{"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/color-2","entry":"color","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":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":9,"n_samples_ran":7,"n_samples_fingerprinted":2,"n_places":10,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":5,"unverified":2},"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":"2606.29493","paper":"/paper/arxiv-2606-29493","title":"Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"leanprover/lean4","path":"script/build_artifact.py","file_url":"https://github.com/leanprover/lean4/blob/HEAD/script/build_artifact.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":"6665056f19db0e93","mcp_get_code":{"code_sha256":"6665056f19db0e93"}},{"arxiv_id":"2605.23643","paper":"/paper/arxiv-2605-23643","title":"Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"niklasmedinger/Tamarin-ML-API","path":"regressionTests.py","file_url":"https://github.com/niklasmedinger/Tamarin-ML-API/blob/HEAD/regressionTests.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"85c53052d0602d48","mcp_get_code":{"code_sha256":"85c53052d0602d48"}},{"arxiv_id":"2402.15813","paper":"/paper/measuring-bargaining-abilities-of-llms-a","title":"Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianxiasjtu/amazonpricehistory","path":"utils/ColoredPrint.py","file_url":"https://github.com/tianxiasjtu/amazonpricehistory/blob/HEAD/utils/ColoredPrint.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":"8234f98afe94e24f","mcp_get_code":{"code_sha256":"8234f98afe94e24f"}},{"arxiv_id":"2107.06882","paper":"/paper/conservative-objective-models-for-effective","title":"Conservative Objective Models for Effective Offline Model-Based Optimization","date":"2021-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dhbrookes/CbAS","path":"src/optimization_algs.py","file_url":"https://github.com/dhbrookes/CbAS/blob/HEAD/src/optimization_algs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29e1a3bca6e404e7","mcp_get_code":{"code_sha256":"29e1a3bca6e404e7"}},{"arxiv_id":"2006.16241","paper":"/paper/the-many-faces-of-robustness-a-critical","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","date":"2020-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hendrycks/imagenet-r","path":"deepfashion_remix/augmix.py","file_url":"https://github.com/hendrycks/imagenet-r/blob/HEAD/deepfashion_remix/augmix.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f53b32f9516fdaa1","mcp_get_code":{"code_sha256":"f53b32f9516fdaa1"}},{"arxiv_id":"1909.13719","paper":"/paper/randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nachiket273/pytorch_resnet_rs","path":"model/randaugment.py","file_url":"https://github.com/nachiket273/pytorch_resnet_rs/blob/HEAD/model/randaugment.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f1efa6a7f09bf92","mcp_get_code":{"code_sha256":"5f1efa6a7f09bf92"}},{"arxiv_id":"1909.13719","paper":"/paper/randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyxxn0414/test-data-generation","path":"auto_augment.py","file_url":"https://github.com/lyxxn0414/test-data-generation/blob/HEAD/auto_augment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"747a0d64c7ffa9e5","mcp_get_code":{"code_sha256":"747a0d64c7ffa9e5"}},{"arxiv_id":"aaai_28539","paper":null,"title":"arXiv:aaai_28539","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pipixin321/HR-Pro","path":"log.py","file_url":"https://github.com/pipixin321/HR-Pro/blob/HEAD/log.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0abd0fd9d76a9db","mcp_get_code":{"code_sha256":"e0abd0fd9d76a9db"}},{"arxiv_id":"136960462","paper":null,"title":"arXiv:136960462","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"levymsn/CQA-CRCT","path":"CRCT/Interactive_demo.py","file_url":"https://github.com/levymsn/CQA-CRCT/blob/HEAD/CRCT/Interactive_demo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d801abdee9495f30","mcp_get_code":{"code_sha256":"d801abdee9495f30"}},{"arxiv_id":"136730727","paper":null,"title":"arXiv:136730727","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"louisYen/S3R","path":"anomaly/apis/utils.py","file_url":"https://github.com/louisYen/S3R/blob/HEAD/anomaly/apis/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0abd0fd9d76a9db","mcp_get_code":{"code_sha256":"e0abd0fd9d76a9db"}}]}