{"id":"W4415171628","doi":"10.2118/228102-ms","title":"Do We Really Need Hundreds of Machine Learning Models in Industry?","year":2025,"lang":"en","type":"article","venue":"SPE Annual Technical Conference and Exhibition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of British Columbia","funders":"","keywords":"Interpretability; Decision tree; Random forest; Tree (set theory); Structured prediction; Workflow; Field (mathematics); Incremental decision tree; Predictive modelling; Decision tree model","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":[0.007388406,0.001202004,0.001579147,0.001006495,0.0009918767,0.004896227,0.003307923,0.002033511,0.009583488],"category_scores_gemma":[0.02586112,0.0009071598,0.001371,0.002262235,0.00147154,0.01249972,0.002373085,0.005169555,0.005367317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001640334,"about_ca_system_score_gemma":0.002529107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006679964,"about_ca_topic_score_gemma":0.006801316,"domain_scores_codex":[0.9965874,0.001158437,0.0001491891,0.0006641806,0.001185709,0.0002549723],"domain_scores_gemma":[0.9883908,0.006127244,0.0006374817,0.002237843,0.001962356,0.0006443242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000880247,0.0005868647,0.02760344,0.0006315683,0.000453314,0.0004041042,0.0003909298,0.270303,0.00274364,0.08656932,0.07125738,0.5381762],"study_design_scores_gemma":[0.00006447226,0.0001512649,0.00263953,0.0002003346,0.00008664901,0.0001721795,0.0004185783,0.8472902,0.001769332,0.1125204,0.0346278,0.00005922635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.1417981,0.01233526,0.768862,0.04727454,0.001423718,0.000151242,0.001662818,0.006869578,0.0196228],"genre_scores_gemma":[0.6177155,0.004816869,0.3596912,0.004229422,0.0008775156,0.0002352257,0.003700918,0.001280893,0.007452499],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.009583488,"threshold_uncertainty_score":0.03907412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03477523702766216,"score_gpt":0.2915347933668858,"score_spread":0.2567595563392236,"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."}}