{"id":"W7126404575","doi":"10.18653/v1/2024.uncertainlp-1.12","title":"Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation","year":2024,"lang":"","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Expert elicitation; Misinformation; Uncertainty quantification; Uncertainty analysis; Measurement uncertainty","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003471946,0.0002631861,0.0002707358,0.0004709495,0.0002278413,0.001532068,0.0002919938,0.0002057906,0.00001197955],"category_scores_gemma":[0.0009953926,0.000273046,0.00007671827,0.0008842679,0.0001227435,0.001644057,0.00004260605,0.0002415729,0.00001130414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445836,"about_ca_system_score_gemma":0.0004659014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004862544,"about_ca_topic_score_gemma":0.00007277752,"domain_scores_codex":[0.9974291,0.0003337406,0.0009324515,0.000695587,0.0002468203,0.0003623166],"domain_scores_gemma":[0.9949993,0.003957911,0.0001880079,0.0003423933,0.0003970966,0.0001152961],"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":[0.00002329848,0.00002197565,0.0000240959,0.0003999031,0.000008722703,2.771717e-7,0.003375538,0.01730718,0.002649619,0.426852,0.00003708876,0.5493003],"study_design_scores_gemma":[0.0004065661,0.0001583272,0.00027198,0.000719081,0.00002376905,0.000002941668,0.0003457013,0.8865948,0.005241401,0.1057087,0.0002352537,0.0002914385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005073864,0.0007311486,0.9886691,0.003623174,0.0007730785,0.0007802706,0.00001769614,0.0001837142,0.0001479514],"genre_scores_gemma":[0.60531,0.00006649746,0.3941661,0.0002672069,0.00002407893,0.00007326105,0.00005818459,0.00000926359,0.00002543291],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8692876,"threshold_uncertainty_score":0.9999722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0724592532974986,"score_gpt":0.3971316445195476,"score_spread":0.3246723912220491,"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."}}