{"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-boxed-answers","entry":"extract_boxed_answers","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":9,"n_papers_ran":8,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":1},"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":"2605.10195","paper":"/paper/arxiv-2605-10195","title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"PKU-SEC-Lab/SPEX","path":"evaluate/data_processing/answer_extraction.py","file_url":"https://github.com/PKU-SEC-Lab/SPEX/blob/HEAD/evaluate/data_processing/answer_extraction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2506.20512","paper":"/paper/octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/octothinker","path":"eval/data_processing/answer_extraction.py","file_url":"https://github.com/gair-nlp/octothinker/blob/HEAD/eval/data_processing/answer_extraction.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":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2505.00662","paper":"/paper/deepcritic-deliberate-critique-with-large","title":"DeepCritic: Deliberate Critique with Large Language Models","date":"2025-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucbm/deepcritic","path":"Critique_Generation/gen_in_depth_critique.py","file_url":"https://github.com/rucbm/deepcritic/blob/HEAD/Critique_Generation/gen_in_depth_critique.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15ffa726dbd74ce2","mcp_get_code":{"code_sha256":"15ffa726dbd74ce2"}},{"arxiv_id":"2502.20122","paper":"/paper/self-training-elicits-concise-reasoning-in","title":"Self-Training Elicits Concise Reasoning in Large Language Models","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tergelmunkhbat/concise-reasoning","path":"src/math_parser.py","file_url":"https://github.com/tergelmunkhbat/concise-reasoning/blob/HEAD/src/math_parser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2502.13834","paper":"/paper/proving-olympiad-inequalities-by-synergizing","title":"Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lizn-zn/NeqLIPS","path":"LIPS/NeSyCore/parser.py","file_url":"https://github.com/Lizn-zn/NeqLIPS/blob/HEAD/LIPS/NeSyCore/parser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2502.12067","paper":"/paper/tokenskip-controllable-chain-of-thought","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hemingkx/TokenSkip","path":"data_processing/answer_extraction.py","file_url":"https://github.com/hemingkx/TokenSkip/blob/HEAD/data_processing/answer_extraction.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":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2406.18629","paper":"/paper/step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/step-dpo","path":"evaluation/data_processing/answer_extraction.py","file_url":"https://github.com/dvlab-research/step-dpo/blob/HEAD/evaluation/data_processing/answer_extraction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2402.03300","paper":"/paper/deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepseek-ai/deepseek-math","path":"evaluation/data_processing/answer_extraction.py","file_url":"https://github.com/deepseek-ai/deepseek-math/blob/HEAD/evaluation/data_processing/answer_extraction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}},{"arxiv_id":"2025.acl-long.1506","paper":null,"title":"arXiv:2025.acl-long.1506","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"deepseek-ai/DeepSeek-Math","path":"evaluation/data_processing/answer_extraction.py","file_url":"https://github.com/deepseek-ai/DeepSeek-Math/blob/HEAD/evaluation/data_processing/answer_extraction.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6390dea763ce122e","mcp_get_code":{"code_sha256":"6390dea763ce122e"}}]}