{"id":"W4384640019","doi":"10.1145/3539618.3591801","title":"A Preference Judgment Tool for Authoritative Assessment","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Preference; Computer science; Information retrieval; Misinformation; Transitive relation; Relevance (law); Pairwise comparison; Salience (neuroscience); Artificial intelligence; Statistics; Mathematics","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":[0.01961864,0.001801352,0.001343638,0.009633852,0.001474232,0.00515131,0.001883612,0.001778831,0.03119481],"category_scores_gemma":[0.1398535,0.000746947,0.001433484,0.006589413,0.0007089934,0.006442628,0.004006241,0.00232431,0.01373517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00119596,"about_ca_system_score_gemma":0.002892807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001749602,"about_ca_topic_score_gemma":0.00350945,"domain_scores_codex":[0.9712993,0.01291483,0.003693445,0.002267548,0.009155446,0.0006694859],"domain_scores_gemma":[0.8576784,0.08677071,0.006061187,0.01244966,0.03464612,0.002393925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001244869,0.0004961098,0.007138134,0.001876848,0.0001937084,0.0002591547,0.002693553,0.005760622,0.009209566,0.0220997,0.1277484,0.8212794],"study_design_scores_gemma":[0.001008973,0.001151409,0.01968456,0.001395906,0.0003284563,0.001566929,0.003142384,0.2979396,0.03884792,0.1418516,0.4921029,0.0009793324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01775585,0.0004103256,0.9138636,0.0004996651,0.0003518756,0.002895146,0.01048713,0.02954005,0.02419633],"genre_scores_gemma":[0.1002125,0.0002129066,0.8753333,0.0003044707,0.0001634712,0.003881488,0.008232602,0.002721993,0.008937173],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03119481,"threshold_uncertainty_score":0.104357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1305086311949691,"score_gpt":0.3554437093966155,"score_spread":0.2249350782016464,"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."}}