{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003730868,0.0001918986,0.0001772643,0.00003108944,0.0003223381,0.0006222089,0.001053717,0.00006508749,0.0007901022],"category_scores_gemma":[0.0001323995,0.000182864,0.00009474628,0.0003445593,0.00003170689,0.001174006,0.0005451767,0.0001960729,0.00005390042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002917087,"about_ca_system_score_gemma":0.00009281865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000288775,"about_ca_topic_score_gemma":0.0002454866,"domain_scores_codex":[0.9982474,0.00006398893,0.000316268,0.0005139351,0.0005500871,0.0003083489],"domain_scores_gemma":[0.9977741,0.001212338,0.000242983,0.0004583969,0.0002463406,0.00006584181],"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":[0.0001379198,0.0005539099,0.009270945,0.001470415,0.001121227,0.000007363673,0.02168776,0.009292328,0.02328869,0.1445883,0.2056162,0.5829649],"study_design_scores_gemma":[0.000780263,0.0001555814,0.001125057,0.000604027,0.0000348453,0.000005682899,0.01133382,0.9392805,0.01253005,0.004281641,0.02948877,0.0003797628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1451275,0.0001483835,0.7845101,0.04185036,0.003352903,0.001423577,0.0005697698,0.000583849,0.02243351],"genre_scores_gemma":[0.7002369,0.000003518286,0.2894943,0.003740478,0.0001043396,0.0003172413,0.00005288689,0.00001544319,0.006034948],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9299881,"threshold_uncertainty_score":0.8651065,"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."}}