{"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/extract-solution","entry":"extract_solution","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":15,"n_papers_ran":14,"n_papers_ran_no_instrument_failure":6,"n_papers_ran_instrument_only":8,"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":15,"n_samples_ran":14,"n_samples_constructed":0,"n_samples_ran_checked":6,"n_samples_instrument":8,"n_samples_unverified":1,"n_samples_fingerprinted":10,"n_places":17,"n_places_pointer_only":11,"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":8,"ran_fixture":0,"ran":6,"unverified":1},"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":"2606.19236","arxiv_id_is_arxiv":true,"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":"verl/utils/reward_score/math_stare.py","file_url":"https://github.com/hp-luo/STARE/blob/HEAD/verl/utils/reward_score/math_stare.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d138cde65a9c4401","code_sha256_prefix":"d138cde65a9c4401","mcp_get_code":{"code_sha256":"d138cde65a9c4401"}},{"arxiv_id":"2602.01365","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"uservan/cross_domain","path":"verify/score/gsm8k.py","file_url":"https://github.com/uservan/cross_domain/blob/HEAD/verify/score/gsm8k.py","status":"ran","verification_level":1,"contract_check":null,"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, uservan/cross_domain when it was checked","code_sha256":"871a5c13b3f8cedb","code_sha256_prefix":"871a5c13b3f8cedb","mcp_get_code":{"code_sha256":"871a5c13b3f8cedb"}},{"arxiv_id":"2602.01365","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-01365","title":"When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"uservan/cross_domain","path":"verify/score/kk.py","file_url":"https://github.com/uservan/cross_domain/blob/HEAD/verify/score/kk.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, uservan/cross_domain when it was checked","code_sha256":"c39f94fe0e1c8d31","code_sha256_prefix":"c39f94fe0e1c8d31","mcp_get_code":{"code_sha256":"c39f94fe0e1c8d31"}},{"arxiv_id":"2601.22532","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"tt725/Bandit-Reinforcement-Fine-tuning","path":"Dataset/gsm8k/gsm8k.py","file_url":"https://github.com/tt725/Bandit-Reinforcement-Fine-tuning/blob/HEAD/Dataset/gsm8k/gsm8k.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, tt725/Bandit-Reinforcement-Fine-tuning when it was checked","code_sha256":"e4128a6f1b0585bc","code_sha256_prefix":"e4128a6f1b0585bc","mcp_get_code":{"code_sha256":"e4128a6f1b0585bc"}},{"arxiv_id":"2601.21484","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"sheriyuo/ETS","path":"llada/gsm8k.py","file_url":"https://github.com/sheriyuo/ETS/blob/HEAD/llada/gsm8k.py","status":"ran","verification_level":1,"contract_check":null,"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, sheriyuo/ETS when it was checked","code_sha256":"dd675dbd0c1a342e","code_sha256_prefix":"dd675dbd0c1a342e","mcp_get_code":{"code_sha256":"dd675dbd0c1a342e"}},{"arxiv_id":"2601.13761","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-13761","title":"DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"RUCBM/DARC","path":"evaluation/eval_bbeh.py","file_url":"https://github.com/RUCBM/DARC/blob/HEAD/evaluation/eval_bbeh.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, RUCBM/DARC when it was checked","code_sha256":"6bc689c85ae67da6","code_sha256_prefix":"6bc689c85ae67da6","mcp_get_code":{"code_sha256":"6bc689c85ae67da6"}},{"arxiv_id":"2601.13761","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-13761","title":"DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"RUCBM/DARC","path":"evaluation/eval_gpqa_diamond.py","file_url":"https://github.com/RUCBM/DARC/blob/HEAD/evaluation/eval_gpqa_diamond.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, RUCBM/DARC when it was checked","code_sha256":"1e94715d7a846945","code_sha256_prefix":"1e94715d7a846945","mcp_get_code":{"code_sha256":"1e94715d7a846945"}},{"arxiv_id":"2510.16079","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-16079","title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Edaizi/EvolveR","path":"evolver/rewards/reward_outcome.py","file_url":"https://github.com/Edaizi/EvolveR/blob/HEAD/evolver/rewards/reward_outcome.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34d7767e8b83b614","code_sha256_prefix":"34d7767e8b83b614","mcp_get_code":{"code_sha256":"34d7767e8b83b614"}},{"arxiv_id":"2510.00568","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2510-00568","title":"ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"TencentBAC/ReSeek","path":"verl/utils/reward_score/reseek_regex.py","file_url":"https://github.com/TencentBAC/ReSeek/blob/HEAD/verl/utils/reward_score/reseek_regex.