{"id":"W4200422038","doi":"10.2196/34674","title":"Evaluating Voice Assistants' Responses to COVID-19 Vaccination in Portuguese: Quality Assessment","year":2021,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"AI in Service Interactions","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rubric; Portuguese; Context (archaeology); Quality (philosophy); Variety (cybernetics); Population; Subject (documents); Pandemic; Coronavirus disease 2019 (COVID-19); Medicine; Computer science; Public relations; Psychology; Medical education; World Wide Web; Political science; Artificial intelligence; Linguistics; Geography; Pedagogy; Environmental health; Pathology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001504846,0.0001935903,0.0002437954,0.0003585266,0.0002930195,0.0003064945,0.0007567207,0.00008852089,0.0004929238],"category_scores_gemma":[0.001370405,0.0002037192,0.00008432387,0.001063585,0.00001111365,0.0008475211,0.0004752307,0.0003212456,0.00005887721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290789,"about_ca_system_score_gemma":0.000730682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005224759,"about_ca_topic_score_gemma":0.002798625,"domain_scores_codex":[0.996616,0.000912178,0.0006230844,0.000680993,0.0008318465,0.0003359146],"domain_scores_gemma":[0.9971427,0.001074844,0.0002452357,0.0009215986,0.0003387747,0.0002767975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009686345,0.002047488,0.7548735,0.0003636086,0.0001250098,0.000387292,0.04762794,0.002116731,0.09305593,0.06799449,0.006616228,0.02469498],"study_design_scores_gemma":[0.0003191451,0.00009141539,0.9917193,0.00002957619,0.000003955008,0.000005312851,0.001515428,0.001104053,0.001132723,0.001737855,0.002086672,0.0002545703],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9608052,0.00001676138,0.03336377,0.003282423,0.0004666339,0.0003756633,0.00001708248,0.0002109506,0.001461478],"genre_scores_gemma":[0.9881803,0.000001097984,0.008943292,0.001537675,0.00004470235,0.0000773076,0.00003344521,0.00001423181,0.001167883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2368459,"threshold_uncertainty_score":0.8307427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2324626516503171,"score_gpt":0.5298487475362073,"score_spread":0.2973860958858902,"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."}}