{"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/timeout","entry":"timeout","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":24,"n_papers_ran":16,"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":16,"n_samples_ran":10,"n_samples_fingerprinted":0,"n_places":24,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":7,"unverified":6},"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":"2605.31058","paper":"/paper/arxiv-2605-31058","title":"Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"icip-cas/ADR","path":"0_pipeline.py","file_url":"https://github.com/icip-cas/ADR/blob/HEAD/0_pipeline.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a1c03255bc6cedf4","mcp_get_code":{"code_sha256":"a1c03255bc6cedf4"}},{"arxiv_id":"2604.03993","paper":"/paper/arxiv-2604-03993","title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ShenzhiYang2000/OLR","path":"eval_scripts/generate_vllm.py","file_url":"https://github.com/ShenzhiYang2000/OLR/blob/HEAD/eval_scripts/generate_vllm.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":"885cc9ddb95422d6","mcp_get_code":{"code_sha256":"885cc9ddb95422d6"}},{"arxiv_id":"2602.07800","paper":"/paper/arxiv-2602-07800","title":"Approximating Matrix Functions with Deep Neural Networks and Transformers","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"rahul3/LAWT","path":"src/utils.py","file_url":"https://github.com/rahul3/LAWT/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e7b55aa114a5156a","mcp_get_code":{"code_sha256":"e7b55aa114a5156a"}},{"arxiv_id":"2505.21413","paper":null,"title":"arXiv:2505.21413","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"xxxiaol/RefTool","path":"code/inference/evaluator.py","file_url":"https://github.com/xxxiaol/RefTool/blob/HEAD/code/inference/evaluator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56d9e73f4137b105","mcp_get_code":{"code_sha256":"56d9e73f4137b105"}},{"arxiv_id":"2411.00566","paper":"/paper/patternboost-constructions-in-mathematics","title":"PatternBoost: Constructions in Mathematics with a Little Help from AI","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zawagner22/transformers_math_experiments","path":"utils.py","file_url":"https://github.com/zawagner22/transformers_math_experiments/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7b55aa114a5156a","mcp_get_code":{"code_sha256":"e7b55aa114a5156a"}},{"arxiv_id":"2410.01353","paper":"/paper/codev-bench-how-do-llms-understand-developer","title":"Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LingmaTongyi/Codev-Bench","path":"src/evaluate.py","file_url":"https://github.com/LingmaTongyi/Codev-Bench/blob/HEAD/src/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"565db4280f75804c","mcp_get_code":{"code_sha256":"565db4280f75804c"}},{"arxiv_id":"2408.12212","paper":"/paper/relational-decomposition-for-program","title":"Relational decomposition for program synthesis","date":"2024-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"celinehocquette/ijcai25-relational-decomposition","path":"popper/popper/util.py","file_url":"https://github.com/celinehocquette/ijcai25-relational-decomposition/blob/HEAD/popper/popper/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"829094d074a416ac","mcp_get_code":{"code_sha256":"829094d074a416ac"}},{"arxiv_id":"2406.12692","paper":"/paper/magic-generating-self-correction-guideline","title":"MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/synqo","path":"magic/multi_agent_feedback_generation.py","file_url":"https://github.com/microsoft/synqo/blob/HEAD/magic/multi_agent_feedback_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a3da427295e86ae","mcp_get_code":{"code_sha256":"9a3da427295e86ae"}},{"arxiv_id":"2406.00045","paper":"/paper/personalized-steering-of-large-language","title":"Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CaoYuanpu/BiPO","path":"evaluate.py","file_url":"https://github.com/CaoYuanpu/BiPO/blob/HEAD/evaluate.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":"b5bce4021c48e0c1","mcp_get_code":{"code_sha256":"b5bce4021c48e0c1"}},{"arxiv_id":"2404.11341","paper":"/paper/the-causal-chambers-real-physical-systems-as","title":"The Causal Chambers: Real Physical Systems as a Testbed for AI Methodology","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juangamella/causal-chamber-paper","path":"case_studies/src/symbolicregression/utils.py","file_url":"https://github.com/juangamella/causal-chamber-paper/blob/HEAD/case_studies/src/symbolicregression/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fe9d54ddd8520af","mcp_get_code":{"code_sha256":"2fe9d54ddd8520af"}},{"arxiv_id":"2403.01749","paper":"/paper/differentially-private-synthetic-data-via-1","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","date":"2024-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI-secure/aug-pe","path":"apis/utils.py","file_url":"https://github.com/AI-secure/aug-pe/blob/HEAD/apis/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0b978e0d687562ae","mcp_get_code":{"code_sha256":"0b978e0d687562ae"}},{"arxiv_id":"2402.04379","paper":"/paper/fine-tuned-language-models-generate-stable","title":"Fine-Tuned Language Models Generate Stable Inorganic Materials as Text","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/crystal-llm","path":"basic_eval.py","file_url":"https://github.com/facebookresearch/crystal-llm/blob/HEAD/basic_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"cf46a2fecbc874d2","mcp_get_code":{"code_sha256":"cf46a2fecbc874d2"}},{"arxiv_id":"2402.02101","paper":"/paper/are-large-language-models-good-prompt","title":"Are