{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03579579,0.001993684,0.003096594,0.004356812,0.001007914,0.004782734,0.003336289,0.002908669,0.004357681],"category_scores_gemma":[0.2169561,0.001384176,0.001602846,0.003124441,0.002667435,0.01064195,0.006093763,0.004800151,0.0004490059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002013656,"about_ca_system_score_gemma":0.002859683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003117919,"about_ca_topic_score_gemma":0.004155385,"domain_scores_codex":[0.9727998,0.01878828,0.001216901,0.001843984,0.004904537,0.0004464205],"domain_scores_gemma":[0.6602151,0.3137898,0.006956866,0.0098179,0.008108633,0.001111783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001099725,0.0005335954,0.005161755,0.001576679,0.0009405989,0.0001962992,0.001528164,0.4217352,0.003066365,0.2232012,0.003219742,0.3377406],"study_design_scores_gemma":[0.00007241821,0.0001207231,0.0008382865,0.0001642518,0.00008847145,0.00006272762,0.0001277792,0.7164897,0.001976125,0.2787069,0.001262263,0.00009039672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006244179,0.0003170727,0.991884,0.0003470576,0.00002620882,0.00007963887,0.0001020371,0.0001140313,0.0008857379],"genre_scores_gemma":[0.4520375,0.0007000165,0.544678,0.0004169475,0.0001778818,0.0005656097,0.0004015709,0.0001556917,0.0008668303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03579579,"threshold_uncertainty_score":0.1893085,"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."}}