{"id":"W2952654638","doi":"10.3390/ecea-5-06682","title":"The Measurement of Statistical Evidence as the Basis for Statistical Reasoning","year":2019,"lang":"en","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistical analysis; Computer science; Basis (linear algebra); Statistical evidence; Statistical theory; Resolution (logic); Statistical hypothesis testing; Statistical model; Artificial intelligence; Econometrics; Management science; Mathematics; Statistics; Engineering","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":[0.001878652,0.00009108002,0.0001219563,0.00001286499,0.0001730535,0.0001589012,0.0008494216,0.00002896005,0.00004779557],"category_scores_gemma":[0.001387788,0.00004545401,0.00003710905,0.0001038737,0.00009287634,0.0001291311,0.0001330498,0.0001052235,0.00006885297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003459931,"about_ca_system_score_gemma":0.0002283182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001009791,"about_ca_topic_score_gemma":0.00002061875,"domain_scores_codex":[0.9985499,0.00009925738,0.0002472576,0.0002603474,0.0005882036,0.0002550816],"domain_scores_gemma":[0.9963298,0.002689588,0.00006586883,0.0005569315,0.0002934666,0.0000643416],"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":[0.00002690575,0.00001184805,0.00006548779,0.00001332129,0.0000121767,3.568004e-7,0.0001362405,0.00008137069,0.0002573562,0.9675558,0.001546646,0.03029249],"study_design_scores_gemma":[0.0001733422,0.0004230162,0.002041754,0.0001842411,0.00002190458,0.000006410735,0.0001467819,0.8983331,0.002353405,0.09401519,0.002122523,0.0001783234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001060676,0.0001546743,0.9944257,0.001998698,0.0001806736,0.0002618621,0.000005331762,0.00003352583,0.001878859],"genre_scores_gemma":[0.8723472,0.00002612554,0.1270823,0.0003062724,0.00001827436,0.00002987839,3.231337e-7,0.000004664958,0.0001849723],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8982517,"threshold_uncertainty_score":0.1853561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06668844460231006,"score_gpt":0.317563460310756,"score_spread":0.2508750157084459,"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."}}