{"id":"W2907895817","doi":"10.1044/2018_ajslp-18-0048","title":"A Comment on Test Validation: The Importance of the Clinical Perspective","year":2019,"lang":"en","type":"article","venue":"American Journal of Speech-Language Pathology","topic":"Language Development and Disorders","field":"Psychology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Test (biology); Perspective (graphical); Conversation; Standardized test; Field (mathematics); Language assessment; Classical test theory; Psychology; Process (computing); Product (mathematics); Computer science; Applied psychology; Item response theory; Psychometrics; Artificial intelligence; Clinical psychology; Pedagogy; Mathematics education","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001254942,0.0001563867,0.0004501501,0.00008905475,0.00005490157,0.00001027307,0.0006298503,0.00006512421,0.001373574],"category_scores_gemma":[0.0005233776,0.00008273943,0.0002645644,0.0003462308,0.0006204927,0.00004040602,0.00008354206,0.000536336,0.0001185318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005637322,"about_ca_system_score_gemma":0.0001063246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006749772,"about_ca_topic_score_gemma":0.00001719621,"domain_scores_codex":[0.9979733,0.0005682479,0.000706926,0.0002174228,0.0002897481,0.0002443278],"domain_scores_gemma":[0.9968999,0.0009807235,0.001295079,0.0005824999,0.0001837526,0.00005806119],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000450444,0.0006677409,0.8983914,0.000005316038,0.0002690429,0.0005655444,0.04093663,0.000006188218,0.0006944797,0.005222788,0.01049226,0.04229814],"study_design_scores_gemma":[0.003450619,0.00462896,0.6421684,0.00007889178,0.0001654792,0.001751939,0.3372681,0.000003546806,0.001598801,0.00107595,0.007441801,0.0003675202],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624868,0.0004579104,0.00004211478,0.02251865,0.001029413,0.0002452234,0.00001022368,0.000008656083,0.01320099],"genre_scores_gemma":[0.9874561,0.00002665389,0.0006474296,0.01110301,0.000237871,0.000004466478,0.000001673921,0.00001821405,0.0005045425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2963315,"threshold_uncertainty_score":0.9995393,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01703427559076811,"score_gpt":0.3518846763740536,"score_spread":0.3348504007832855,"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."}}