{"id":"W7097530823","doi":"","title":"� Balanced Item Pool Assembly in Computerized Adaptive Testing","year":2007,"lang":"en","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Discretion; Government (linguistics); Accreditation; Agency (philosophy); Common law; Public law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01540647,0.0001434916,0.0003926396,0.0007888341,0.00008711765,0.0001455847,0.0007069485,0.00008406613,0.0001228655],"category_scores_gemma":[0.1181311,0.00009927445,0.00006463092,0.005383525,0.00004385786,0.0002109339,0.0002076499,0.0001947468,0.00009287561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004813965,"about_ca_system_score_gemma":0.0000369523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001574319,"about_ca_topic_score_gemma":0.00004946446,"domain_scores_codex":[0.9968804,0.0003176861,0.0009043479,0.0005427737,0.0008565983,0.0004982211],"domain_scores_gemma":[0.888386,0.1104733,0.0003034209,0.0004209309,0.0002901578,0.0001262192],"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":[0.00005849102,0.00004156254,0.300871,0.000001242207,0.000004806314,0.00005450479,0.00009304747,0.0001539624,0.004555739,0.001036743,0.0008317635,0.6922972],"study_design_scores_gemma":[0.0007422497,0.0001177165,0.9259498,0.00002353213,0.000001472534,0.00001934827,0.0008702771,0.06219151,0.0008028782,0.008379167,0.0007188177,0.0001832308],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.48839,0.00003164191,0.442419,0.00007557435,0.0003866283,0.0001118586,7.471853e-7,0.00009205363,0.06849248],"genre_scores_gemma":[0.6380063,6.774219e-7,0.3612615,0.0002686431,0.00006806949,0.000001655366,2.338572e-7,0.000005170177,0.0003876875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6921139,"threshold_uncertainty_score":0.8892973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5907761345273238,"score_gpt":0.4859520636099765,"score_spread":0.1048240709173473,"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."}}