{"id":"W6906630872","doi":"10.17605/osf.io/ekdu5","title":"BADE Evidence Integration Task","year":2022,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Task (project management); Empirical evidence; Perception; Task analysis","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002364142,0.0002508616,0.0002712321,0.000130555,0.0007963362,0.0000756271,0.001313628,0.00006955906,0.3211224],"category_scores_gemma":[0.004399091,0.000249132,0.0001604442,0.000443106,0.0002932119,0.0003971524,0.002458861,0.0007278337,0.4403851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000198285,"about_ca_system_score_gemma":0.00005056114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008516085,"about_ca_topic_score_gemma":0.00001685405,"domain_scores_codex":[0.9949857,0.001403763,0.0004237786,0.002219632,0.0005470947,0.0004200171],"domain_scores_gemma":[0.9968007,0.0009017773,0.0002044226,0.001920356,0.00004968512,0.0001231058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002055965,0.0003398467,0.006916652,0.00001064582,0.000009020713,0.00007887333,0.001082866,0.0001931874,0.9350896,0.0005495584,0.03276099,0.0227632],"study_design_scores_gemma":[0.0007726559,0.00001506824,0.03450431,0.00007082403,0.00009121971,0.0005342667,0.0007369476,0.0002975193,0.8021474,0.00815565,0.1518122,0.000861962],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7887001,0.000003018275,0.0002618889,0.003140295,0.001058964,0.0007565358,0.00002339804,0.0002561419,0.2057997],"genre_scores_gemma":[0.850475,0.00007007585,0.0001101329,0.001297271,0.00004773363,0.0004276414,0.000002802312,0.00002081649,0.1475485],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1329422,"threshold_uncertainty_score":0.9999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1192817472766218,"score_gpt":0.3602321954521719,"score_spread":0.2409504481755501,"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."}}