{"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/parse-digits","entry":"parse_digits","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":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":21,"n_places_pointer_only":6,"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":"2604.11056","paper":"/paper/arxiv-2604-11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"QwenLM/Qwen2.5-Math","path":"evaluation/grader.py","file_url":"https://github.com/QwenLM/Qwen2.5-Math/blob/HEAD/evaluation/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2604.08281","paper":"/paper/arxiv-2604-08281","title":"When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"00Dreamer00/ATTC","path":"grader.py","file_url":"https://github.com/00Dreamer00/ATTC/blob/HEAD/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2603.20215","paper":"/paper/arxiv-2603-20215","title":"Multi-Agent Debate with Memory Masking","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"tmlr-group/MAD-MM","path":"src/evaluator.py","file_url":"https://github.com/tmlr-group/MAD-MM/blob/HEAD/src/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5983f446aa569e81","mcp_get_code":{"code_sha256":"5983f446aa569e81"}},{"arxiv_id":"2601.09233","paper":"/paper/arxiv-2601-09233","title":"GIFT: Reconciling Post-Training Objectives via Finite-Temperature Gibbs Initialization","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zzy1127/GIFT","path":"utils/polymath/scripts.py","file_url":"https://github.com/zzy1127/GIFT/blob/HEAD/utils/polymath/scripts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2601.03895","paper":"/paper/arxiv-2601-03895","title":"All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"chi2liu/ABC-GRPO","path":"eval_math/grader.py","file_url":"https://github.com/chi2liu/ABC-GRPO/blob/HEAD/eval_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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2601.03895","paper":"/paper/arxiv-2601-03895","title":"All-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"chi2liu/ABC-GRPO","path":"eval_math/grader_improved.py","file_url":"https://github.com/chi2liu/ABC-GRPO/blob/HEAD/eval_math/grader_improved.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":"919681ac6d877afe","mcp_get_code":{"code_sha256":"919681ac6d877afe"}},{"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/qwen_verify.py","file_url":"https://github.com/zhangyx1122/TokenSqueeze/blob/HEAD/utils/qwen_verify.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2508.13037","paper":"/paper/arxiv-2508-13037","title":"Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"Xinhe-Li/LoRID","path":"src/evaluation/grader.py","file_url":"https://github.com/Xinhe-Li/LoRID/blob/HEAD/src/evaluation/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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"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/grader.py","file_url":"https://github.com/lwl-cpu/question-free-fine-tuning/blob/HEAD/eval/utils/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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2505.19716","paper":"/paper/concise-reasoning-big-gains-pruning-long","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evanwu1125/litecot","path":"eval/Qwen2.5-Math/evaluation/grader.py","file_url":"https://github.com/evanwu1125/litecot/blob/HEAD/eval/Qwen2.5-Math/evaluation/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"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/grader.py","file_url":"https://github.com/thu-coai/lrm-safety-study/blob/HEAD/reasoning_evaluation/utils/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2505.13308","paper":"/paper/seek-in-the-dark-reasoning-via-test-time","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-nlco/latentseek","path":"src/extract_judge_answer/grader.py","file_url":"https://github.com/bigai-nlco/latentseek/blob/HEAD/src/extract_judge_answer/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2504.20571","paper":"/paper/reinforcement-learning-for-reasoning-in-large","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","date":"2025-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ypwang61/one-shot-rlvr","path":"Qwen2.5-Eval/evaluation/grader.py","file_url":"https://github.com/ypwang61/one-shot-rlvr/blob/HEAD/Qwen2.5-Eval/evaluation/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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2504.05185","paper":"/paper/concise-reasoning-via-reinforcement-learning","title":"Concise Reasoning via Reinforcement Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai-wand/concise-reasoning","path":"eval/grader.py","file_url":"https://github.com/ai-wand/concise-reasoning/blob/HEAD/eval/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2503.16212","paper":"/paper/mathfusion-enhancing-mathematic-problem","title":"MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion","date":"2025-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qizhipei/mathfusion","path":"evaluation/dart_math/grader.py","file_url":"https://github.com/qizhipei/mathfusion/blob/HEAD/evaluation/dart_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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2502.12215","paper":"/paper/revisiting-the-test-time-scaling-of-o1-like","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhiYuanZeng/test-time-scaling-eval","path":"qwen_math_evaluator.py","file_url":"https://github.com/ZhiYuanZeng/test-time-scaling-eval/blob/HEAD/qwen_math_evaluator.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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2502.06773","paper":"/paper/on-the-emergence-of-thinking-in-llms-i","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","date":"2025-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GuanghaoYe/Emergence-of-Thinking","path":"evaluation/grader.py","file_url":"https://github.com/GuanghaoYe/Emergence-of-Thinking/blob/HEAD/evaluation/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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2502.06703","paper":"/paper/can-1b-llm-surpass-405b-llm-rethinking","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","date":"2025-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RyanLiu112/compute-optimal-tts","path":"src/envs/MATH/grader.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2410.07985","paper":"/paper/omni-math-a-universal-olympiad-level","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kbsdjames/omni-math-rule","path":"evaluation/grader.py","file_url":"https://github.com/kbsdjames/omni-math-rule/blob/HEAD/evaluation/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"2405.14365","paper":"/paper/jiuzhang3-0-efficiently-improving","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/jiuzhang3.0","path":"eval/grader.py","file_url":"https://github.com/rucaibox/jiuzhang3.0/blob/HEAD/eval/grader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"arxiv_id":"openreview_Tkdgg5uqNK","paper":null,"title":"arXiv:openreview_Tkdgg5uqNK","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ZhijianZhou/Disppo","path":"recipe/disppo/eval_grader.py","file_url":"https://github.com/ZhijianZhou/Disppo/blob/HEAD/recipe/disppo/eval_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":"7d4b7f8c3875b126","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}}]}