcp_get_code":{"code_sha256":"d5ae7b1b53efaacf"}},{"arxiv_id":"2025.emnlp-main.67","paper":null,"title":"arXiv:2025.emnlp-main.67","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"isyuhaochen/RRC-DSCD","path":"code/rl/rewards.py","file_url":"https://github.com/isyuhaochen/RRC-DSCD/blob/HEAD/code/rl/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"82e8cc4611bb22a4","mcp_get_code":{"code_sha256":"82e8cc4611bb22a4"}}]}