{"id":"W3175886919","doi":"10.1609/aaai.v35i6.16687","title":"Aggregating Binary Judgments Ranked by Accuracy","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Game Theory and Voting Systems","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Binary number; Ranking (information retrieval); Computer science; Data mining; Distortion (music); Ground truth; Binary data; Machine learning; Artificial intelligence; Algorithm; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01782395,0.001430506,0.002486,0.003905259,0.001201897,0.004099279,0.002324616,0.00198383,0.003169373],"category_scores_gemma":[0.05923698,0.000603059,0.0009053951,0.003308153,0.001481382,0.004890028,0.002830918,0.002781285,0.0008904252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001580414,"about_ca_system_score_gemma":0.001220466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003893798,"about_ca_topic_score_gemma":0.00477153,"domain_scores_codex":[0.9862334,0.006389545,0.000812377,0.002648212,0.003127252,0.0007892993],"domain_scores_gemma":[0.9560213,0.0281738,0.00475443,0.005524667,0.004509438,0.001016298],"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":[0.001299894,0.0005250988,0.04243368,0.0005436092,0.0005985903,0.0003137641,0.002111159,0.2101894,0.005038793,0.140367,0.01073041,0.5858486],"study_design_scores_gemma":[0.00009689522,0.0002904503,0.01030368,0.000138542,0.0001388241,0.0001223335,0.0004091531,0.7299919,0.004208666,0.2493173,0.004847971,0.0001343746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1367667,0.0008429061,0.851039,0.002063153,0.0001903169,0.0002215895,0.0007362898,0.0004825065,0.007657411],"genre_scores_gemma":[0.7704026,0.0003754158,0.2239716,0.0003195922,0.0004166794,0.0001808067,0.001226355,0.0001080986,0.002999033],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01782395,"threshold_uncertainty_score":0.0942632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.102301927611632,"score_gpt":0.2771321674975789,"score_spread":0.1748302398859468,"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."}}