{"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/reward-fn","entry":"reward_fn","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":7,"n_papers_ran":6,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":0,"unverified":2},"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":"2506.11902","paper":"/paper/treerl-llm-reinforcement-learning-with-on","title":"TreeRL: LLM Reinforcement Learning with On-Policy Tree Search","date":"2025-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/TreeRL","path":"train_reinforce_ray.py","file_url":"https://github.com/THUDM/TreeRL/blob/HEAD/train_reinforce_ray.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"18ed61dcfadbbdf0","mcp_get_code":{"code_sha256":"18ed61dcfadbbdf0"}},{"arxiv_id":"2506.11902","paper":"/paper/treerl-llm-reinforcement-learning-with-on","title":"TreeRL: LLM Reinforcement Learning with On-Policy Tree Search","date":"2025-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUDM/TreeRL","path":"train_ppo_ray.py","file_url":"https://github.com/THUDM/TreeRL/blob/HEAD/train_ppo_ray.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":"582b5f2a2d95b05b","mcp_get_code":{"code_sha256":"582b5f2a2d95b05b"}},{"arxiv_id":"2504.08837","paper":"/paper/vl-rethinker-incentivizing-self-reflection-of","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiger-ai-lab/vl-rethinker","path":"openrlhf/cli/eval_ray.py","file_url":"https://github.com/tiger-ai-lab/vl-rethinker/blob/HEAD/openrlhf/cli/eval_ray.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"18ed61dcfadbbdf0","mcp_get_code":{"code_sha256":"18ed61dcfadbbdf0"}},{"arxiv_id":"2504.05185","paper":"/paper/concise-reasoning-via-reinforcement-learning","title":"Concise Reasoning via Reinforcement Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"18ed61dcfadbbdf0","mcp_get_code":{"code_sha256":"18ed61dcfadbbdf0"}},{"arxiv_id":"2503.22828","paper":"/paper/learning-to-reason-for-long-form-story","title":"Learning to Reason for Long-Form Story Generation","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alex-Gurung/ReasoningNCP","path":"rl_training/train_ncp.py","file_url":"https://github.com/Alex-Gurung/ReasoningNCP/blob/HEAD/rl_training/train_ncp.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18ed61dcfadbbdf0","mcp_get_code":{"code_sha256":"18ed61dcfadbbdf0"}},{"arxiv_id":"2210.08708","paper":"/paper/teacher-forcing-recovers-reward-functions-for","title":"Teacher Forcing Recovers Reward Functions for Text Generation","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manga-uofa/lmreward","path":"reinforce.py","file_url":"https://github.com/manga-uofa/lmreward/blob/HEAD/reinforce.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b7caa86b3587a838","mcp_get_code":{"code_sha256":"b7caa86b3587a838"}},{"arxiv_id":"2204.05862","paper":"/paper/training-a-helpful-and-harmless-assistant","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","date":"2022-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miaoyuchun/inform","path":"openrlhf/cli/train_ppo_ray.py","file_url":"https://github.com/miaoyuchun/inform/blob/HEAD/openrlhf/cli/train_ppo_ray.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"18ed61dcfadbbdf0","mcp_get_code":{"code_sha256":"18ed61dcfadbbdf0"}},{"arxiv_id":"1807.00412","paper":"/paper/learning-to-drive-in-a-day","title":"Learning to Drive in a Day","date":"2018-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bitsauce/Carla-ppo","path":"CarlaEnv/carla_lap_env.py","file_url":"https://github.com/bitsauce/Carla-ppo/blob/HEAD/CarlaEnv/carla_lap_env.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"810da5dae21567b6","mcp_get_code":{"code_sha256":"810da5dae21567b6"}}]}