{"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/extract-solution","entry":"extract_solution","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":15,"n_papers_ran":3,"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":3,"n_samples_fingerprinted":3,"n_places":17,"n_places_pointer_only":10,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":12},"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","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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d138cde65a9c4401","mcp_get_code":{"code_sha256":"d138cde65a9c4401"}},{"arxiv_id":"2602.01365","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"871a5c13b3f8cedb","mcp_get_code":{"code_sha256":"871a5c13b3f8cedb"}},{"arxiv_id":"2602.01365","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c39f94fe0e1c8d31","mcp_get_code":{"code_sha256":"c39f94fe0e1c8d31"}},{"arxiv_id":"2601.22532","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e4128a6f1b0585bc","mcp_get_code":{"code_sha256":"e4128a6f1b0585bc"}},{"arxiv_id":"2601.21484","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd675dbd0c1a342e","mcp_get_code":{"code_sha256":"dd675dbd0c1a342e"}},{"arxiv_id":"2601.13761","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bc689c85ae67da6","mcp_get_code":{"code_sha256":"6bc689c85ae67da6"}},{"arxiv_id":"2601.13761","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e94715d7a846945","mcp_get_code":{"code_sha256":"1e94715d7a846945"}},{"arxiv_id":"2510.16079","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"34d7767e8b83b614","mcp_get_code":{"code_sha256":"34d7767e8b83b614"}},{"arxiv_id":"2510.00568","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,"code_sha256_prefix":"8c333eb8c4df0dee","mcp_get_code":{"code_sha256":"8c333eb8c4df0dee"}},{"arxiv_id":"2506.14448","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c24f96833221b2b2","mcp_get_code":{"code_sha256":"c24f96833221b2b2"}},{"arxiv_id":"2506.01413","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,"code_sha256_prefix":"6ef992e42dcc5d8c","mcp_get_code":{"code_sha256":"6ef992e42dcc5d8c"}},{"arxiv_id":"2504.01698","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1f0645c6a0d2044e","mcp_get_code":{"code_sha256":"1f0645c6a0d2044e"}},{"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/precess_gsm8k.py","file_url":"https://github.com/lzhxmu/cppo/blob/HEAD/cppo_verl/recipe/cppo/precess_gsm8k.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":"e4128a6f1b0585bc","mcp_get_code":{"code_sha256":"e4128a6f1b0585bc"}},{"arxiv_id":"2502.14768","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b870fd9007fabd94","mcp_get_code":{"code_sha256":"b870fd9007fabd94"}},{"arxiv_id":"2405.19550","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,"code_sha256_prefix":"4f20cd4e4d054fc6","mcp_get_code":{"code_sha256":"4f20cd4e4d054fc6"}},{"arxiv_id":"openreview_BamDfCP5R3","paper":null,"title":"arXiv: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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"34d7767e8b83b614","mcp_get_code":{"code_sha256":"34d7767e8b83b614"}},{"arxiv_id":"2025.findings-emnlp.1015","paper":null,"title":"arXiv: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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5bf05fe925349cb0","mcp_get_code":{"code_sha256":"5bf05fe925349cb0"}}]}