{"id":"W2001638213","doi":"10.1177/0013164406288162","title":"Automated Simultaneous Assembly of Multistage Testlets for a High-Stakes Licensing Examination","year":2007,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Spreadsheets and End-User Computing","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computerized adaptive testing; Test (biology); Computer science; Certification; Constraint (computer-aided design); Integer programming; Test Management Approach; Extension (predicate logic); Algorithm; Operations research; Reliability engineering; Programming language; Mathematics; Psychometrics; Statistics; Engineering","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":[0.001158842,0.000108798,0.0001272377,0.00007430822,0.0001211822,0.00005215779,0.0001959646,0.00005771184,0.000008745345],"category_scores_gemma":[0.0004700294,0.00008791478,0.00003044456,0.0001671957,0.00003557825,0.00008587533,0.0000293339,0.00005841211,0.000002920056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005150589,"about_ca_system_score_gemma":0.00002607517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001970924,"about_ca_topic_score_gemma":0.000006441043,"domain_scores_codex":[0.9987816,0.00004251807,0.0002877475,0.0003234576,0.00035415,0.0002105746],"domain_scores_gemma":[0.9986047,0.0006473583,0.0001260856,0.000166775,0.0003724105,0.00008262964],"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":[0.0001187462,0.004706159,0.003602074,0.0001614964,0.0001034333,0.00001412356,0.003379116,0.0009204707,0.1062426,0.1122843,0.003043066,0.7654244],"study_design_scores_gemma":[0.001100494,0.00087282,0.9326656,0.0001279464,0.0000162159,0.00003697553,0.0001150149,0.05339807,0.005796565,0.003865038,0.001640243,0.0003649816],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7088875,0.000191085,0.2878319,0.001174466,0.0007043318,0.0002792713,0.000002971344,0.0001378367,0.0007906493],"genre_scores_gemma":[0.9157251,0.000002623412,0.08390379,0.000187842,0.0001317344,0.000008715138,0.000004746524,0.00000439326,0.00003106732],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9290636,"threshold_uncertainty_score":0.3585061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1158456593923128,"score_gpt":0.3445786012784414,"score_spread":0.2287329418861286,"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."}}