{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/get-custom-reward-fn","entry":"get_custom_reward_fn","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":13,"n_papers_ran":13,"n_papers_ran_no_instrument_failure":3,"n_papers_ran_instrument_only":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":7,"n_samples_constructed":0,"n_samples_ran_checked":2,"n_samples_instrument":5,"n_samples_unverified":0,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":5,"n_places_pointer_only_link_open":1,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":5,"ran_fixture":0,"ran":2,"unverified":0},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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","arxiv_id_is_arxiv":true,"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, GAIR-NLP/daVinci-kernel when it was checked","code_sha256":"23a9da6ee45a38bd","code_sha256_prefix":"23a9da6ee45a38bd","mcp_get_code":{"code_sha256":"23a9da6ee45a38bd"}},{"arxiv_id":"2606.06428","arxiv_id_is_arxiv":true,"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hanxuhu/rl-new-language when it was checked","code_sha256":"e535567b971a2a42","code_sha256_prefix":"e535567b971a2a42","mcp_get_code":{"code_sha256":"e535567b971a2a42"}},{"arxiv_id":"2604.09793","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34be00218891a21a","code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2506.12935","arxiv_id_is_arxiv":true,"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b6a2a67dab81f497","code_sha256_prefix":"b6a2a67dab81f497","mcp_get_code":{"code_sha256":"b6a2a67dab81f497"}},{"arxiv_id":"2506.08672","arxiv_id_is_arxiv":true,"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b6512040439cb7a2","code_sha256_prefix":"b6512040439cb7a2","mcp_get_code":{"code_sha256":"b6512040439cb7a2"}},{"arxiv_id":"2506.01347","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0a596501e7243b1f","code_sha256_prefix":"0a596501e7243b1f","mcp_get_code":{"code_sha256":"0a596501e7243b1f"}},{"arxiv_id":"2505.22019","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"34be00218891a21a","code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2505.17508","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34be00218891a21a","code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2505.14362","arxiv_id_is_arxiv":true,"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b6512040439cb7a2","code_sha256_prefix":"b6512040439cb7a2","mcp_get_code":{"code_sha256":"b6512040439cb7a2"}},{"arxiv_id":"2505.13417","arxiv_id_is_arxiv":true,"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hanxuhu/rl-new-language, and GitHub detected no licence in that repository when it was checked","code_sha256":"e535567b971a2a42","code_sha256_prefix":"e535567b971a2a42","mcp_get_code":{"code_sha256":"e535567b971a2a42"}},{"arxiv_id":"2504.11343","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"a3d29a95bae787bf","code_sha256_prefix":"a3d29a95bae787bf","mcp_get_code":{"code_sha256":"a3d29a95bae787bf"}},{"arxiv_id":"2504.05812","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","code_sha256":"34be00218891a21a","code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}},{"arxiv_id":"2503.22342","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34be00218891a21a","code_sha256_prefix":"34be00218891a21a","mcp_get_code":{"code_sha256":"34be00218891a21a"}}],"record_sha256":"ab5591049460a2657cdb819ed5d356e4298e60f264090f5ab4ef46c3e30eae68","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}