{"id":"W3015588689","doi":"10.1145/3411764.3445579","title":"Designers Characterize Naturalness in Voice User Interfaces: Their Goals, Practices, and Challenges","year":2021,"lang":"en","type":"article","venue":"","topic":"AI in Service Interactions","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Naturalness; Computer science; Conversation; Bridging (networking); Human–computer interaction; Dilemma; Context (archaeology); User interface; Psychology","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":[0.0002903834,0.000178583,0.0001980048,0.0001016158,0.00007048644,0.0003279232,0.0006315879,0.0000958275,0.00006630268],"category_scores_gemma":[0.0001993107,0.0001484856,0.00003020478,0.000344966,0.00003144152,0.002466647,0.0005241078,0.0003265281,0.00006761887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005696238,"about_ca_system_score_gemma":0.00008802858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001770445,"about_ca_topic_score_gemma":0.001790251,"domain_scores_codex":[0.9985411,0.0002208026,0.0002541729,0.0005564429,0.0001573716,0.000270095],"domain_scores_gemma":[0.9983214,0.0006561495,0.00021043,0.0005754603,0.0001554034,0.00008111675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001715985,0.002141848,0.008876351,0.001091726,0.0005592007,0.001195806,0.07173352,0.00008679171,0.204979,0.1863407,0.003005584,0.5198179],"study_design_scores_gemma":[0.002327407,0.0003103654,0.2137635,0.0009548544,0.00004762099,0.001817735,0.03506173,0.04200529,0.1946082,0.005620228,0.5010313,0.002451808],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8521141,0.009764894,0.02075924,0.1040307,0.00192292,0.0003657524,0.000006517706,0.0004529002,0.01058302],"genre_scores_gemma":[0.9750472,0.003125406,0.01884292,0.001841911,0.00005813716,0.00003335147,0.000003818015,0.00001560967,0.001031694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5173661,"threshold_uncertainty_score":0.6055068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08060591087588886,"score_gpt":0.2906243997933746,"score_spread":0.2100184889174858,"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."}}