{"id":"W4406376912","doi":"10.1111/jedm.12424","title":"Using Multilabel Neural Network to Score High‐Dimensional Assessments for Different Use Foci: An Example with College Major Preference Assessment","year":2025,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Preference; Artificial neural network; Artificial intelligence; Psychology; Machine learning; Computer science; Evaluation methods; Statistics; Mathematics; Reliability engineering","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":[0.0009613713,0.0002767582,0.0004306461,0.0003503606,0.0003155564,0.0002124061,0.0008065459,0.00005291634,0.00001684954],"category_scores_gemma":[0.0001097058,0.00021361,0.0001215317,0.0005743017,0.00003140869,0.001061306,0.000155767,0.0002229646,4.207604e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234514,"about_ca_system_score_gemma":0.001503505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006126718,"about_ca_topic_score_gemma":0.0001810554,"domain_scores_codex":[0.9968321,0.0001796928,0.0007347908,0.0004591639,0.001418256,0.0003760063],"domain_scores_gemma":[0.995916,0.0002785983,0.0006007354,0.0005045338,0.002444106,0.0002559946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001419331,0.01015389,0.2059343,0.0002469596,0.002774913,0.00002032935,0.0005128519,0.2555192,0.07425781,0.3959546,0.02599247,0.02721333],"study_design_scores_gemma":[0.003717344,0.002788671,0.785786,0.001590485,0.0005863298,0.00006055098,0.00007309904,0.1324154,0.006550907,0.0640351,0.001398489,0.0009976801],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3063923,0.00006488577,0.6906399,0.001643788,0.0005885716,0.0006257754,0.000007957929,0.00001831677,0.00001855511],"genre_scores_gemma":[0.5438488,0.000001277604,0.4554617,0.0004260677,0.0001272462,0.00006143313,0.000004529093,0.000009584684,0.00005937689],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5798516,"threshold_uncertainty_score":0.8710763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.233287845927402,"score_gpt":0.3977295805474502,"score_spread":0.1644417346200483,"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."}}