{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004391918,0.0001106573,0.0001921934,0.0002541449,0.0000644498,0.00007822727,0.0003102887,0.0002351544,0.0000124427],"category_scores_gemma":[0.0001259922,0.0001063715,0.00002887487,0.0005467067,0.00007488741,0.0005300109,0.0002231462,0.0006772563,0.00000328081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002428541,"about_ca_system_score_gemma":0.00008328235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002688266,"about_ca_topic_score_gemma":0.0000814478,"domain_scores_codex":[0.9988987,0.0001102327,0.0003118331,0.0003452742,0.0001645329,0.0001694693],"domain_scores_gemma":[0.999369,0.0000743675,0.00009973456,0.0002980891,0.0001097628,0.00004910944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003542693,0.0001018984,0.003883947,0.00005668614,0.000005286029,0.000004158698,0.000400927,0.0004679118,0.005274443,0.7985654,0.0004465153,0.1907573],"study_design_scores_gemma":[0.001824785,0.0007320076,0.05284534,0.001370361,0.00002784658,0.00002383289,0.000992141,0.4760894,0.002723549,0.4520131,0.01068883,0.0006688233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07546838,0.0009047374,0.8644241,0.01922869,0.0001029556,0.0003859026,0.00003664759,0.0004314024,0.03901718],"genre_scores_gemma":[0.9954319,0.0005284983,0.003628906,0.00008294258,0.0000114349,0.00001015885,0.00003079235,0.000003639879,0.0002716992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9199635,"threshold_uncertainty_score":0.4337704,"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."}}