{"id":"W4412055558","doi":"10.1145/3719160.3737642","title":"“Hey Google, How Do I File My Taxes?”: Evaluating Conversational Interfaces for Newcomers Navigating Government Services","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Government (linguistics); Computer science; World Wide Web; Internet privacy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009630081,0.00133853,0.0007591148,0.0009086421,0.00114116,0.003966695,0.001827395,0.003095453,0.008203976],"category_scores_gemma":[0.08395304,0.0004669605,0.0006996575,0.0003777241,0.0008460666,0.005130588,0.002787591,0.001995278,0.003758289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001129117,"about_ca_system_score_gemma":0.001073087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006488558,"about_ca_topic_score_gemma":0.008345421,"domain_scores_codex":[0.9919751,0.0057313,0.0006692932,0.0004635654,0.0009280903,0.0002326454],"domain_scores_gemma":[0.9513194,0.04022218,0.001366923,0.001499272,0.004106784,0.001485459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.04567738,0.01739669,0.05504528,0.01484486,0.00158738,0.0008798639,0.1284366,0.007043427,0.03769916,0.005997136,0.06587169,0.6195206],"study_design_scores_gemma":[0.02050563,0.09350663,0.2105354,0.006372083,0.01213526,0.002479447,0.1429414,0.2080846,0.06343783,0.01714364,0.2205711,0.00228684],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9687382,0.0007861594,0.009351593,0.001201361,0.0004353669,0.002658593,0.001062683,0.001675822,0.01409024],"genre_scores_gemma":[0.932776,0.0005878123,0.04406462,0.0024957,0.0002493663,0.005114801,0.002291678,0.000455073,0.01196481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009630081,"threshold_uncertainty_score":0.05092937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02197416975581651,"score_gpt":0.3305503427884353,"score_spread":0.3085761730326188,"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."}}