{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004249848,0.000230956,0.0003190652,0.0002754026,0.0003170873,0.0008167178,0.002033975,0.00005065167,0.000008850249],"category_scores_gemma":[0.0002222939,0.0001513995,0.000232143,0.0002009455,0.00007420674,0.001133978,0.0003249914,0.000217431,0.00001909759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000291297,"about_ca_system_score_gemma":0.0001329982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005398846,"about_ca_topic_score_gemma":0.00002573682,"domain_scores_codex":[0.9970896,0.0002720709,0.0008550815,0.0004100447,0.001089144,0.0002840417],"domain_scores_gemma":[0.9956949,0.0008421712,0.0002186133,0.0003474161,0.002789657,0.0001072883],"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":[0.0003263192,0.0003545999,0.0005707153,0.0001297514,0.003411712,0.00008749847,0.03939703,0.05540768,0.002631006,0.0369008,0.09364258,0.7671403],"study_design_scores_gemma":[0.001291721,0.002134569,0.009182955,0.0005159909,0.0001489963,0.0002259635,0.0002604452,0.9196862,0.004416867,0.01987142,0.04180022,0.0004646606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.169229,0.0006532723,0.8135166,0.01075447,0.005308611,0.0003708037,0.00000679705,0.00007265468,0.00008781584],"genre_scores_gemma":[0.6884537,0.00007703795,0.3080686,0.001283968,0.001600991,0.00007816001,0.000003723165,0.00002807318,0.000405823],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8642785,"threshold_uncertainty_score":0.7875628,"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."}}