{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008535711,0.0002014558,0.0004025932,0.0000836603,0.0002154889,0.0001783598,0.0007141047,0.0001055326,0.0005218362],"category_scores_gemma":[0.0015211,0.0001882012,0.0001576413,0.0004833778,0.0001675761,0.0002584425,0.0001843212,0.0002800443,0.0004941268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004920924,"about_ca_system_score_gemma":0.00003564541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005448928,"about_ca_topic_score_gemma":0.000002754505,"domain_scores_codex":[0.9981304,0.00001707729,0.0009183639,0.0004926574,0.0001102811,0.0003311742],"domain_scores_gemma":[0.9983999,0.0001361926,0.000889171,0.0002531084,0.0002577956,0.00006389706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005207426,0.0001967852,0.002069842,0.00008414162,0.00004787444,8.528027e-7,0.001041215,0.00001738699,0.04683467,0.942417,0.0008969115,0.006341235],"study_design_scores_gemma":[0.00008414427,0.0001054673,0.0002987877,0.0004889147,0.00001228737,0.000007115036,0.001524511,0.005016932,0.6417965,0.3483453,0.001937542,0.0003824811],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9423301,0.0004148435,0.0004304271,0.002528899,0.0008107525,0.0003112634,0.00006416981,0.00005960433,0.05304998],"genre_scores_gemma":[0.9973875,0.00007321998,0.0002024455,0.0002790015,0.00007599111,0.0000205413,0.000002932217,0.00002073772,0.001937664],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5949618,"threshold_uncertainty_score":0.7674622,"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."}}