{"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/execute-code","entry":"execute_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":14,"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":14,"n_samples_ran":7,"n_samples_fingerprinted":2,"n_places":15,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":6,"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":"2609.02387","paper":"/paper/arxiv-2609-02387","title":"Semantics-Guided Automatic Tensorization for Multiobjective Evolutionary Algorithms: A Multi-Agent Framework","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"EMI-Group/evococo","path":"backend/executor.py","file_url":"https://github.com/EMI-Group/evococo/blob/HEAD/backend/executor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"11506b23f1290cfb","mcp_get_code":{"code_sha256":"11506b23f1290cfb"}},{"arxiv_id":"2607.19847","paper":"/paper/arxiv-2607-19847","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"lyrain2001/auto-fill","path":"inference/run_specialists.py","file_url":"https://github.com/lyrain2001/auto-fill/blob/HEAD/inference/run_specialists.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":"c21b4338fc97b984","mcp_get_code":{"code_sha256":"c21b4338fc97b984"}},{"arxiv_id":"2606.00761","paper":"/paper/arxiv-2606-00761","title":"Confidence-Adaptive SwiGLU for Mixture-of-Experts","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"karpathy/nanochat","path":"nanochat/execution.py","file_url":"https://github.com/karpathy/nanochat/blob/HEAD/nanochat/execution.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d2839629a84c9ed","mcp_get_code":{"code_sha256":"3d2839629a84c9ed"}},{"arxiv_id":"2605.26414","paper":"/paper/arxiv-2605-26414","title":"Reasoning, Code, or Both? How Large Language Models Handle Variations in Math Questions","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"masamodelkin/llm-robustness-code-execution","path":"src/evals/PAL.py","file_url":"https://github.com/masamodelkin/llm-robustness-code-execution/blob/HEAD/src/evals/PAL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0e689a905260a24","mcp_get_code":{"code_sha256":"e0e689a905260a24"}},{"arxiv_id":"2605.17842","paper":"/paper/arxiv-2605-17842","title":"SNLP: Layer-Parallel Inference via Structured Newton Corrections","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"phymhan/nanochat-snlp","path":"nanochat/execution.py","file_url":"https://github.com/phymhan/nanochat-snlp/blob/HEAD/nanochat/execution.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"686a4f93a88bb3d2","mcp_get_code":{"code_sha256":"686a4f93a88bb3d2"}},{"arxiv_id":"2605.00632","paper":"/paper/arxiv-2605-00632","title":"BlenderRAG: High-Fidelity 3D Object Generation via Retrieval-Augmented Code Synthesis","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"MaxRondelli/BlenderRAG","path":"utils.py","file_url":"https://github.com/MaxRondelli/BlenderRAG/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6eadc8c73f4b7acc","mcp_get_code":{"code_sha256":"6eadc8c73f4b7acc"}},{"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/execute.py","file_url":"https://github.com/CHIANGEL/Agora-Opt/blob/HEAD/code/Agora-Opt/src/debate_memory/execute.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e6aced355e6f72e7","mcp_get_code":{"code_sha256":"e6aced355e6f72e7"}},{"arxiv_id":"2602.02522","paper":"/paper/arxiv-2602-02522","title":"IMU-1: Sample-Efficient Pre-training of Small Language Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"thepowerfuldeez/sample_efficient_gpt","path":"sample_efficient_gpt/evals/execution.py","file_url":"https://github.com/thepowerfuldeez/sample_efficient_gpt/blob/HEAD/sample_efficient_gpt/evals/execution.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"686a4f93a88bb3d2","mcp_get_code":{"code_sha256":"686a4f93a88bb3d2"}},{"arxiv_id":"2504.00906","paper":"/paper/agent-s2-a-compositional-generalist","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","date":"2025-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simular-ai/agent-s","path":"gui_agents/s3/agents/code_agent.py","file_url":"https://github.com/simular-ai/agent-s/blob/HEAD/gui_agents/s3/agents/code_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":"80e0cd7f0c4f74bf","mcp_get_code":{"code_sha256":"80e0cd7f0c4f74bf"}},{"arxiv_id":"2503.18102","paper":"/paper/agentrxiv-towards-collaborative-autonomous","title":"AgentRxiv: Towards Collaborative Autonomous Research","date":"2025-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samuelschmidgall/agentlaboratory","path":"tools.py","file_url":"https://github.com/samuelschmidgall/agentlaboratory/blob/HEAD/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c8118a3cbe9a20a","mcp_get_code":{"code_sha256":"7c8118a3cbe9a20a"}},{"arxiv_id":"2502.19328","paper":"/paper/agentic-reward-modeling-integrating-human","title":"Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems","date":"2025-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-keg/agentic-reward-modeling","path":"reward_agent/agent.py","file_url":"https://github.com/thu-keg/agentic-reward-modeling/blob/HEAD/reward_agent/agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"652a84fac4a5d223","mcp_get_code":{"code_sha256":"652a84fac4a5d223"}},{"arxiv_id":"2501.04227","paper":"/paper/agent-laboratory-using-llm-agents-as-research","title":"Agent Laboratory: Using LLM Agents as Research Assistants","date":"2025-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Masao-Taketani/LocalAgentLaboratory","path":"tools.py","file_url":"https://github.com/Masao-Taketani/LocalAgentLaboratory/blob/HEAD/tools.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f6ad073cc70700d","mcp_get_code":{"code_sha256":"9f6ad073cc70700d"}},{"arxiv_id":"2410.08196","paper":"/paper/mathcoder2-better-math-reasoning-from","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mathllm/mathcoder2","path":"data_processing/mathematical_code/extract_to_blocks.py","file_url":"https://github.com/mathllm/mathcoder2/blob/HEAD/data_processing/mathematical_code/extract_to_blocks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b6ef8d618b02a5bb","mcp_get_code":{"code_sha256":"b6ef8d618b02a5bb"}},{"arxiv_id":"2407.19633","paper":"/paper/optimus-0-3-using-large-language-models-to","title":"OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale","date":"2024-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teshnizi/optimus","path":"Reflexion.py","file_url":"https://github.com/teshnizi/optimus/blob/HEAD/Reflexion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a6804b25b53643a","mcp_get_code":{"code_sha256":"0a6804b25b53643a"}},{"arxiv_id":"2407.19633","paper":"/paper/optimus-0-3-using-large-language-models-to","title":"OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale","date":"2024-07-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teshnizi/optimus","path":"execute_code.py","file_url":"https://github.com/teshnizi/optimus/blob/HEAD/execute_code.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dab23c4f1db56c16","mcp_get_code":{"code_sha256":"dab23c4f1db56c16"}}]}