{"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/get-custom-reward-fn","entry":"get_custom_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":13,"n_papers_ran":10,"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":5,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":2,"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":"2606.16497","paper":"/paper/arxiv-2606-16497","title":"daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"GAIR-NLP/daVinci-kernel","path":"davinci-kernel/kernel/main_grading.py","file_url":"https://github.com/GAIR-NLP/daVinci-kernel/blob/HEAD/davinci-kernel/kernel/main_grading.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23a9da6ee45a38bd","mcp_get_code":{"code_sha256":"23a9da6ee45a38bd"}},{"arxiv_id":"2606.06428","paper":"/paper/arxiv-2606-06428","title":"Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hanxuhu/rl-new-language","path":"main_ppo.py","file_url":"https://github.com/hanxuhu/rl-new-language/blob/HEAD/main_ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e535567b971a2a42","mcp_get_code":{"code_sha256":"e535567b971a2a42"}},{"arxiv_id":"2604.09793","paper":"/paper/arxiv-2604-09793","title":"GIANTS: Generative Insight Anticipation from Scientific Literature","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"joyheyueya/giants","path":"recipe/dapo/src/main_dapo.py","file_url":"https://github.com/joyheyueya/giants/blob/HEAD/recipe/dapo/src/main_dapo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2506.12935","paper":"/paper/soundmind-rl-incentivized-logic-reasoning-for","title":"SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Models","date":"2025-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xid32/SoundMind","path":"recipe/dapo/main_dapo.py","file_url":"https://github.com/xid32/SoundMind/blob/HEAD/recipe/dapo/main_dapo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6a2a67dab81f497","mcp_get_code":{"code_sha256":"b6a2a67dab81f497"}},{"arxiv_id":"2506.08672","paper":"/paper/rulereasoner-reinforced-rule-based-reasoning","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-nlco/rulereasoner","path":"verl/recipe/dapo/src/main_dapo.py","file_url":"https://github.com/bigai-nlco/rulereasoner/blob/HEAD/verl/recipe/dapo/src/main_dapo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b6512040439cb7a2","mcp_get_code":{"code_sha256":"b6512040439cb7a2"}},{"arxiv_id":"2506.01347","paper":"/paper/the-surprising-effectiveness-of-negative","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianhongzxy/rlvr-decomposed","path":"verl/trainer/main_ppo.py","file_url":"https://github.com/tianhongzxy/rlvr-decomposed/blob/HEAD/verl/trainer/main_ppo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0a596501e7243b1f","mcp_get_code":{"code_sha256":"0a596501e7243b1f"}},{"arxiv_id":"2505.22019","paper":"/paper/vrag-rl-empower-vision-perception-based-rag","title":"VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning","date":"2025-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2505.17508","paper":null,"title":"arXiv:2505.17508","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"complex-reasoning/RPG","path":"recipe/rpg/src/main_rpg.py","file_url":"https://github.com/complex-reasoning/RPG/blob/HEAD/recipe/rpg/src/main_rpg.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2505.14362","paper":"/paper/deepeyes-incentivizing-thinking-with-images","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"visual-agent/deepeyes","path":"recipe/dapo/src/main_dapo.py","file_url":"https://github.com/visual-agent/deepeyes/blob/HEAD/recipe/dapo/src/main_dapo.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":"b6512040439cb7a2","mcp_get_code":{"code_sha256":"b6512040439cb7a2"}},{"arxiv_id":"2505.13417","paper":"/paper/adaptthink-reasoning-models-can-learn-when-to","title":"AdaptThink: Reasoning Models Can Learn When to Think","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-keg/adaptthink","path":"src/main_ppo.py","file_url":"https://github.com/thu-keg/adaptthink/blob/HEAD/src/main_ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e535567b971a2a42","mcp_get_code":{"code_sha256":"e535567b971a2a42"}},{"arxiv_id":"2504.11343","paper":"/paper/a-minimalist-approach-to-llm-reasoning-from","title":"A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce","date":"2025-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlhflow/minimal-rl","path":"verl/trainer/main_eval.py","file_url":"https://github.com/rlhflow/minimal-rl/blob/HEAD/verl/trainer/main_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a3d29a95bae787bf","mcp_get_code":{"code_sha256":"a3d29a95bae787bf"}},{"arxiv_id":"2504.05812","paper":"/paper/right-question-is-already-half-the-answer","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","date":"2025-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2503.22342","paper":"/paper/cppo-accelerating-the-training-of-group","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","date":"2025-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lzhxmu/cppo","path":"cppo_verl/recipe/cppo/src/main_cppo.py","file_url":"https://github.com/lzhxmu/cppo/blob/HEAD/cppo_verl/recipe/cppo/src/main_cppo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}}]}