{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002377119,0.0002632616,0.0004170022,0.0001733064,0.0002197671,0.0006251152,0.001174395,0.0002041287,0.00004895133],"category_scores_gemma":[0.0003233664,0.0001953556,0.0002348426,0.0007786271,0.00007362712,0.0004408649,0.0002685986,0.0007369673,0.00002466254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003182672,"about_ca_system_score_gemma":0.00002243966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003569832,"about_ca_topic_score_gemma":7.308252e-7,"domain_scores_codex":[0.9969469,0.0007239996,0.000408981,0.001106391,0.0002148502,0.0005988649],"domain_scores_gemma":[0.9975765,0.001606526,0.00006170766,0.0004531837,0.00006323421,0.0002387929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001102332,0.00004064712,0.00001281338,0.00005186434,0.00001559843,0.00001346707,0.0002508333,0.0007594669,0.0002921904,0.4190356,0.00008014984,0.5794363],"study_design_scores_gemma":[0.0001142457,0.000164009,0.0001325649,0.0000309946,0.000008525096,0.00005944508,0.00000926978,0.5809283,0.00008881919,0.4128537,0.005439194,0.0001710176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000495608,0.00114559,0.9793535,0.002092398,0.0006835188,0.0002409468,6.587106e-7,0.0008241333,0.01560964],"genre_scores_gemma":[0.142149,0.0000380593,0.8568806,0.0004533019,0.0001453043,0.0001249868,0.000002126634,0.00001901711,0.000187648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5801688,"threshold_uncertainty_score":0.7966369,"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."}}