{"id":"W7106818517","doi":"10.48448/cvkr-f426","title":"Uncovering Factor-Level Preference to Improve Human-Model Alignment","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Preference; Measure (data warehouse); Preference elicitation; 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":[],"consensus_categories":[],"category_scores_codex":[0.009179154,0.001784365,0.001121121,0.002486249,0.0008483418,0.003545612,0.001608446,0.001605127,0.003934261],"category_scores_gemma":[0.05238211,0.0005867883,0.0009169141,0.001468567,0.0008257205,0.00353491,0.003128826,0.002005695,0.002866499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001033936,"about_ca_system_score_gemma":0.002140264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003498453,"about_ca_topic_score_gemma":0.006389044,"domain_scores_codex":[0.9878992,0.00665014,0.0005978586,0.00278333,0.001567816,0.0005015425],"domain_scores_gemma":[0.9752854,0.01349565,0.002002702,0.005484329,0.003054768,0.0006771326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001131995,0.0008747276,0.05744061,0.0008598802,0.0006808377,0.0003351234,0.003025194,0.09028155,0.06594326,0.009338109,0.0212581,0.7488306],"study_design_scores_gemma":[0.0001244739,0.0003947192,0.01106071,0.0001198027,0.000154025,0.0001923099,0.0008353724,0.9135753,0.03884631,0.02285212,0.01172196,0.0001229234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1879739,0.001421306,0.7777487,0.001132884,0.0002228458,0.0003385026,0.001511307,0.02272741,0.006923138],"genre_scores_gemma":[0.7697139,0.0001541279,0.2229207,0.0003794431,0.0000635231,0.0002681386,0.002821537,0.002187505,0.001491121],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009179154,"threshold_uncertainty_score":0.04854465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1478012668991,"score_gpt":0.3590075604991078,"score_spread":0.2112062936000078,"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."}}