Large Language Models Good Prompt Optimizers?","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rtmaww/LLM_AutoPromptStudy","path":"LLM/thread_utils.py","file_url":"https://github.com/rtmaww/LLM_AutoPromptStudy/blob/HEAD/LLM/thread_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"132d00fe97f4c5c1","mcp_get_code":{"code_sha256":"132d00fe97f4c5c1"}},{"arxiv_id":"2401.16215","paper":"/paper/learning-big-logical-rules-by-joining-small","title":"Learning big logical rules by joining small rules","date":"2024-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"celinehocquette/ijcai24-joiner","path":"joiner/popper/util.py","file_url":"https://github.com/celinehocquette/ijcai24-joiner/blob/HEAD/joiner/popper/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"829094d074a416ac","mcp_get_code":{"code_sha256":"829094d074a416ac"}},{"arxiv_id":"2312.00027","paper":"/paper/stealthy-and-persistent-unalignment-on-large","title":"Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caoyuanpu/backdoorunalign","path":"auto_eval.py","file_url":"https://github.com/caoyuanpu/backdoorunalign/blob/HEAD/auto_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0b978e0d687562ae","mcp_get_code":{"code_sha256":"0b978e0d687562ae"}},{"arxiv_id":"2311.08803","paper":"/paper/strategyllm-large-language-models-as-strategy","title":"StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gao-xiao-bai/StrategyLLM","path":"source/model/base.py","file_url":"https://github.com/gao-xiao-bai/StrategyLLM/blob/HEAD/source/model/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf46a2fecbc874d2","mcp_get_code":{"code_sha256":"cf46a2fecbc874d2"}},{"arxiv_id":"2309.14681","paper":"/paper/are-human-generated-demonstrations-necessary","title":"Are Human-generated Demonstrations Necessary for In-context Learning?","date":"2023-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruili33/sec","path":"models/api_base.py","file_url":"https://github.com/ruili33/sec/blob/HEAD/models/api_base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39371ef75b2a42aa","mcp_get_code":{"code_sha256":"39371ef75b2a42aa"}},{"arxiv_id":"2308.09393","paper":"/paper/learning-mdl-logic-programs-from-noisy-data","title":"Learning MDL logic programs from noisy data","date":"2023-08-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"celinehocquette/aaai24-maxsynth","path":"maxsynth/popper/util.py","file_url":"https://github.com/celinehocquette/aaai24-maxsynth/blob/HEAD/maxsynth/popper/util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"829094d074a416ac","mcp_get_code":{"code_sha256":"829094d074a416ac"}},{"arxiv_id":"2301.13379","paper":"/paper/faithful-chain-of-thought-reasoning","title":"Faithful Chain-of-Thought Reasoning","date":"2023-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"veronica320/faithful-cot","path":"source/model/codex.py","file_url":"https://github.com/veronica320/faithful-cot/blob/HEAD/source/model/codex.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf46a2fecbc874d2","mcp_get_code":{"code_sha256":"cf46a2fecbc874d2"}},{"arxiv_id":"2207.03578","paper":"/paper/code-translation-with-compiler","title":"Code Translation with Compiler Representations","date":"2022-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/CodeGen","path":"codegen_sources/IR_tools/utils_ir.py","file_url":"https://github.com/facebookresearch/CodeGen/blob/HEAD/codegen_sources/IR_tools/utils_ir.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"781797e5f4a5b6ec","mcp_get_code":{"code_sha256":"781797e5f4a5b6ec"}},{"arxiv_id":"2110.03501","paper":"/paper/pretrained-language-models-are-symbolic","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","date":"2021-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"softsys4ai/differentiable-proving","path":"src/utils.py","file_url":"https://github.com/softsys4ai/differentiable-proving/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7b55aa114a5156a","mcp_get_code":{"code_sha256":"e7b55aa114a5156a"}},{"arxiv_id":"2107.03374","paper":"/paper/evaluating-large-language-models-trained-on","title":"Evaluating Large Language Models Trained on Code","date":"2021-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codedotal/gpt-code-clippy","path":"data_processing/download_license_info.py","file_url":"https://github.com/codedotal/gpt-code-clippy/blob/HEAD/data_processing/download_license_info.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":"2e22b41539e9cf87","mcp_get_code":{"code_sha256":"2e22b41539e9cf87"}},{"arxiv_id":"aaai_34511","paper":null,"title":"arXiv:aaai_34511","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/SynQo","path":"magic/multi_agent_feedback_generation.py","file_url":"https://github.com/microsoft/SynQo/blob/HEAD/magic/multi_agent_feedback_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a3da427295e86ae","mcp_get_code":{"code_sha256":"9a3da427295e86ae"}},{"arxiv_id":"2024.emnlp-main.481","paper":null,"title":"arXiv:2024.emnlp-main.481","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yangheng95/Rapid","path":"textattack/attacker.py","file_url":"https://github.com/yangheng95/Rapid/blob/HEAD/textattack/attacker.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee2aa0668f50e6a0","mcp_get_code":{"code_sha256":"ee2aa0668f50e6a0"}}]}