{"id":"W4362735211","doi":"10.1080/1091367x.2023.2199126","title":"Trust the “Process”? When Fundamental Motor Skill Scores are Reliably Unreliable","year":2023,"lang":"en","type":"article","venue":"Measurement in Physical Education and Exercise Science","topic":"Children's Physical and Motor Development","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Gross motor skill; Motor skill; Reliability (semiconductor); Inter-rater reliability; Internal consistency; Physical medicine and rehabilitation; Applied psychology; Physical therapy; Clinical psychology; Psychometrics; Rating scale; Developmental psychology; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0007518015,0.0001775375,0.000198902,0.0001713064,0.0003866037,0.0001257348,0.0004378669,0.00003092385,0.00010333],"category_scores_gemma":[0.0001123745,0.000122975,0.0000479515,0.001192744,0.000443432,0.0002269497,0.0001010585,0.0001810081,0.0003234137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000168685,"about_ca_system_score_gemma":0.0003618748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002156203,"about_ca_topic_score_gemma":0.00001400125,"domain_scores_codex":[0.9977813,0.00003646732,0.0002157506,0.0005754667,0.000924274,0.0004667349],"domain_scores_gemma":[0.9991695,0.00004166774,0.00008626186,0.0003408569,0.0001788658,0.000182818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005726956,0.01510078,0.1736801,0.000348416,0.00008151347,0.0000106246,0.1914793,0.0001933348,0.02833283,0.0243709,0.1453706,0.4204589],"study_design_scores_gemma":[0.0004970504,0.00007880218,0.9670676,0.0002983306,0.00001860893,0.000001358391,0.008924759,0.000305946,0.001469721,0.01662642,0.004431463,0.000279967],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915584,0.0001474275,0.000003953866,0.002081391,0.001461984,0.0005195329,0.00000543125,0.00007179693,0.004150022],"genre_scores_gemma":[0.9968009,0.00003111535,0.00003404147,0.0004990808,0.0001910488,0.0003452816,0.000005575536,0.00001221037,0.00208077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7933874,"threshold_uncertainty_score":0.5014777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02853696743147281,"score_gpt":0.310054374542902,"score_spread":0.2815174071114291,"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."}}