{"id":"W2057483415","doi":"10.1080/14999013.2011.627087","title":"Reaching for the Brass Ring of Psychometric Test Standards: Commenting on Slaney, Storey, and Barnes","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":"Queen's University","funders":"","keywords":"Test (biology); Psychology; Field (mathematics); Test theory; Applied psychology; Computer science; Psychometrics; Clinical psychology; Mathematics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01319474,0.0001113902,0.0003363371,0.0008459426,0.0002086491,0.00008483326,0.0007533751,0.00002975357,0.00004181778],"category_scores_gemma":[0.0245197,0.00006406678,0.0001325549,0.0004947738,0.0001035675,0.0001864982,0.0001058476,0.0002111472,6.189288e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001632597,"about_ca_system_score_gemma":0.00009090656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001359946,"about_ca_topic_score_gemma":0.00002363516,"domain_scores_codex":[0.9965639,0.0001883375,0.001148073,0.0001820442,0.001717483,0.0002001416],"domain_scores_gemma":[0.9798294,0.01737596,0.001783052,0.0001740207,0.0007287206,0.0001088295],"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":[0.0003463986,0.0001244652,0.1243654,0.0000142544,0.00009731791,0.000002657884,0.002075627,0.00001103233,0.00007650573,0.001736066,0.006473184,0.8646771],"study_design_scores_gemma":[0.00734469,0.006842373,0.8581089,0.001500685,0.00005485025,0.0009446237,0.01606123,0.00427737,0.002896184,0.06600976,0.03552109,0.0004382059],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9333411,0.002609876,0.04711745,0.006695713,0.006315489,0.0004207737,0.0002477561,0.00001288404,0.00323896],"genre_scores_gemma":[0.9710934,0.0002780218,0.02778807,0.0005697344,0.0002261387,0.000001594868,0.00000141411,0.000008482984,0.00003319348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8642389,"threshold_uncertainty_score":0.9836972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4356372626067284,"score_gpt":0.5015778292471855,"score_spread":0.06594056664045717,"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."}}