{"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/normalize-final-answer","entry":"normalize_final_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":20,"n_papers_ran":6,"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":8,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":20,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":1,"unverified":4},"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":"2607.11506","paper":"/paper/arxiv-2607-11506","title":"SCOPE-RL: Optimizing Reasoning Paths Before and After Success","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"tokencraft-lab/SCOPE-RL","path":"verl/recipe/scope_rl/reward_score/step_quality.py","file_url":"https://github.com/tokencraft-lab/SCOPE-RL/blob/HEAD/verl/recipe/scope_rl/reward_score/step_quality.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"996c6d7cf3a99d1e","mcp_get_code":{"code_sha256":"996c6d7cf3a99d1e"}},{"arxiv_id":"2605.26971","paper":"/paper/arxiv-2605-26971","title":"RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Celine-hxy/ATLAS","path":"verl/verl/utils/reward_score/math_dapo.py","file_url":"https://github.com/Celine-hxy/ATLAS/blob/HEAD/verl/verl/utils/reward_score/math_dapo.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":"45fce0ce6cf82699","mcp_get_code":{"code_sha256":"45fce0ce6cf82699"}},{"arxiv_id":"2604.11048","paper":"/paper/arxiv-2604-11048","title":"A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"cjia7/DPR","path":"src/npti/eval/eval_math.py","file_url":"https://github.com/cjia7/DPR/blob/HEAD/src/npti/eval/eval_math.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4f5267c667058423","mcp_get_code":{"code_sha256":"4f5267c667058423"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"arxiv_id":"2602.22296","paper":"/paper/arxiv-2602-22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dshah02/upskill","path":"src/DAPO_math_dapo.py","file_url":"https://github.com/dshah02/upskill/blob/HEAD/src/DAPO_math_dapo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8eed3cb436fe2a3","mcp_get_code":{"code_sha256":"f8eed3cb436fe2a3"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"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":"aime24/utils.py","file_url":"https://github.com/sheriyuo/ETS/blob/HEAD/aime24/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8eed3cb436fe2a3","mcp_get_code":{"code_sha256":"f8eed3cb436fe2a3"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"arxiv_id":"2511.13223","paper":"/paper/arxiv-2511-13223","title":"TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"zhangyx1122/TokenSqueeze","path":"utils/orz_verify.py","file_url":"https://github.com/zhangyx1122/TokenSqueeze/blob/HEAD/utils/orz_verify.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"arxiv_id":"2506.12860","paper":"/paper/qfft-question-free-fine-tuning-for-adaptive","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","date":"2025-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lwl-cpu/question-free-fine-tuning","path":"eval/utils/math_normalization.py","file_url":"https://github.com/lwl-cpu/question-free-fine-tuning/blob/HEAD/eval/utils/math_normalization.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":"31ee6b861ee71ef7","mcp_get_code":{"code_sha256":"31ee6b861ee71ef7"}},{"arxiv_id":"2505.15404","paper":"/paper/how-should-we-enhance-the-safety-of-large","title":"How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/lrm-safety-study","path":"reasoning_evaluation/utils/math_normalization.py","file_url":"https://github.com/thu-coai/lrm-safety-study/blob/HEAD/reasoning_evaluation/utils/math_normalization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31ee6b861ee71ef7","mcp_get_code":{"code_sha256":"31ee6b861ee71ef7"}},{"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":"5662e5ee755b541c","mcp_get_code":{"code_sha256":"5662e5ee755b541c"}},{"arxiv_id":"2503.02324","paper":"/paper/promptcot-synthesizing-olympiad-level","title":"PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models","date":"2025-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaoxlpku/promptcot","path":"eval/math_equivalence.py","file_url":"https://github.com/zhaoxlpku/promptcot/blob/HEAD/eval/math_equivalence.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2046955201af63e6","mcp_get_code":{"code_sha256":"2046955201af63e6"}},{"arxiv_id":"2502.07154","paper":"/paper/rethinking-fine-tuning-when-scaling-test-time","title":"Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning","date":"2025-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allanraventos/refine","path":"refine/training/filter_samples.py","file_url":"https://github.com/allanraventos/refine/blob/HEAD/refine/training/filter_samples.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8464320e407bc6cd","mcp_get_code":{"code_sha256":"8464320e407bc6cd"}},{"arxiv_id":"2407.13647","paper":"/paper/weak-to-strong-reasoning","title":"Weak-to-Strong Reasoning","date":"2024-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/weak-to-strong-reasoning","path":"src/eval/math_normalization.py","file_url":"https://github.com/gair-nlp/weak-to-strong-reasoning/blob/HEAD/src/eval/math_normalization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"31ee6b861ee71ef7","mcp_get_code":{"code_sha256":"31ee6b861ee71ef7"}}]}