{"id":"W3161452158","doi":"10.31234/osf.io/3s9du","title":"Reclassifying guesses to increase signal-to-noise ratio in psychological experiments","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Behavioral Health and Interventions","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Python (programming language); Computer science; MATLAB; Noise (video); Variable (mathematics); Speech recognition; Artificial intelligence; Statistics; Data mining; Machine learning; Mathematics","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":[0.03408262,0.002034327,0.002118933,0.001383316,0.0009295496,0.002656892,0.002225101,0.002728939,0.01088879],"category_scores_gemma":[0.2097691,0.001094849,0.001126697,0.0009945239,0.002287693,0.003322641,0.003052244,0.004288578,0.003636061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006841505,"about_ca_system_score_gemma":0.000869773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000308254,"about_ca_topic_score_gemma":0.000466987,"domain_scores_codex":[0.979826,0.01087911,0.00161361,0.003720735,0.003434861,0.0005256455],"domain_scores_gemma":[0.8613054,0.09582116,0.01061026,0.02520067,0.005823571,0.001238896],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01364871,0.004630943,0.02500019,0.003950492,0.001717914,0.0004262115,0.003505437,0.02514814,0.2570672,0.02302284,0.01523987,0.626642],"study_design_scores_gemma":[0.003916393,0.01310012,0.1718496,0.001203058,0.001738805,0.00194713,0.0007011082,0.2395308,0.3087741,0.2116072,0.04448362,0.001148104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2850994,0.001176437,0.6888842,0.001368852,0.0008540234,0.00323915,0.001652611,0.007975176,0.009750251],"genre_scores_gemma":[0.5239001,0.0004153184,0.4569468,0.001789066,0.0003091173,0.007502703,0.001395636,0.004003541,0.003737726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9659173,"threshold_uncertainty_score":0.1802483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2929489294595975,"score_gpt":0.5190782111567005,"score_spread":0.226129281697103,"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."}}