{"id":"W3160121929","doi":"10.1109/saner50967.2021.00061","title":"MSR4ML: Reconstructing Artifact Traceability in Machine Learning Repositories","year":2021,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Traceability; Computer science; Artifact (error); Software engineering; Software versioning; Source code; Commit; Software evolution; Software development; Requirements traceability; Software; Process (computing); Database; Software construction; Programming language; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006056637,0.0000831297,0.0001270909,0.00007555976,0.0000727176,0.0001821266,0.0002875607,0.00004337219,0.00005981812],"category_scores_gemma":[0.003269196,0.00008294423,0.00003698827,0.0005016731,0.00002286395,0.0003433196,0.0002386427,0.0003947041,0.00001745874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008191641,"about_ca_system_score_gemma":0.00010186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001284039,"about_ca_topic_score_gemma":0.0001065769,"domain_scores_codex":[0.9987869,0.0001213723,0.0002183615,0.0003786236,0.0002243908,0.0002703341],"domain_scores_gemma":[0.9984447,0.0009519496,0.0000254133,0.0004288646,0.00008280071,0.00006620795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001599253,0.0000245765,0.9656747,0.00001608959,0.000005355324,0.0001290126,0.0005455333,0.001034006,0.001526717,0.001028186,0.00001527044,0.02999894],"study_design_scores_gemma":[0.0005962924,0.00008735686,0.4465925,0.00008158361,0.000002707724,0.0005889056,0.0003576907,0.4268305,0.1200239,0.002248823,0.002019624,0.0005701549],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.885639,0.0002022703,0.1109056,0.0005241645,0.0005009308,0.00006330501,1.692488e-7,0.0007508614,0.001413641],"genre_scores_gemma":[0.9133227,0.000003493256,0.08601144,0.000010921,0.0000343911,0.000005179977,8.245712e-7,0.000006435457,0.0006046316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5190822,"threshold_uncertainty_score":0.391377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01758268226082918,"score_gpt":0.2589639617290205,"score_spread":0.2413812794681914,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}