{"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/mathd-normalize-answer","entry":"mathd_normalize_answer","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":14,"n_papers_ran":5,"n_papers_ran_no_instrument_failure":0,"n_papers_ran_instrument_only":5,"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":1,"n_samples_constructed":0,"n_samples_ran_checked":0,"n_samples_instrument":1,"n_samples_unverified":2,"n_samples_fingerprinted":1,"n_places":14,"n_places_pointer_only":4,"n_places_pointer_only_link_open":0,"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":1,"ran_fixture":0,"ran":0,"unverified":2},"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":"2604.03993","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2604.00698","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, Andree-9/HiLL when it was checked","code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2604.00130","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2602.12113","arxiv_id_is_arxiv":true,"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":"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":"ec578739f88adc22","code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2602.03190","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, wenquanlu/PrAg-PO when it was checked","code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2602.03143","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2601.22648","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2511.15694","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, d-matrix-ai/rlquant when it was checked","code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"arxiv_id":"2509.24372","arxiv_id_is_arxiv":true,"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,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, VsonicV/es-at-scale when it was checked","code_sha256":"0388e4fa2f36659e","code_sha256_prefix":"0388e4fa2f36659e","mcp_get_code":{"code_sha256":"0388e4fa2f36659e"}},{"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/adapt_think_rm.py","file_url":"https://github.com/thu-keg/adaptthink/blob/HEAD/src/adapt_think_rm.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":"ec578739f88adc22","code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2505.13379","arxiv_id_is_arxiv":true,"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":"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":"ec578739f88adc22","code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2505.03335","arxiv_id_is_arxiv":true,"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":"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":"ec578739f88adc22","code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}},{"arxiv_id":"2504.16084","arxiv_id_is_arxiv":true,"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,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3f78ce44e20c50d1","code_sha256_prefix":"3f78ce44e20c50d1","mcp_get_code":{"code_sha256":"3f78ce44e20c50d1"}},{"arxiv_id":"2503.10460","arxiv_id_is_arxiv":true,"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":"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":"ec578739f88adc22","code_sha256_prefix":"ec578739f88adc22","mcp_get_code":{"code_sha256":"ec578739f88adc22"}}],"record_sha256":"f504a495c91d1b178526cd885963694d4ae0e36a9e76be6c9a3611e4c36891c5","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}