{"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/strip-string","entry":"strip_string","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":18,"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":10,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":18,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":7},"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":"5abed389274c4c03","mcp_get_code":{"code_sha256":"5abed389274c4c03"}},{"arxiv_id":"2604.13552","paper":"/paper/arxiv-2604-13552","title":"Training-Free Test-Time Contrastive Learning for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"KevinSCUTer/TF-TTCL","path":"core/source/compare/selection_kernel.py","file_url":"https://github.com/KevinSCUTer/TF-TTCL/blob/HEAD/core/source/compare/selection_kernel.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":"2e5a927ea1fd6fb2","mcp_get_code":{"code_sha256":"2e5a927ea1fd6fb2"}},{"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":"f41d597c152eab12","mcp_get_code":{"code_sha256":"f41d597c152eab12"}},{"arxiv_id":"2510.20342","paper":"/paper/arxiv-2510-20342","title":"Teaching Language Models to Reason with Tools","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"ChengpengLi1003/CoRT","path":"infer/parser.py","file_url":"https://github.com/ChengpengLi1003/CoRT/blob/HEAD/infer/parser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06b04cb075356fb9","mcp_get_code":{"code_sha256":"06b04cb075356fb9"}},{"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":"5abed389274c4c03","mcp_get_code":{"code_sha256":"5abed389274c4c03"}},{"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":"5abed389274c4c03","mcp_get_code":{"code_sha256":"5abed389274c4c03"}},{"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":"5abed389274c4c03","mcp_get_code":{"code_sha256":"5abed389274c4c03"}},{"arxiv_id":"2502.06781","paper":"/paper/exploring-the-limit-of-outcome-reward-for","title":"Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning","date":"2025-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"internlm/oreal","path":"oreal/judgers/utils.py","file_url":"https://github.com/internlm/oreal/blob/HEAD/oreal/judgers/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":"2b62ac820df81c34","mcp_get_code":{"code_sha256":"2b62ac820df81c34"}},{"arxiv_id":"2411.00784","paper":"/paper/fire-fact-checking-with-iterative-retrieval","title":"FIRE: Fact-checking with Iterative Retrieval and Verification","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mbzuai-nlp/fire","path":"common/utils.py","file_url":"https://github.com/mbzuai-nlp/fire/blob/HEAD/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ee0530df323c190","mcp_get_code":{"code_sha256":"0ee0530df323c190"}},{"arxiv_id":"2410.15700","paper":"/paper/internlm2-5-stepprover-advancing-automated","title":"InternLM2.5-StepProver: Advancing Automated Theorem Proving via Expert Iteration on Large-Scale LEAN Problems","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"internlm/internlm-math","path":"agent/math_agent.py","file_url":"https://github.com/internlm/internlm-math/blob/HEAD/agent/math_agent.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":"d80926644fbab50a","mcp_get_code":{"code_sha256":"d80926644fbab50a"}},{"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":"7f3eb00b0552d5c6","mcp_get_code":{"code_sha256":"7f3eb00b0552d5c6"}},{"arxiv_id":"2403.18802","paper":"/paper/long-form-factuality-in-large-language-models","title":"Long-form factuality in large language models","date":"2024-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/long-form-factuality","path":"common/utils.py","file_url":"https://github.com/google-deepmind/long-form-factuality/blob/HEAD/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0ee0530df323c190","mcp_get_code":{"code_sha256":"0ee0530df323c190"}},{"arxiv_id":"2402.06925","paper":"/paper/a-thorough-examination-of-decoding-methods-in","title":"A Thorough Examination of Decoding Methods in the Era of LLMs","date":"2024-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidfanzz/llm_decoding","path":"lm_eval/tasks/gsm8k.py","file_url":"https://github.com/davidfanzz/llm_decoding/blob/HEAD/lm_eval/tasks/gsm8k.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06b04cb075356fb9","mcp_get_code":{"code_sha256":"06b04cb075356fb9"}},{"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":"5abed389274c4c03","mcp_get_code":{"code_sha256":"5abed389274c4c03"}},{"arxiv_id":"2309.17452","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/tora","path":"src/utils/parser.py","file_url":"https://github.com/microsoft/tora/blob/HEAD/src/utils/parser.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06b04cb075356fb9","mcp_get_code":{"code_sha256":"06b04cb075356fb9"}},{"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_parser.py","file_url":"https://github.com/ZhijianZhou/Disppo/blob/HEAD/recipe/disppo/eval_parser.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":"22ce21919d4279f6","mcp_get_code":{"code_sha256":"22ce21919d4279f6"}},{"arxiv_id":"openreview_QrC8OgQyOI","paper":null,"title":"arXiv:openreview_QrC8OgQyOI","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"viiika/Prism","path":"Dream/Dream_Prism/metrics/gsmk8_eval.py","file_url":"https://github.com/viiika/Prism/blob/HEAD/Dream/Dream_Prism/metrics/gsmk8_eval.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":"7ce155f35572f664","mcp_get_code":{"code_sha256":"7ce155f35572f664"}},{"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":"5abed389274c4c03","mcp_get_code":{"code_sha256":"5abed389274c4c03"}}]}