{"id":"W6929142849","doi":"10.48448/80hd-b327","title":"Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Immunodeficiency and Autoimmune Disorders","field":"Immunology and Microbiology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Conversation; Question answering; Filter (signal processing); Selection (genetic algorithm); Smoothing; Paragraph; Model selection","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":[0.0008765105,0.0002772755,0.0002495338,0.0004980679,0.0003868559,0.0000597367,0.0002360438,0.0001984739,0.0003670776],"category_scores_gemma":[0.0002050591,0.000228378,0.00002465709,0.000668861,0.001324837,0.0001097405,0.0000321853,0.0003241176,0.0001002261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002039748,"about_ca_system_score_gemma":0.0007321374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004018529,"about_ca_topic_score_gemma":0.001029727,"domain_scores_codex":[0.998385,0.0001151252,0.0002283825,0.0006066205,0.000271055,0.0003938625],"domain_scores_gemma":[0.9992599,0.00008511449,0.000199592,0.0002412137,0.0001979949,0.000016201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003761434,0.002883092,0.007974831,0.00129582,0.001641371,0.0001263266,0.002889587,0.1825582,0.4112008,0.1631567,0.07657982,0.1459321],"study_design_scores_gemma":[0.02158626,0.007728086,0.03213065,0.01279828,0.001072999,0.0003325853,0.004699661,0.3774293,0.03548164,0.002007106,0.4965748,0.008158613],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.03842009,0.03861841,0.3220306,0.01178374,0.03163465,0.01657992,0.001880984,0.02384793,0.5152037],"genre_scores_gemma":[0.9834798,0.00006334439,0.00009956323,0.0002525204,0.00001213283,0.00003122312,0.0001626466,0.0001566344,0.01574215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9450597,"threshold_uncertainty_score":0.9312984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01603426615987573,"score_gpt":0.2454133938802137,"score_spread":0.2293791277203379,"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."}}