{"id":"W4383711346","doi":"10.3758/s13428-023-02158-6","title":"Reclassifying guesses to increase signal-to-noise ratio in psychological experiments","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Neural and Behavioral Psychology Studies","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Python (programming language); Computer science; Noise (video); MATLAB; Speech recognition; Variable (mathematics); Artificial intelligence; Psychology; Statistics; Data mining; Machine learning; Mathematics; Programming language","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":[],"category_scores_codex":[0.004302633,0.0002641889,0.0003889735,0.001152279,0.0004665185,0.0001254436,0.0008492998,0.0001472549,0.0003247174],"category_scores_gemma":[0.003010315,0.0002153634,0.00009009712,0.004565403,0.0003206667,0.0001877245,0.0008862414,0.0008020813,0.001401796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000120959,"about_ca_system_score_gemma":0.00003176731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000152924,"about_ca_topic_score_gemma":0.00001976177,"domain_scores_codex":[0.9920752,0.004038997,0.0004677299,0.001321737,0.000872015,0.001224319],"domain_scores_gemma":[0.9973487,0.001368717,0.00004100584,0.0006017687,0.0001208859,0.0005188695],"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":[0.0001816724,0.0005346311,0.009320207,0.000005041901,9.877067e-7,0.00067795,0.0004923975,0.000003210418,0.9142067,0.00003652124,0.006324163,0.06821653],"study_design_scores_gemma":[0.0005263279,0.0007761509,0.1462802,0.00004329639,0.000006000954,0.00002189155,0.0006247303,0.00001154518,0.8460779,0.0002879799,0.005016127,0.000327859],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940085,0.00002782052,0.0002238585,0.002241034,0.0004359604,0.001491039,0.00002101847,0.0002489258,0.001301883],"genre_scores_gemma":[0.980006,0.00005260498,0.01192148,0.0009755311,0.0001040328,0.002822382,0.000003919852,0.00004559357,0.004068404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.13696,"threshold_uncertainty_score":0.9993757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8334514151004707,"score_gpt":0.7131823945226864,"score_spread":0.1202690205777843,"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."}}