{"id":"W4392858836","doi":"10.1145/3626253.3635599","title":"A Generalized Framework for Describing Question Randomization","year":2024,"lang":"en","type":"article","venue":"","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Randomization; Computer science; Randomized controlled trial; Randomized experiment; Machine learning; Artificial intelligence; Mathematics; Statistics; Medicine","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":[0.007404106,0.00007912973,0.0001488403,0.0001215731,0.0001150209,0.0006357662,0.0001987211,0.00006597907,0.0007823583],"category_scores_gemma":[0.005949764,0.0000483265,0.000143957,0.0004097652,0.00002200538,0.0002593719,0.00002331251,0.00006385868,0.0001865626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004757745,"about_ca_system_score_gemma":0.00003766556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001236972,"about_ca_topic_score_gemma":0.00001136026,"domain_scores_codex":[0.9982088,0.0001915229,0.0004480298,0.0003537449,0.000658634,0.0001393231],"domain_scores_gemma":[0.9975294,0.001904729,0.00004305214,0.0002500436,0.0002275974,0.00004510993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001687788,0.00002848727,0.0003667884,0.00001631543,0.00001785133,6.349979e-7,0.000263126,0.001810356,0.001480013,0.8756535,0.01894298,0.1012512],"study_design_scores_gemma":[0.0006749745,0.00003697574,0.00006583461,0.00009679321,0.00001620189,6.610223e-7,0.0001022412,0.08883119,0.001928555,0.87205,0.03610606,0.00009053762],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02846309,0.0004034844,0.9641924,0.003795256,0.001224998,0.0005283825,0.000002990152,0.0001151324,0.001274258],"genre_scores_gemma":[0.800905,0.00004077466,0.1943935,0.0005654101,0.0003450037,0.0001331975,0.000007100671,0.00001020885,0.003599792],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7724419,"threshold_uncertainty_score":0.8566275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2836176893562416,"score_gpt":0.4298999124077332,"score_spread":0.1462822230514916,"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."}}