{"id":"W4390265350","doi":"10.21449/ijate.1406304","title":"A dialectic on validity: Explanation-focused and the many ways of being human","year":2023,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; University of Cambridge","keywords":"Test (biology); External validity; Classical test theory; Test validity; Epistemology; Construct validity; Psychology; Variation (astronomy); Dialectic; Predictive validity; Cognitive psychology; Item response theory; Social psychology; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001158866,0.0000626771,0.0001897531,0.0003143366,0.00002910577,0.00004413916,0.0001230162,0.00004156926,0.00003273779],"category_scores_gemma":[0.009446448,0.00004354596,0.0000751999,0.0001649813,0.00005808002,0.0001033092,0.0000215451,0.0002544397,0.000002953209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001440149,"about_ca_system_score_gemma":0.00032052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003450434,"about_ca_topic_score_gemma":0.00000349484,"domain_scores_codex":[0.9987117,0.00008475195,0.0005052433,0.00008572622,0.0005383704,0.00007420889],"domain_scores_gemma":[0.9928461,0.006334102,0.0003460677,0.00008928182,0.0003445437,0.00003986158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001310435,0.00256377,0.5657342,0.00006549699,0.000550053,0.0001620465,0.003835668,0.0003262446,0.001714675,0.2195779,0.01956214,0.1845974],"study_design_scores_gemma":[0.004426183,0.0005188421,0.95576,0.001990515,0.00009262128,0.0000764872,0.0007222026,0.0005209153,0.0004822086,0.03468309,0.0006538078,0.00007309832],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573185,0.00001967547,0.000231523,0.03894414,0.0009536544,0.000140255,0.000001738872,0.000006872956,0.002383586],"genre_scores_gemma":[0.9971052,0.0001796507,0.0004955107,0.001589581,0.0005075996,0.00001370682,0.00002255016,0.000006725219,0.00007944468],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3900259,"threshold_uncertainty_score":0.9988974,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025470264963527,"score_gpt":0.4401993006598252,"score_spread":0.3376522741634725,"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."}}