{"id":"W4416894890","doi":"10.1080/0969594x.2025.2591284","title":"An implementation of argument-based validation for assessing college major preferences with a hybrid of Likert-rating and forced-choice formats","year":2025,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data collection; Measure (data warehouse); Key (lock); Quality (philosophy)","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":[0.2269134,0.001669645,0.001494465,0.004674664,0.002772464,0.003601327,0.002383689,0.002108547,0.004780988],"category_scores_gemma":[0.3946678,0.001349963,0.002327072,0.003256688,0.003125284,0.004003254,0.0049859,0.003949816,0.001910217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002800831,"about_ca_system_score_gemma":0.00545352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008998437,"about_ca_topic_score_gemma":0.002216887,"domain_scores_codex":[0.7270362,0.2187802,0.0179029,0.007827743,0.02615341,0.002299615],"domain_scores_gemma":[0.409423,0.4311151,0.01819993,0.06046839,0.07903808,0.001755534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004052783,0.007814126,0.139231,0.001901658,0.000614239,0.0004025382,0.04054982,0.005708607,0.03039971,0.04781372,0.01659497,0.704917],"study_design_scores_gemma":[0.004357783,0.01703181,0.2568441,0.004184096,0.0007481516,0.002305048,0.02933078,0.2440626,0.1688095,0.1195322,0.1507362,0.00205776],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.215996,0.0001225099,0.7313499,0.001378325,0.0007145423,0.02645112,0.001254405,0.001525524,0.02120763],"genre_scores_gemma":[0.2360189,0.00007108289,0.7189558,0.000609814,0.00007989855,0.04103569,0.0007042863,0.0002880181,0.002236564],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2269134,"threshold_uncertainty_score":0.9533534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04844669177838798,"score_gpt":0.4835110550125784,"score_spread":0.4350643632341904,"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."}}