{"id":"W3135039812","doi":"10.1007/s00184-021-00811-8","title":"Checking for model failure and for prior-data conflict with the constrained multinomial model","year":2021,"lang":"en","type":"article","venue":"Metrika","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education, India; Ministry of Education - Singapore; National Research Foundation Singapore; National Research Foundation","keywords":"Multinomial distribution; Consistency (knowledge bases); Inference; Mathematics; Econometrics; Multinomial probit; Multinomial logistic regression; Statistics; Computer science; Artificial intelligence; Discrete mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004962974,0.0001412425,0.0001898637,0.00004541945,0.0002463803,0.0002825799,0.0007518834,0.00006942696,7.690675e-7],"category_scores_gemma":[0.0001769967,0.00009711216,0.00004042252,0.0002070587,0.00007676912,0.0002717414,0.0002818705,0.000116825,4.982422e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001328159,"about_ca_system_score_gemma":0.0003358909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005679894,"about_ca_topic_score_gemma":0.00002863149,"domain_scores_codex":[0.9988697,0.00002167826,0.0001589903,0.0005270682,0.0001498663,0.0002727051],"domain_scores_gemma":[0.9985994,0.0002954371,0.00007247461,0.0007269533,0.0002312131,0.00007451295],"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":[0.0002780774,0.0002737777,0.0001404086,0.0003386084,0.0003625453,0.00001909573,0.005863228,0.2472308,0.01786557,0.4505039,0.01199774,0.2651262],"study_design_scores_gemma":[0.0009634867,0.0000503694,0.000004379625,0.0000180308,0.00002705229,0.00001420784,0.0000654118,0.993221,0.002226323,0.002037352,0.001216635,0.0001557825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006613346,0.0002394955,0.9891974,0.003291164,0.00003785342,0.0003511229,0.00009622916,0.00006435349,0.0001090673],"genre_scores_gemma":[0.5085928,0.000008233486,0.490629,0.0004359237,0.00003675615,0.0000386199,0.00001799168,0.000009362768,0.0002313722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7459902,"threshold_uncertainty_score":0.3960119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1326698199948023,"score_gpt":0.3224944355833813,"score_spread":0.1898246155885789,"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."}}