{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003445824,0.00187309,0.002463496,0.00540327,0.001475694,0.002535656,0.005533554,0.00397424,0.009851424],"category_scores_gemma":[0.009507593,0.001241706,0.002898265,0.00419667,0.0005384742,0.004951215,0.002653274,0.003677667,0.00554977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001857956,"about_ca_system_score_gemma":0.002292982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01941623,"about_ca_topic_score_gemma":0.0545252,"domain_scores_codex":[0.99751,0.0008982907,0.0001637941,0.0005721439,0.0006658861,0.0001899333],"domain_scores_gemma":[0.9955226,0.001884939,0.0001715713,0.001437786,0.0007555774,0.000227454],"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":[0.0008917004,0.001267118,0.004177625,0.0004292667,0.001064325,0.0001996252,0.000169772,0.064877,0.004853669,0.00916436,0.07829347,0.834612],"study_design_scores_gemma":[0.00009670985,0.0001272109,0.0003682096,0.00005914286,0.0001396838,0.00008372845,0.00005035543,0.965185,0.003070705,0.0210711,0.00968974,0.00005848076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00624589,0.001354646,0.9649647,0.0007620111,0.0002539748,0.0002511837,0.003180495,0.02114958,0.001837502],"genre_scores_gemma":[0.09754743,0.0004806827,0.8858719,0.000832793,0.0002156434,0.0003525627,0.006372467,0.0009503468,0.007376244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01941623,"threshold_uncertainty_score":0.03860641,"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."}}