{"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/mathd-normalize-answer","entry":"mathd_normalize_answer","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":14,"n_papers_ran":0,"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":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":3},"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":"2604.03993","paper":"/paper/arxiv-2604-03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ShenzhiYang2000/OLR","path":"eval_scripts/oat_math_grader.py","file_url":"https://github.com/ShenzhiYang2000/OLR/blob/HEAD/eval_scripts/oat_math_grader.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":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2604.00698","paper":"/paper/arxiv-2604-00698","title":"Learning to Hint for Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Andree-9/HiLL","path":"eval/oat_math_grader.py","file_url":"https://github.com/Andree-9/HiLL/blob/HEAD/eval/oat_math_grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2604.00130","paper":"/paper/arxiv-2604-00130","title":"Hierarchical Chain-of-Thought: Enhancing LLM Reasoning Performance and Efficiency","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"XingshuaiHuang/Hi-CoT","path":"utils/math_grader.py","file_url":"https://github.com/XingshuaiHuang/Hi-CoT/blob/HEAD/utils/math_grader.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":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2602.12113","paper":"/paper/arxiv-2602-12113","title":"Adaptive Reflection and Length Coordinated Penalty (ARLCP) STOP UNNECESSARY REFLECTION: TRAINING LRMS FOR EFFICIENT REASONING WITH ADAPTIVE REFLEC-TION AND LENGTH COORDINATED PENALTY","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"ZeweiYu1/ARLCP","path":"src/rm.py","file_url":"https://github.com/ZeweiYu1/ARLCP/blob/HEAD/src/rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2602.03190","paper":"/paper/arxiv-2602-03190","title":"PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"wenquanlu/PrAg-PO","path":"understand_r1_zero/math_grader.py","file_url":"https://github.com/wenquanlu/PrAg-PO/blob/HEAD/understand_r1_zero/math_grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2602.03143","paper":"/paper/arxiv-2602-03143","title":"Self-Hinting Language Models Enhance Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BaohaoLiao/SAGE","path":"eval/oat_math_grader.py","file_url":"https://github.com/BaohaoLiao/SAGE/blob/HEAD/eval/oat_math_grader.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":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2601.22648","paper":"/paper/arxiv-2601-22648","title":"UCPO: Uncertainty-Aware Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"xzhouzeng/ucpo","path":"eval/utils.py","file_url":"https://github.com/xzhouzeng/ucpo/blob/HEAD/eval/utils.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":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2511.15694","paper":"/paper/arxiv-2511-15694","title":"The Impact of Quantization on Large Reasoning Model Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"d-matrix-ai/rlquant","path":"helper_functions.py","file_url":"https://github.com/d-matrix-ai/rlquant/blob/HEAD/helper_functions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2509.24372","paper":"/paper/arxiv-2509-24372","title":"Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"VsonicV/es-at-scale","path":"es_at_scale/reward_function/math_grader.py","file_url":"https://github.com/VsonicV/es-at-scale/blob/HEAD/es_at_scale/reward_function/math_grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"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/adapt_think_rm.py","file_url":"https://github.com/thu-keg/adaptthink/blob/HEAD/src/adapt_think_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2505.13379","paper":"/paper/thinkless-llm-learns-when-to-think","title":"Thinkless: LLM Learns When to Think","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vainf/thinkless","path":"deepscaler/rewards/math_utils/utils.py","file_url":"https://github.com/vainf/thinkless/blob/HEAD/deepscaler/rewards/math_utils/utils.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":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2505.03335","paper":"/paper/absolute-zero-reinforced-self-play-reasoning","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","date":"2025-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeapLabTHU/Absolute-Zero-Reasoner","path":"absolute_zero_reasoner/rewards/math_utils.py","file_url":"https://github.com/LeapLabTHU/Absolute-Zero-Reasoner/blob/HEAD/absolute_zero_reasoner/rewards/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2504.16084","paper":"/paper/ttrl-test-time-reinforcement-learning","title":"TTRL: Test-Time Reinforcement Learning","date":"2025-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prime-rl/ttrl","path":"verl/verl/utils/reward_score/ttrl_math/math_utils.py","file_url":"https://github.com/prime-rl/ttrl/blob/HEAD/verl/verl/utils/reward_score/ttrl_math/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f78ce44e20c50d1","mcp_get_code":{"code_sha256":"3f78ce44e20c50d1"}},{"arxiv_id":"2503.10460","paper":"/paper/light-r1-curriculum-sft-dpo-and-rl-for-long","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Qihoo360/Light-R1","path":"deepscaler-release/deepscaler/rewards/math_utils/utils.py","file_url":"https://github.com/Qihoo360/Light-R1/blob/HEAD/deepscaler-release/deepscaler/rewards/math_utils/utils.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":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}}]}