{"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/evaluate-metrics","entry":"evaluate_metrics","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":8,"n_papers_ran":3,"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":3,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":2,"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":"2602.07812","paper":"/paper/arxiv-2602-07812","title":"LLMs Know More About Numbers than They Can Say","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"VCY019/Numeracy-Probing","path":"src/train_probe_arxiv.py","file_url":"https://github.com/VCY019/Numeracy-Probing/blob/HEAD/src/train_probe_arxiv.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f510f6bdf42175af","mcp_get_code":{"code_sha256":"f510f6bdf42175af"}},{"arxiv_id":"2601.17823","paper":"/paper/arxiv-2601-17823","title":"DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"pkasela/DIETA-Machine-Translation","path":"src/evaluation_table.py","file_url":"https://github.com/pkasela/DIETA-Machine-Translation/blob/HEAD/src/evaluation_table.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f589eada15f29c5","mcp_get_code":{"code_sha256":"9f589eada15f29c5"}},{"arxiv_id":"2407.21633","paper":"/paper/2407-21633","title":"Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation","date":"2024-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"suntea233/DualLoRA","path":"evaluate.py","file_url":"https://github.com/suntea233/DualLoRA/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c60c1943203bd0e","mcp_get_code":{"code_sha256":"5c60c1943203bd0e"}},{"arxiv_id":"2304.00902","paper":"/paper/finalmlp-an-enhanced-two-stream-mlp-model-for-1","title":"FinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction","date":"2023-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reczoo/FuxiCTR","path":"model_zoo/FinalMLP/src/FinalMLP.py","file_url":"https://github.com/reczoo/FuxiCTR/blob/HEAD/model_zoo/FinalMLP/src/FinalMLP.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":"35e81e110e77d460","mcp_get_code":{"code_sha256":"35e81e110e77d460"}},{"arxiv_id":"2212.08570","paper":"/paper/audio-based-ai-classifiers-show-no-evidence","title":"Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers","date":"2022-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alan-turing-institute/turing-rss-health-data-lab-biomedical-acoustic-markers","path":"BNNBaseline/lib/evaluate.py","file_url":"https://github.com/alan-turing-institute/turing-rss-health-data-lab-biomedical-acoustic-markers/blob/HEAD/BNNBaseline/lib/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07b5a3d2cc0c0aa2","mcp_get_code":{"code_sha256":"07b5a3d2cc0c0aa2"}},{"arxiv_id":"2205.09626","paper":"/paper/bars-towards-open-benchmarking-for","title":"BARS: Towards Open Benchmarking for Recommender Systems","date":"2022-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openbenchmark/BARS","path":"matching/cf/EASE_R/src/utils.py","file_url":"https://github.com/openbenchmark/BARS/blob/HEAD/matching/cf/EASE_R/src/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":"d1bf42856841eb19","mcp_get_code":{"code_sha256":"d1bf42856841eb19"}},{"arxiv_id":"2205.09626","paper":"/paper/bars-towards-open-benchmarking-for","title":"BARS: Towards Open Benchmarking for Recommender Systems","date":"2022-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openbenchmark/BARS","path":"matching/item2item/ItemCF/ItemKNN_utils.py","file_url":"https://github.com/openbenchmark/BARS/blob/HEAD/matching/item2item/ItemCF/ItemKNN_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":"e752f6a871ca1c99","mcp_get_code":{"code_sha256":"e752f6a871ca1c99"}},{"arxiv_id":"1909.03496","paper":"/paper/devign-effective-vulnerability-identification","title":"Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks","date":"2019-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saikat107/Devign","path":"trainer.py","file_url":"https://github.com/saikat107/Devign/blob/HEAD/trainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7930b76c6c087f9f","mcp_get_code":{"code_sha256":"7930b76c6c087f9f"}},{"arxiv_id":"1902.08570","paper":"/paper/particlenet-jet-tagging-via-particle-clouds","title":"ParticleNet: Jet Tagging via Particle Clouds","date":"2019-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hqucms/weaver-core","path":"weaver/utils/nn/metrics.py","file_url":"https://github.com/hqucms/weaver-core/blob/HEAD/weaver/utils/nn/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6424b6b029d386f2","mcp_get_code":{"code_sha256":"6424b6b029d386f2"}}]}