{"id":"W4393385387","doi":"10.31219/osf.io/wzqxg","title":"Bayesian estimation in multiple comparisons","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Bayesian probability; Estimation; Computer science; Bayes estimator; Artificial intelligence; Econometrics; Statistics; Machine learning; Mathematics; Economics","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006041273,0.0002240011,0.0004369474,0.0004643261,0.00005613951,0.0006684497,0.0009338856,0.000222844,0.001281871],"category_scores_gemma":[0.002487882,0.0001547108,0.0001938363,0.0004867962,0.00006474676,0.00006880838,0.001365541,0.0007975267,0.002095551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001748616,"about_ca_system_score_gemma":0.000160144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000449989,"about_ca_topic_score_gemma":0.002007557,"domain_scores_codex":[0.9953755,0.0002775116,0.001177964,0.0009206063,0.002014092,0.0002343176],"domain_scores_gemma":[0.9976648,0.0008886389,0.0001718688,0.001031635,0.000158274,0.00008478944],"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":[0.00003662264,0.000532301,0.1156058,0.0002333052,0.00005339045,0.00002233095,0.001384004,0.5221007,0.0001116817,0.006092341,0.2612796,0.09254793],"study_design_scores_gemma":[0.0001098022,0.00001232542,0.01085695,0.0001454202,0.000008970434,3.546402e-7,0.0002628164,0.6707475,0.0001144472,0.3123533,0.00522304,0.0001650035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2193493,0.0009624514,0.6240661,0.02210134,0.006880249,0.002581829,0.00008081187,0.0003652168,0.1236128],"genre_scores_gemma":[0.9767734,0.000008635821,0.020727,0.0001364329,0.00004933626,0.00006765537,0.00001596419,0.000009236308,0.002212344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7574241,"threshold_uncertainty_score":0.9996311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2554361265663144,"score_gpt":0.4161703013996847,"score_spread":0.1607341748333703,"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."}}