{"id":"W4396673092","doi":"10.1037/met0000645","title":"A deep learning method for comparing Bayesian hierarchical models.","year":2024,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"Deutsche Forschungsgemeinschaft; Google","keywords":"Computer science; Benchmark (surveying); Machine learning; Artificial intelligence; Inference; Bayesian inference; Model selection; Bayesian probability; Set (abstract data type); Hierarchical database model; Probabilistic logic; Code (set theory); Approximate Bayesian computation; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.01286695,0.001555223,0.00146211,0.004196425,0.001235974,0.002478777,0.004296372,0.002020248,0.01263508],"category_scores_gemma":[0.05882728,0.001111009,0.002501203,0.00295752,0.001906976,0.003474663,0.005247233,0.00554209,0.00156966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003025866,"about_ca_system_score_gemma":0.005234534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007566485,"about_ca_topic_score_gemma":0.01170012,"domain_scores_codex":[0.9941642,0.003411522,0.0003112772,0.0009412748,0.001015034,0.0001566734],"domain_scores_gemma":[0.9814196,0.01469986,0.001082599,0.001493859,0.0009192413,0.000385017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002547631,0.0001975395,0.005117612,0.0007203849,0.00108013,0.0001360279,0.0003595769,0.2498216,0.001521332,0.2989211,0.01776453,0.4241054],"study_design_scores_gemma":[0.00005201809,0.00004250771,0.0005669311,0.0001046472,0.00007225587,0.00007052897,0.00003463745,0.7180902,0.0007478817,0.275467,0.004724372,0.00002697966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001697578,0.0002087904,0.9958703,0.0001893421,0.00003274174,0.0001188713,0.000281074,0.0006552815,0.0009459358],"genre_scores_gemma":[0.08794475,0.0002840484,0.9070962,0.0003871363,0.00008666846,0.0009761917,0.001286945,0.0004455071,0.001492645],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01286695,"threshold_uncertainty_score":0.0680477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08995888785594917,"score_gpt":0.442734058898519,"score_spread":0.3527751710425698,"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."}}