{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004492093,0.00006550614,0.00007497274,0.00005292376,0.00005819488,0.0001578558,0.0003420628,0.00003241255,0.00003782749],"category_scores_gemma":[0.0000247971,0.00005778744,0.00001546154,0.0001007597,0.00001667551,0.0001409688,0.0001993355,0.00008184477,0.00003574621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007983836,"about_ca_system_score_gemma":0.00001819867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000519965,"about_ca_topic_score_gemma":0.0001322372,"domain_scores_codex":[0.9994279,0.00004443767,0.00008124913,0.0002726731,0.00008844246,0.00008533717],"domain_scores_gemma":[0.9994794,0.00005899195,0.00003059425,0.0003817257,0.00001173425,0.00003753813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001529062,0.00007628426,0.4757826,0.00003759312,0.00006098338,0.00003277983,0.004747795,0.00002068908,0.003416653,0.01911857,0.004314287,0.4923765],"study_design_scores_gemma":[0.0002036224,0.00001243363,0.9444973,0.00003396497,0.000005448127,7.69791e-7,0.00005898059,0.007234586,0.0001549065,0.0005733559,0.04714142,0.00008324181],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9265034,0.0003146323,0.06039748,0.003259759,0.0002314732,0.0001060874,0.00002139395,0.0001576259,0.009008207],"genre_scores_gemma":[0.997148,0.00003620692,0.001207058,0.0005256742,0.0000280416,0.000007123202,0.00003215967,0.000003545621,0.001012216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4922932,"threshold_uncertainty_score":0.2356503,"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."}}