{"id":"W4388290411","doi":"10.36487/acg_repo/2335_19","title":"The risk of confusing model calibration and model validation with model acceptance","year":2023,"lang":"en","type":"article","venue":"","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Calibration; Judgement; Computer science; Model validation; Set (abstract data type); Meaning (existential); Excuse; Management science; Data mining; Data science; Epistemology; Engineering; Mathematics; Statistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2337228,0.001716494,0.002863923,0.004036613,0.005433982,0.0114278,0.007508506,0.01279773,0.002908368],"category_scores_gemma":[0.4924826,0.001796608,0.002298381,0.003316047,0.05701841,0.03027834,0.02089086,0.02390576,0.001500394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00566595,"about_ca_system_score_gemma":0.008670381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003727178,"about_ca_topic_score_gemma":0.002358502,"domain_scores_codex":[0.6933014,0.2187139,0.01432217,0.01461208,0.05620861,0.002841796],"domain_scores_gemma":[0.4688093,0.3765991,0.03707104,0.07894613,0.03657217,0.002002198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001067837,0.0000327797,0.001212915,0.0005148736,0.00007602009,0.0002375083,0.01059151,0.003169414,0.0003880502,0.9543864,0.005224165,0.02405951],"study_design_scores_gemma":[0.00004707743,0.00007877596,0.0005065989,0.001243624,0.00003992576,0.0004665942,0.003060829,0.00769628,0.001378886,0.9478359,0.03749882,0.0001467719],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.02433828,0.005253443,0.7564446,0.1578332,0.003438891,0.0002203928,0.0001384413,0.0006053602,0.05172738],"genre_scores_gemma":[0.7661254,0.002210124,0.1841929,0.03734201,0.002340222,0.0009874196,0.0001371814,0.0007739245,0.005890742],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.2337228,"threshold_uncertainty_score":0.9449562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01203433451785662,"score_gpt":0.1972860776046166,"score_spread":0.1852517430867599,"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."}}