{"id":"W4412002212","doi":"10.1016/j.patter.2025.101317","title":"OpenML: Insights from 10 years and more than a thousand papers","year":2025,"lang":"en","type":"article","venue":"Patterns","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Leibniz-Gemeinschaft; HORIZON EUROPE Framework Programme; Tartu Ülikool; KU Leuven; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Technische Universiteit Eindhoven; Deutsche Forschungsgemeinschaft; Ludwig-Maximilians-Universität München; European Commission; Universiteit Leiden; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"History; Data science; Computer science","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","open_science"],"consensus_categories":[],"category_scores_codex":[0.02105771,0.001000938,0.0007333272,0.02230062,0.002515018,0.01847345,0.002414239,0.003073986,0.02297014],"category_scores_gemma":[0.1029382,0.000676427,0.001129505,0.02815397,0.003410957,0.02530397,0.007267011,0.003785315,0.01167238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004143339,"about_ca_system_score_gemma":0.006214395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003631134,"about_ca_topic_score_gemma":0.005666323,"domain_scores_codex":[0.986805,0.00401598,0.001263274,0.001252921,0.005964203,0.0006987068],"domain_scores_gemma":[0.8959025,0.07216126,0.006215661,0.005712181,0.01561565,0.004392786],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0001649551,0.00007441061,0.004492095,0.00325072,0.00013567,0.0005357414,0.004483077,0.001775912,0.001150934,0.2052631,0.5170614,0.2616119],"study_design_scores_gemma":[0.0000088886,0.00001071565,0.001188488,0.00109222,0.00002839414,0.0002151337,0.0007383456,0.0003881163,0.00035257,0.05303779,0.9429066,0.00003275978],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01684919,0.2633348,0.08247016,0.3769607,0.01888014,0.000209449,0.04090188,0.00857845,0.1918153],"genre_scores_gemma":[0.1942199,0.354504,0.140747,0.06673455,0.03115331,0.0008493074,0.1040435,0.01356933,0.09417917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9975858,"threshold_uncertainty_score":0.1113651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109027440840229,"score_gpt":0.2630513411137447,"score_spread":0.2521485970297218,"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."}}