{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001777034,0.0001160883,0.0001861462,0.0003036003,0.0003287303,0.0001693488,0.0001227748,0.00004658314,0.00001108987],"category_scores_gemma":[0.0005783815,0.0001124965,0.00001960712,0.0004211101,0.0001028775,0.001961696,0.0000275883,0.00008201207,5.816528e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001543954,"about_ca_system_score_gemma":0.00296777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00528487,"about_ca_topic_score_gemma":0.001728005,"domain_scores_codex":[0.9984451,0.0004021802,0.0004538211,0.0002187012,0.0002889973,0.0001912341],"domain_scores_gemma":[0.9965391,0.002300221,0.0006561158,0.0001279561,0.0003228883,0.00005369718],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002057682,0.0009727982,0.4774331,0.0006083126,0.0001095444,1.704726e-7,0.01404523,0.0001036723,0.002193719,0.4673372,0.00008502579,0.03690543],"study_design_scores_gemma":[0.003326574,0.000594447,0.568276,0.0005674294,0.0003521846,0.0000019917,0.3990984,0.001538567,0.006703575,0.006076785,0.01307826,0.0003858013],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807323,0.00006987273,0.003294966,0.004250352,0.0001107337,0.001192372,0.00002554476,0.00001498977,0.01030884],"genre_scores_gemma":[0.9706818,0.0001255195,0.02850212,0.0002435917,0.00006391154,0.0002132193,0.00006602218,0.000006566947,0.00009725805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4612604,"threshold_uncertainty_score":0.7989177,"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."}}