{"id":"W4399602353","doi":"10.1016/j.ijhcs.2024.103317","title":"The Guided Evaluation Method: An easier way to empirically estimate trained user performance for unfamiliar keyboard layouts","year":2024,"lang":"en","type":"article","venue":"International Journal of Human-Computer Studies","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Simon Fraser University","funders":"","keywords":"Computer science; Human–computer interaction","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":[0.007389407,0.001347081,0.0009872185,0.001610617,0.0004987745,0.001253885,0.001238278,0.001802305,0.005101867],"category_scores_gemma":[0.06416798,0.0005579074,0.0005878788,0.0008383944,0.0005962381,0.002138285,0.001546751,0.00107689,0.001673662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004345588,"about_ca_system_score_gemma":0.0009192781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002544461,"about_ca_topic_score_gemma":0.005475827,"domain_scores_codex":[0.9891443,0.006860765,0.000535885,0.0008661855,0.002415816,0.0001770144],"domain_scores_gemma":[0.944051,0.03710554,0.002959639,0.006286181,0.008662436,0.0009351778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003789606,0.004179601,0.0622023,0.001707566,0.000758912,0.0001899762,0.005649399,0.01509497,0.08777811,0.003873479,0.009980768,0.8047953],"study_design_scores_gemma":[0.002281245,0.05402133,0.3944838,0.001085571,0.001144213,0.002102191,0.004220991,0.3622996,0.138493,0.01259362,0.02611483,0.001159656],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2619371,0.0003697787,0.7201849,0.0001440834,0.0001669947,0.002318062,0.0006157664,0.003083929,0.01117945],"genre_scores_gemma":[0.6440658,0.0001416245,0.3452128,0.0002614775,0.00003624442,0.003556686,0.0004689383,0.0005292933,0.005727161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007389407,"threshold_uncertainty_score":0.03907943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1574932008852521,"score_gpt":0.4772609425430596,"score_spread":0.3197677416578074,"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."}}