{"id":"W1509317141","doi":"10.1002/9781118411360.wbcla070","title":"Multifaceted Rasch Analysis for Test Evaluation","year":2013,"lang":"en","type":"other","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Rasch model; Facet (psychology); Polytomous Rasch model; Test (biology); Task (project management); Scale (ratio); Computer science; Focus (optics); Psychology; Artificial intelligence; Machine learning; Natural language processing; Item response theory; Psychometrics; Social psychology; Developmental psychology; Engineering; Systems 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":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01089468,0.0002140092,0.0007045465,0.003153173,0.00006616597,0.0002642338,0.0008169764,0.0003007497,0.07696949],"category_scores_gemma":[0.2967932,0.0001313864,0.0003817218,0.00563972,0.00003985441,0.0000559058,0.00008425132,0.00009526107,0.0009825251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003086768,"about_ca_system_score_gemma":0.00005277224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004365156,"about_ca_topic_score_gemma":0.0001223923,"domain_scores_codex":[0.9962829,0.0003943779,0.0006331873,0.0007944703,0.001630134,0.0002649012],"domain_scores_gemma":[0.9289061,0.06766586,0.001036825,0.001391333,0.0008787457,0.000121111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001070412,0.00001918505,0.01388565,0.00000268159,0.0001930987,6.666981e-8,0.000008114486,0.00007241396,0.00001286235,0.00004044859,0.7795483,0.2062161],"study_design_scores_gemma":[0.0006090689,0.00005774435,0.02507224,0.00001325098,0.000716077,4.067171e-7,0.000232116,0.232442,0.00001760563,0.00336389,0.7371308,0.0003447642],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00006476768,0.000415411,0.3522366,0.0001081635,0.0005217473,0.0008655351,0.00004468739,0.0001410104,0.6456021],"genre_scores_gemma":[0.00106096,0.00001543673,0.1974708,0.00007765074,0.0001908803,0.0001398688,0.00003845899,0.00007920656,0.8009267],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2858985,"threshold_uncertainty_score":0.9997953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7058905102004684,"score_gpt":0.5619458144991976,"score_spread":0.1439446957012709,"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."}}