{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003497427,0.00006481844,0.00007585464,0.0000538511,0.00007307178,0.00008702324,0.0004042418,0.00002254319,0.00001385365],"category_scores_gemma":[0.00003086146,0.00005454578,0.00003540796,0.0002047539,0.000006392547,0.0002009856,0.0002008848,0.0000450626,0.00005813376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004302782,"about_ca_system_score_gemma":0.00007365799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000801643,"about_ca_topic_score_gemma":0.000002922738,"domain_scores_codex":[0.999177,0.00002052315,0.0001355202,0.0002852168,0.000177609,0.0002041725],"domain_scores_gemma":[0.9994318,0.0001462785,0.00002683755,0.00030261,0.0000563973,0.00003606746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001084482,0.00001793999,0.000153483,0.00001493864,0.0000102454,0.000001674202,0.0007035594,0.0006743942,0.0004485715,0.9228047,0.003315029,0.07185437],"study_design_scores_gemma":[0.0002165623,0.00007422642,0.002836452,0.000009791244,0.000002030749,4.884956e-7,0.00008288959,0.9382589,0.0007561751,0.0538534,0.003794408,0.0001146173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007454668,0.000003125387,0.9843926,0.002273977,0.0002986782,0.0003070175,0.000001907473,0.0003672995,0.004900742],"genre_scores_gemma":[0.3971101,0.000002467942,0.5976565,0.0001800915,0.0000352837,0.000209709,0.00000242662,0.000003874953,0.004799585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9375846,"threshold_uncertainty_score":0.2224312,"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."}}