{"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-python-code","entry":"extract_python_code","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":17,"n_papers_ran":9,"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":21,"n_samples_ran":9,"n_samples_fingerprinted":9,"n_places":21,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":6,"unverified":12},"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":"2607.08690","paper":"/paper/arxiv-2607-08690","title":"A Practical Investigation of Training-free Relaxed Speculative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"graphcore-research/relaxed-spec-dec-repro","path":"src/ens_spec_dec/tasks/_code.py","file_url":"https://github.com/graphcore-research/relaxed-spec-dec-repro/blob/HEAD/src/ens_spec_dec/tasks/_code.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a4c84d086f4d57e8","mcp_get_code":{"code_sha256":"a4c84d086f4d57e8"}},{"arxiv_id":"2606.26327","paper":"/paper/arxiv-2606-26327","title":"EVOM: Agentic Meta-Evolution of Actor-Critic Architectures for Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"xiaofangxd/EVOM","path":"evom.py","file_url":"https://github.com/xiaofangxd/EVOM/blob/HEAD/evom.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e56c2f976486e74","mcp_get_code":{"code_sha256":"6e56c2f976486e74"}},{"arxiv_id":"2606.09278","paper":"/paper/arxiv-2606-09278","title":"Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Huawei-AI4Math/PyGeoX","path":"model_testing/PyGeoX-Wild/image.py","file_url":"https://github.com/Huawei-AI4Math/PyGeoX/blob/HEAD/model_testing/PyGeoX-Wild/image.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9b5bac7fe4d7d84","mcp_get_code":{"code_sha256":"a9b5bac7fe4d7d84"}},{"arxiv_id":"2606.09278","paper":"/paper/arxiv-2606-09278","title":"Internalizing Geometric Law: Learning from Solver Residuals for Precision-Critical Generation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Huawei-AI4Math/PyGeoX","path":"model_testing/PyGeoX-Wild/generate.py","file_url":"https://github.com/Huawei-AI4Math/PyGeoX/blob/HEAD/model_testing/PyGeoX-Wild/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10b22e52ac7138d8","mcp_get_code":{"code_sha256":"10b22e52ac7138d8"}},{"arxiv_id":"2606.05859","paper":"/paper/arxiv-2606-05859","title":"TARPO: Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"NKU-LITI/TARPO-master","path":"eval_tharp_humaneval_avg.py","file_url":"https://github.com/NKU-LITI/TARPO-master/blob/HEAD/eval_tharp_humaneval_avg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6cad710a9cef59bc","mcp_get_code":{"code_sha256":"6cad710a9cef59bc"}},{"arxiv_id":"2605.30052","paper":"/paper/arxiv-2605-30052","title":"REPOT: Recoverable Program-of-Thought via Checkpoint Repair *","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"parsa-mz/RePot","path":"repot/agents/repot/agent.py","file_url":"https://github.com/parsa-mz/RePot/blob/HEAD/repot/agents/repot/agent.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,"code_sha256_prefix":"c75f985348c28391","mcp_get_code":{"code_sha256":"c75f985348c28391"}},{"arxiv_id":"2604.25847","paper":"/paper/arxiv-2604-25847","title":"From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"CHIANGEL/Agora-Opt","path":"code/Agora-Opt/src/debate_memory/generate_with_memory.py","file_url":"https://github.com/CHIANGEL/Agora-Opt/blob/HEAD/code/Agora-Opt/src/debate_memory/generate_with_memory.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d68281fa7da95c0","mcp_get_code":{"code_sha256":"0d68281fa7da95c0"}},{"arxiv_id":"2604.22239","paper":"/paper/arxiv-2604-22239","title":"Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Zhanli-Li/MuDABench","path":"agent/agent_runner.py","file_url":"https://github.com/Zhanli-Li/MuDABench/blob/HEAD/agent/agent_runner.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":"41d7561067299007","mcp_get_code":{"code_sha256":"41d7561067299007"}},{"arxiv_id":"2512.14681","paper":"/paper/arxiv-2512-14681","title":"Fast and Accurate Causal Parallel Decoding using Jacobi Forcing FAST AND ACCURATE CAUSAL PARALLEL DECODING USING JACOBI FORCING","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"hao-ai-lab/JacobiForcing","path":"JacobiForcing/ar_inference_baseline.py","file_url":"https://github.com/hao-ai-lab/JacobiForcing/blob/HEAD/JacobiForcing/ar_inference_baseline.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":"f650a566b3a44b39","mcp_get_code":{"code_sha256":"f650a566b3a44b39"}},{"arxiv_id":"2512.14681","paper":"/paper/arxiv-2512-14681","title":"Fast and Accurate Causal Parallel Decoding using Jacobi Forcing FAST AND ACCURATE CAUSAL PARALLEL DECODING USING JACOBI FORCING","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"hao-ai-lab/JacobiForcing","path":"JacobiForcing/jacobi_forcing_inference_MR_humaneval.py","file_url":"https://github.com/hao-ai-lab/JacobiForcing/blob/HEAD/JacobiForcing/jacobi_forcing_inference_MR_humaneval.