{"id":"W2965597477","doi":"10.15530/urtec-2019-396","title":"Why Most Models Fail: The Importance of Blind Validation","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 7th Unconventional Resources Technology Conference","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Encana (Canada)","funders":"","keywords":"Computer science","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":[0.001245366,0.0001375853,0.0002642921,0.0002998564,0.0001593773,0.00007700485,0.002281864,0.0001748142,0.0003508085],"category_scores_gemma":[0.0008203773,0.00007913574,0.0001457164,0.001779053,0.0005935651,0.000301903,0.0004676894,0.0002431983,0.00001979169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002331981,"about_ca_system_score_gemma":0.00006795012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001567012,"about_ca_topic_score_gemma":0.000005687241,"domain_scores_codex":[0.9975696,0.00001625604,0.0007947625,0.0003985309,0.00105073,0.0001701829],"domain_scores_gemma":[0.9961609,0.0003278916,0.001167091,0.0005082638,0.001807952,0.00002784972],"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":[0.00004293128,0.00005761801,0.1401699,0.00001837684,0.00002785291,3.682601e-8,0.0002423295,0.0004179806,0.01138321,0.8424991,0.00298387,0.002156824],"study_design_scores_gemma":[0.0003346375,0.00005948908,0.004264937,0.00006745113,0.00002075235,0.000006091042,0.001557233,0.01078383,0.04688276,0.9190789,0.01682818,0.0001157365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9771293,0.00007013504,0.002184261,0.01052008,0.00005687029,0.0006154779,0.00001967235,0.00007135009,0.009332842],"genre_scores_gemma":[0.9972681,0.00001073644,0.000750496,0.0002144888,0.00001498051,0.00005936628,0.000002020777,0.000008915355,0.001670924],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.135905,"threshold_uncertainty_score":0.424031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07921849459820626,"score_gpt":0.3407682537686444,"score_spread":0.2615497591704381,"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."}}