{"id":"W4412989613","doi":"10.56952/arma-2025-0602","title":"Modeling with Confidence: Leveraging Conformal Prediction for Calibrated Machine Learning Based Mechanical and Petrophysical Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Conformal map; Computer science; Machine learning; Artificial intelligence; Petrophysics; Engineering; Mathematics; Geotechnical engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001938931,0.0001402989,0.0001778612,0.0001051734,0.00009100708,0.00006375767,0.00005420038,0.00007281038,0.000007559764],"category_scores_gemma":[0.00002897257,0.0001205609,0.00003174329,0.0001420852,0.00001170485,0.0002302179,0.00001333459,0.0002076879,2.421398e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002808145,"about_ca_system_score_gemma":0.00002466098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002422484,"about_ca_topic_score_gemma":0.000001851938,"domain_scores_codex":[0.9993244,0.00002266055,0.000191386,0.0001631893,0.0001084896,0.0001898483],"domain_scores_gemma":[0.999638,0.000130911,0.00000916612,0.00009797536,0.00006174708,0.00006225373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005100847,0.000004242835,0.00002737355,0.00009542947,0.00002876766,4.928061e-7,0.00002943202,0.9902678,0.001247292,0.007958874,0.000006537973,0.0002827441],"study_design_scores_gemma":[0.001079358,0.00005200755,0.000008136641,0.0000557824,0.00002206284,0.000001149908,0.00003600478,0.9954298,0.002219875,0.0009108355,0.00006099067,0.0001240301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1190827,0.00005033229,0.8797023,0.00004045817,0.00007445436,0.0001543601,0.000004131305,0.0005081008,0.0003832663],"genre_scores_gemma":[0.9344422,0.000009527806,0.06530527,0.00002491081,0.0000232231,0.0000299504,0.00002491419,0.00002243572,0.0001175206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8153596,"threshold_uncertainty_score":0.491633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01813628010830434,"score_gpt":0.2418509514697384,"score_spread":0.223714671361434,"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."}}