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":"f30e3943ccb923f5","mcp_get_code":{"code_sha256":"f30e3943ccb923f5"}},{"arxiv_id":"2512.14681","paper":"/paper/arxiv-2512-14681","title":"Fast and Accurate Causal Parallel Decoding using Jacobi Forcing FAST AND ACCURATE CAUSAL PARALLEL DECODING USING JACOBI FORCING","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"hao-ai-lab/JacobiForcing","path":"JacobiForcing/jacobi_forcing_inference_MR_humaneval_config_grid_search.py","file_url":"https://github.com/hao-ai-lab/JacobiForcing/blob/HEAD/JacobiForcing/jacobi_forcing_inference_MR_humaneval_config_grid_search.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":"935fb30ac04be7c7","mcp_get_code":{"code_sha256":"935fb30ac04be7c7"}},{"arxiv_id":"2507.13266","paper":"/paper/questa-expanding-reasoning-capacity-in-llms","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","date":"2025-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"foreverlasting1202/QuestA","path":"AReaL/evaluation/code_eval.py","file_url":"https://github.com/foreverlasting1202/QuestA/blob/HEAD/AReaL/evaluation/code_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"446ea191616b9ed9","mcp_get_code":{"code_sha256":"446ea191616b9ed9"}},{"arxiv_id":"2506.13841","paper":"/paper/locationreasoner-evaluating-llms-on-real","title":"LocationReasoner: Evaluating LLMs on Real-World Site Selection Reasoning","date":"2025-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"miho-koda/LocationReasoner","path":"code/core/router.py","file_url":"https://github.com/miho-koda/LocationReasoner/blob/HEAD/code/core/router.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"474e1d327bf447c9","mcp_get_code":{"code_sha256":"474e1d327bf447c9"}},{"arxiv_id":"2505.07215","paper":"/paper/measuring-general-intelligence-with-generated","title":"Measuring General Intelligence with Generated Games","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vivek3141/gg-bench","path":"gg_bench/utils/markdown.py","file_url":"https://github.com/vivek3141/gg-bench/blob/HEAD/gg_bench/utils/markdown.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5555027230c54cd2","mcp_get_code":{"code_sha256":"5555027230c54cd2"}},{"arxiv_id":"2410.08068","paper":"/paper/teaching-inspired-integrated-prompting","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sallytan13/teaching-inspired-prompting","path":"tip_prompt/utils/calcu_python_util.py","file_url":"https://github.com/sallytan13/teaching-inspired-prompting/blob/HEAD/tip_prompt/utils/calcu_python_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c5837fd82df0bd2","mcp_get_code":{"code_sha256":"8c5837fd82df0bd2"}},{"arxiv_id":"2406.12036","paper":"/paper/medcalc-bench-evaluating-large-language","title":"MedCalc-Bench: Evaluating Large Language Models for Medical Calculations","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ncbi-nlp/medcalc-bench","path":"evaluation/generate_code_prompt.py","file_url":"https://github.com/ncbi-nlp/medcalc-bench/blob/HEAD/evaluation/generate_code_prompt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd634356035bea9f","mcp_get_code":{"code_sha256":"dd634356035bea9f"}},{"arxiv_id":"2403.05307","paper":"/paper/tapilot-crossing-benchmarking-and-evolving","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","date":"2024-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tapilot-crossing/tapilot_code","path":"postprocessing/combine_code_gen_COT.py","file_url":"https://github.com/tapilot-crossing/tapilot_code/blob/HEAD/postprocessing/combine_code_gen_COT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7289a9d629da016d","mcp_get_code":{"code_sha256":"7289a9d629da016d"}},{"arxiv_id":"2401.14196","paper":"/paper/deepseek-coder-when-the-large-language-model","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepseek-ai/DeepSeek-Coder","path":"Evaluation/LeetCode/evaluate_leetcode.py","file_url":"https://github.com/deepseek-ai/DeepSeek-Coder/blob/HEAD/Evaluation/LeetCode/evaluate_leetcode.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2508ea408193905","mcp_get_code":{"code_sha256":"f2508ea408193905"}},{"arxiv_id":"2306.17582","paper":"/paper/chatgpt-for-robotics-design-principles-and","title":"ChatGPT for Robotics: Design Principles and Model Abilities","date":"2023-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/promptcraft-robotics","path":"chatgpt_airsim/chatgpt_airsim.py","file_url":"https://github.com/microsoft/promptcraft-robotics/blob/HEAD/chatgpt_airsim/chatgpt_airsim.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"706579426a241b5e","mcp_get_code":{"code_sha256":"706579426a241b5e"}},{"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/humaneval_eval.py","file_url":"https://github.com/viiika/Prism/blob/HEAD/Dream/Dream_Prism/metrics/humaneval_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":"a8c290638876d80f","mcp_get_code":{"code_sha256":"a8c290638876d80f"}},{"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/mbpp_eval.py","file_url":"https://github.com/viiika/Prism/blob/HEAD/Dream/Dream_Prism/metrics/mbpp_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":"0277fc79c30ff9ce","mcp_get_code":{"code_sha256":"0277fc79c30ff9ce"}}]}