{"id":"W4308866009","doi":"10.3390/vision6040065","title":"Musical Novices Are Unable to Judge Musical Quality from Brief Video Clips: A Failed Replication of Tsay (2014)","year":2022,"lang":"en","type":"article","venue":"Vision","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"Office of Defense Programs; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Defense","keywords":"Musical; Replication (statistics); Quality (philosophy); Psychology; Cognitive psychology; Computer science; Visual arts","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001062114,0.0001573531,0.0002759774,0.0001592333,0.0004336987,0.0000729875,0.0005858868,0.00005921577,0.000903395],"category_scores_gemma":[0.001533445,0.0001487346,0.0001046628,0.0008082893,0.0001242942,0.0003666525,0.0005829624,0.0002538682,0.0001628354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009943576,"about_ca_system_score_gemma":0.00006169303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006248524,"about_ca_topic_score_gemma":0.00006113962,"domain_scores_codex":[0.9961717,0.0004623451,0.0004817954,0.001648333,0.0009333654,0.0003024844],"domain_scores_gemma":[0.9976737,0.0003234467,0.0002857774,0.001496808,0.0000568664,0.0001633522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001450599,0.0003283932,0.0004086997,0.00001004375,6.622874e-7,0.000006479262,0.0006768137,0.00009071936,0.9789549,0.0004526452,0.007809801,0.01111577],"study_design_scores_gemma":[0.001239331,0.001368284,0.6226854,0.00005946732,0.00002474096,0.00001151471,0.0009425927,0.003688472,0.2225341,0.001715931,0.1451559,0.0005742331],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951994,0.000003731369,0.0007758941,0.001990984,0.0006222961,0.000421462,0.0001437096,0.0001131269,0.000729436],"genre_scores_gemma":[0.9926311,0.000007467755,0.0001809297,0.0066613,0.0001437124,0.00007852251,0.00001874116,0.00001762458,0.0002605413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7564209,"threshold_uncertainty_score":0.9891542,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05938127848475169,"score_gpt":0.3531853783222646,"score_spread":0.2938040998375129,"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."}}