{"id":"W4416408141","doi":"10.1007/s10994-025-06909-8","title":"MetaML: a multi-label meta-learning approach for pipeline recommendation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Pipeline (software); Preprocessor; Computational complexity theory; Pipeline transport; Sequence (biology); Code (set theory); Bayesian probability; Source code","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002250416,0.0003210758,0.0004903365,0.0004069797,0.0006910565,0.0003724866,0.0008065423,0.0001241818,0.00005783068],"category_scores_gemma":[0.001542373,0.0002819894,0.0002191836,0.0008396214,0.00003114923,0.0005353925,0.0003551219,0.000827545,0.00002986919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006277131,"about_ca_system_score_gemma":0.00006251733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001286352,"about_ca_topic_score_gemma":0.00001616411,"domain_scores_codex":[0.9973027,0.0006714744,0.0005181031,0.0008665505,0.0002103264,0.0004309012],"domain_scores_gemma":[0.9984279,0.0004571608,0.0003375231,0.0005144343,0.0001719422,0.00009104997],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006062655,0.0004530047,0.004539682,0.0001701593,0.0007799713,0.000001362609,0.0005243914,0.02986499,0.001784706,0.03133148,0.002885309,0.9276043],"study_design_scores_gemma":[0.001007333,0.00006554124,0.0002846127,0.000007442314,0.0002722139,0.000003106634,0.00002665133,0.7922732,0.0001524433,0.0001367268,0.2055537,0.0002170732],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000131003,0.0008814244,0.986982,0.004151196,0.0001996083,0.000417564,0.000007138065,0.0007792556,0.006450842],"genre_scores_gemma":[0.1346643,0.00007291636,0.8380377,0.0008018644,0.00009740574,0.0002783648,0.001283911,0.00004391369,0.02471959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9273872,"threshold_uncertainty_score":0.9999632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07266868996257791,"score_gpt":0.3308045038421709,"score_spread":0.2581358138795929,"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."}}