{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1221488,0.002962943,0.0020941,0.009155124,0.004072388,0.00965705,0.006445426,0.00704143,0.01158891],"category_scores_gemma":[0.1822689,0.001643893,0.003968201,0.009136285,0.01589897,0.0136815,0.006955188,0.007692534,0.004716276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007133718,"about_ca_system_score_gemma":0.01104539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006736564,"about_ca_topic_score_gemma":0.004600966,"domain_scores_codex":[0.7967479,0.1646244,0.01311046,0.01074787,0.0125386,0.002230905],"domain_scores_gemma":[0.8128914,0.1321031,0.01136354,0.02220868,0.01983567,0.001597471],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003419796,0.00002744264,0.0004885707,0.000214482,0.00002819687,0.00006821832,0.001750216,0.003197395,0.0002863533,0.9650826,0.002491085,0.02633113],"study_design_scores_gemma":[0.00004227339,0.00008677106,0.0003300125,0.0003932547,0.00003921943,0.0002334181,0.0004797117,0.02303341,0.0006047273,0.9112639,0.06341748,0.00007578426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007406258,0.0003760051,0.9918182,0.001388492,0.0001224295,0.0006335491,0.0002982899,0.0003375539,0.004284821],"genre_scores_gemma":[0.03632275,0.0005207058,0.953622,0.001098806,0.0002487437,0.005533087,0.0005186008,0.0001959351,0.001939404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8778511,"threshold_uncertainty_score":0.6459925,"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."}}