{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002837106,0.00003970368,0.00004235188,0.0000654226,0.00007358991,0.00006731076,0.0003287456,0.00002753801,0.00000550246],"category_scores_gemma":[0.00004140142,0.0000353182,0.0000259629,0.0002947154,0.000006963123,0.0001669146,0.00003811491,0.00002241601,0.0002432261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002041913,"about_ca_system_score_gemma":0.00002574679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001576709,"about_ca_topic_score_gemma":0.000007083776,"domain_scores_codex":[0.9994209,0.00001199184,0.0001187068,0.0002334561,0.00009420299,0.0001207061],"domain_scores_gemma":[0.9993969,0.00008813632,0.00003186437,0.0003959513,0.00006253621,0.00002464169],"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":[8.710914e-7,0.000006147505,0.00008930038,0.000006219503,0.0000018202,8.341774e-8,0.0001388705,0.002440399,0.00441344,0.8802502,0.004240932,0.1084117],"study_design_scores_gemma":[0.00006894083,0.000006953715,0.002559154,0.000001843836,7.658778e-7,2.725892e-7,0.00004241781,0.9722813,0.0006439683,0.01368236,0.01066257,0.0000494588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006828933,0.000003893463,0.9842504,0.00637099,0.0002509417,0.0001649599,7.427189e-7,0.0004857639,0.001643343],"genre_scores_gemma":[0.9403093,0.000003802242,0.05681053,0.0001411233,0.00004782504,0.00006705938,0.00001310644,0.00000363987,0.002603595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9698409,"threshold_uncertainty_score":0.3126261,"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."}}