{"id":"W4384891006","doi":"10.1145/3539618.3594243","title":"Uncertainty Quantification for Text Classification","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Uncertainty quantification; Artificial intelligence; Machine learning; Scalability; Robustness (evolution); Calibration; Context (archaeology); Ensemble learning; Deep learning; Mathematics; Statistics; Database","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":[0.008355423,0.001840838,0.001649277,0.004354389,0.001471865,0.005448939,0.002395057,0.002454766,0.00766376],"category_scores_gemma":[0.04280724,0.0008977058,0.002210229,0.003559296,0.002911191,0.009816564,0.004531988,0.005550791,0.002694433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003368325,"about_ca_system_score_gemma":0.001673085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886887,"about_ca_topic_score_gemma":0.001140064,"domain_scores_codex":[0.9899586,0.003392558,0.0008565296,0.001782823,0.003632204,0.0003773159],"domain_scores_gemma":[0.9802462,0.01440003,0.001201328,0.00184204,0.002001786,0.0003084527],"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":[0.0001318168,0.00006069928,0.001359186,0.0009200381,0.0001931545,0.0001924813,0.0005153041,0.114954,0.003416761,0.460094,0.02293827,0.3952243],"study_design_scores_gemma":[0.000007602708,0.00002984662,0.0004359703,0.0002185524,0.00002848196,0.0001376139,0.00007296676,0.3327643,0.002134548,0.6461502,0.01797089,0.00004905554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001223919,0.002798075,0.9914954,0.001048302,0.0002673287,0.00004963079,0.0003274755,0.0004379019,0.002351968],"genre_scores_gemma":[0.2193153,0.01123153,0.7467651,0.00249511,0.005795346,0.001008402,0.003863722,0.001091081,0.00843431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008355423,"threshold_uncertainty_score":0.04418826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1315274212625581,"score_gpt":0.32902778271927,"score_spread":0.1975003614567119,"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."}}