{"id":"W1989941651","doi":"10.1080/14999013.2011.629716","title":"When “Good Enough” Is Just Not Good Enough: Response to Holden and Marjanovic","year":2011,"lang":"en","type":"article","venue":"International Journal of Forensic Mental Health","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Test (biology); Psychology; Construct (python library); Mental health; Applied psychology; Psychotherapist; Computer science","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":[0.01000843,0.0001816229,0.0004591362,0.001049722,0.0001602774,0.0001612846,0.001126529,0.00006572853,0.0006574731],"category_scores_gemma":[0.007253619,0.0001327515,0.0001508098,0.0004862222,0.00009850944,0.0003803355,0.0003024224,0.0002738977,0.00006555952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002599246,"about_ca_system_score_gemma":0.0002643103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000224046,"about_ca_topic_score_gemma":0.00003218376,"domain_scores_codex":[0.995073,0.0005881341,0.001407452,0.0003652395,0.002210939,0.0003551965],"domain_scores_gemma":[0.9936905,0.003726654,0.001169879,0.0002867737,0.0006742176,0.0004519996],"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":[0.006249024,0.0003710983,0.03492976,0.00001508659,0.0002429556,0.0001874848,0.02684119,0.000004357222,0.00132262,0.003405583,0.1054038,0.821027],"study_design_scores_gemma":[0.005966188,0.006832761,0.6472384,0.0006344229,0.00003720671,0.004383555,0.01425856,0.0002077113,0.008364039,0.04809584,0.2632839,0.0006974091],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9349647,0.0005673215,0.003267339,0.0523647,0.004588399,0.0002448644,0.0001160956,0.00001729257,0.003869251],"genre_scores_gemma":[0.911409,0.0001397739,0.07942459,0.007070869,0.0003666132,0.000002001181,0.000001820939,0.00001511287,0.001570173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8203296,"threshold_uncertainty_score":0.8683783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4722078879498454,"score_gpt":0.4885562271526259,"score_spread":0.0163483392027805,"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."}}