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, TencentBAC/ReSeek when it was checked","code_sha256":"8c333eb8c4df0dee","code_sha256_prefix":"8c333eb8c4df0dee","mcp_get_code":{"code_sha256":"8c333eb8c4df0dee"}},{"arxiv_id":"2506.14448","arxiv_id_is_arxiv":true,"paper":"/paper/how-far-can-llms-improve-from-experience","title":"How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparison","date":"2025-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Alice1998/Test-time-Learning","path":"cumulative_setting/dynamic_cheatsheet/utils/extractor.py","file_url":"https://github.com/Alice1998/Test-time-Learning/blob/HEAD/cumulative_setting/dynamic_cheatsheet/utils/extractor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Alice1998/Test-time-Learning when it was checked","code_sha256":"c24f96833221b2b2","code_sha256_prefix":"c24f96833221b2b2","mcp_get_code":{"code_sha256":"c24f96833221b2b2"}},{"arxiv_id":"2506.01413","arxiv_id_is_arxiv":true,"paper":"/paper/incentivizing-reasoning-for-advanced","title":"Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuleiqin/raif","path":"openrlhf/trainer/ppo_utils/complex_scoring.py","file_url":"https://github.com/yuleiqin/raif/blob/HEAD/openrlhf/trainer/ppo_utils/complex_scoring.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, yuleiqin/raif (NOASSERTION)","code_sha256":"6ef992e42dcc5d8c","code_sha256_prefix":"6ef992e42dcc5d8c","mcp_get_code":{"code_sha256":"6ef992e42dcc5d8c"}},{"arxiv_id":"2504.01698","arxiv_id_is_arxiv":true,"paper":"/paper/tom-rl-reinforcement-learning-unlocks-theory","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?","date":"2025-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-ai/ToM-RL","path":"verl/utils/reward_score/explore_tom.py","file_url":"https://github.com/bigai-ai/ToM-RL/blob/HEAD/verl/utils/reward_score/explore_tom.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1f0645c6a0d2044e","code_sha256_prefix":"1f0645c6a0d2044e","mcp_get_code":{"code_sha256":"1f0645c6a0d2044e"}},{"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/precess_gsm8k.py","file_url":"https://github.com/lzhxmu/cppo/blob/HEAD/cppo_verl/recipe/cppo/precess_gsm8k.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from tt725/Bandit-Reinforcement-Fine-tuning, and GitHub detected no licence in that repository when it was checked","code_sha256":"e4128a6f1b0585bc","code_sha256_prefix":"e4128a6f1b0585bc","mcp_get_code":{"code_sha256":"e4128a6f1b0585bc"}},{"arxiv_id":"2502.14768","arxiv_id_is_arxiv":true,"paper":"/paper/logic-rl-unleashing-llm-reasoning-with-rule","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Unakar/Logic-RL","path":"eval_kk/compute_score.py","file_url":"https://github.com/Unakar/Logic-RL/blob/HEAD/eval_kk/compute_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b870fd9007fabd94","code_sha256_prefix":"b870fd9007fabd94","mcp_get_code":{"code_sha256":"b870fd9007fabd94"}},{"arxiv_id":"2405.19550","arxiv_id_is_arxiv":true,"paper":"/paper/stress-testing-capability-elicitation-with","title":"Stress-Testing Capability Elicitation With Password-Locked Models","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FabienRoger/sandbagging","path":"sandbagging/code_data.py","file_url":"https://github.com/FabienRoger/sandbagging/blob/HEAD/sandbagging/code_data.py","status":"unverified","verification_level":0,"contract_check":null,"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, FabienRoger/sandbagging when it was checked","code_sha256":"4f20cd4e4d054fc6","code_sha256_prefix":"4f20cd4e4d054fc6","mcp_get_code":{"code_sha256":"4f20cd4e4d054fc6"}},{"arxiv_id":"openreview_BamDfCP5R3","arxiv_id_is_arxiv":false,"paper":null,"title":"OpenReview id openreview_BamDfCP5R3","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"KnowledgeXLab/EvolveR","path":"evolver/rewards/reward_outcome.py","file_url":"https://github.com/KnowledgeXLab/EvolveR/blob/HEAD/evolver/rewards/reward_outcome.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"34d7767e8b83b614","code_sha256_prefix":"34d7767e8b83b614","mcp_get_code":{"code_sha256":"34d7767e8b83b614"}},{"arxiv_id":"2025.findings-emnlp.1015","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-emnlp.1015","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"fzp0424/MT-R1-Zero","path":"eval/vllm_inference.py","file_url":"https://github.com/fzp0424/MT-R1-Zero/blob/HEAD/eval/vllm_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5bf05fe925349cb0","code_sha256_prefix":"5bf05fe925349cb0","mcp_get_code":{"code_sha256":"5bf05fe925349cb0"}}],"record_sha256":"470e1fa7bc681fc45d56006a26922faf5229bdd1599a4be6c95f9b6dfcd86f9b","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}