{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009305075,0.001226918,0.00126324,0.000549075,0.0004506218,0.001564431,0.001257768,0.002632275,0.004409299],"category_scores_gemma":[0.07619654,0.0006774027,0.0003972811,0.0003425402,0.001016222,0.001696431,0.0007931651,0.002642992,0.001214678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004717982,"about_ca_system_score_gemma":0.0004515038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003180253,"about_ca_topic_score_gemma":0.0004018528,"domain_scores_codex":[0.9939067,0.002861384,0.0006860627,0.0009551836,0.001285688,0.0003050408],"domain_scores_gemma":[0.9493904,0.03610625,0.004208998,0.007356117,0.001887507,0.001050735],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02412465,0.01332542,0.01233523,0.0009792018,0.0003825138,0.0002379136,0.001514756,0.01062409,0.7179256,0.006970295,0.001895737,0.2096847],"study_design_scores_gemma":[0.003873368,0.03783247,0.1166212,0.0003485775,0.0009620138,0.001201141,0.0005210012,0.2155902,0.578622,0.03820961,0.005697555,0.0005207543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9437193,0.0002027506,0.05108196,0.0003607468,0.0002925521,0.0007069519,0.0001390076,0.0006869341,0.002809835],"genre_scores_gemma":[0.9364477,0.0001912405,0.05765865,0.0006803292,0.0001189021,0.001090658,0.000249838,0.0004014976,0.003161156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9906949,"threshold_uncertainty_score":0.04921055,"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."}}