{"id":"W4382362073","doi":"10.1145/3589806.3600039","title":"Integrated Reproducibility with Self-describing Machine Learning Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Java; Machine learning; Modular design; Process (computing); Artificial intelligence; License; MIT License; Documentation; Software engineering; Human–computer interaction; Data science; Programming language; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04671803,0.00135618,0.001604654,0.002359835,0.002225678,0.009173596,0.006615058,0.002156264,0.005330451],"category_scores_gemma":[0.1462688,0.002044098,0.003249166,0.00198482,0.004629602,0.01318376,0.01587974,0.005807007,0.003787927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002303536,"about_ca_system_score_gemma":0.007191741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003813016,"about_ca_topic_score_gemma":0.003560927,"domain_scores_codex":[0.9718736,0.009778915,0.003558549,0.004630983,0.009197008,0.0009609279],"domain_scores_gemma":[0.8275301,0.03868129,0.005817178,0.1138337,0.01171352,0.002424299],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002456838,0.0009887828,0.03982407,0.001671368,0.0007551179,0.001805814,0.008607828,0.09489734,0.02475054,0.2858793,0.08606592,0.4522972],"study_design_scores_gemma":[0.0003208293,0.0002767072,0.00321089,0.0005606799,0.0002343712,0.0008045635,0.0003615088,0.4053573,0.06190149,0.3177432,0.2087357,0.0004928607],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008978066,0.0002266239,0.8684497,0.00096034,0.0002946737,0.0003714547,0.001553977,0.11544,0.003725262],"genre_scores_gemma":[0.2185752,0.0005035874,0.7092788,0.00138939,0.0004560747,0.00129664,0.01193145,0.0477444,0.008824489],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9532819,"threshold_uncertainty_score":0.2470715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3395261948733915,"score_gpt":0.3580994167655376,"score_spread":0.01857322189214611,"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."}}