{"id":"W4200633865","doi":"10.1145/3512943","title":"Human-AI Collaboration for UX Evaluation: Effects of Explanation and Synchronization","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); University of Waterloo","funders":"","keywords":"Usability; Computer science; Human–computer interaction; Context (archaeology); Wizard of oz; Asynchronous communication; Synchronization (alternating current); Test (biology); User experience design","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":[0.0007954939,0.0001438015,0.0001832986,0.0002783709,0.0005951395,0.0001677156,0.001100257,0.00004475872,0.00001408875],"category_scores_gemma":[0.0004488667,0.0001355413,0.00006868917,0.0005587428,0.00004181131,0.001223529,0.0006466213,0.0001591292,0.000001210659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002965898,"about_ca_system_score_gemma":0.00004381318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001995981,"about_ca_topic_score_gemma":0.000006710036,"domain_scores_codex":[0.9983472,0.00005665315,0.0004498283,0.0003874421,0.0006080149,0.0001508641],"domain_scores_gemma":[0.9975736,0.0002009286,0.0006682805,0.0003728999,0.001156856,0.00002745631],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002055688,0.001119719,0.001289776,0.001325102,0.0002029435,8.072843e-7,0.02620297,0.02600696,0.379195,0.4491048,0.03248212,0.08286424],"study_design_scores_gemma":[0.0007027169,0.001637486,0.001656802,0.0002014719,0.00006418811,0.0000115366,0.0008952869,0.4375126,0.4889168,0.06728395,0.0008632708,0.0002539763],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9473336,0.00004549402,0.04601794,0.002608569,0.001672112,0.001895536,0.000004108882,0.00008624437,0.0003363691],"genre_scores_gemma":[0.9949316,0.000002123682,0.004287323,0.0002303761,0.0001509356,0.0003032694,0.000009085042,0.00001369789,0.00007158644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4115056,"threshold_uncertainty_score":0.5527213,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04460961568483576,"score_gpt":0.3544957742154282,"score_spread":0.3098861585305924,"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."}}