{"id":"W3133934064","doi":"","title":"Classification Confidence Scores with Point-wise Guarantees.","year":2021,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Point (geometry); Confidence interval; Artificial intelligence; Machine learning; 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":[0.0004872035,0.0002116543,0.0001940125,0.0001630055,0.0002649906,0.0005149736,0.000758137,0.00008265321,0.0003903697],"category_scores_gemma":[0.000605143,0.0001863074,0.00006037033,0.000743362,0.0001650512,0.000476647,0.00009478304,0.0003912491,0.000637732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007224597,"about_ca_system_score_gemma":0.0007639165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003657709,"about_ca_topic_score_gemma":0.00007917155,"domain_scores_codex":[0.9973905,0.000161183,0.0003898249,0.0007188813,0.001041072,0.0002985493],"domain_scores_gemma":[0.9974114,0.0003107839,0.0001744965,0.0004489615,0.00153549,0.0001188606],"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":[0.00002231628,0.0001171532,0.00008152518,0.000006255701,0.00001027553,0.00002908099,0.0002222166,0.001197264,0.002507705,0.921377,0.0001314439,0.07429773],"study_design_scores_gemma":[0.00006564823,0.0002061795,0.002459525,0.0001419567,0.000005752077,0.00006424584,0.0002759195,0.653001,0.04570741,0.2969527,0.0007142028,0.0004054749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004412466,0.00005356488,0.9610828,0.01111126,0.0003403163,0.0001455858,0.000009460504,0.0002140175,0.02263058],"genre_scores_gemma":[0.9803041,0.00003234887,0.01780103,0.0009587807,0.0001380048,0.00002822952,0.00002089278,0.00001065064,0.0007060227],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9758916,"threshold_uncertainty_score":0.8196968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09752630771783521,"score_gpt":0.3380556511823711,"score_spread":0.2405293434645359,"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."}}