{"id":"W1786530154","doi":"10.3968/j.css.1923669720120804.1263","title":"Development of an Item Bank of Order and Graph by Applying Multidimensional Item Response Theory","year":2012,"lang":"en","type":"article","venue":"Canadian social science","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Item response theory; Multidimensional analysis; Graph; Computer science; Graph theory; Econometrics; Artificial intelligence; Machine learning; Mathematics; Statistics; Theoretical computer science; Psychometrics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01795709,0.0006797775,0.001083556,0.003909942,0.0007735931,0.001376407,0.001315256,0.0007969137,0.004447444],"category_scores_gemma":[0.03812703,0.0004368738,0.001326132,0.002769621,0.0006057142,0.002106791,0.001473037,0.001271308,0.001715339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001122424,"about_ca_system_score_gemma":0.003040622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009874335,"about_ca_topic_score_gemma":0.001668389,"domain_scores_codex":[0.9862948,0.006651007,0.002062976,0.0006306557,0.004023364,0.000337174],"domain_scores_gemma":[0.9664284,0.01392095,0.002388626,0.002535137,0.01415457,0.0005723847],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005633188,0.001691476,0.3956432,0.001545632,0.0004572091,0.0002924422,0.004447212,0.006828768,0.00883895,0.0130222,0.01698704,0.5496825],"study_design_scores_gemma":[0.0006879328,0.004880205,0.7623999,0.001530739,0.0005234405,0.001104996,0.01181323,0.07808939,0.01952289,0.03042626,0.08859189,0.000429109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6026317,0.0007025851,0.3345892,0.002084859,0.0005613802,0.0251446,0.00742019,0.001569101,0.02529638],"genre_scores_gemma":[0.4991253,0.0004755177,0.4594551,0.0002834919,0.00008502511,0.0288146,0.007591208,0.0001413567,0.004028341],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01795709,"threshold_uncertainty_score":0.09496731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03582537548181487,"score_gpt":0.3599608201608819,"score_spread":0.324135444679067,"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."}}