{"id":"W2078504914","doi":"10.1145/634067.634127","title":"On the reliability of usability testing","year":2001,"lang":"en","type":"article","venue":"","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Usability; Usability lab; Dialog box; Computer science; Usability inspection; Reliability (semiconductor); Heuristic evaluation; Test (biology); System usability scale; Pluralistic walkthrough; Usability engineering; Web usability; Human–computer interaction; Knowledge management; World Wide Web","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":[0.001433079,0.00008134398,0.0001087414,0.00001812184,0.00008231042,0.00003849714,0.0009317343,0.00003389074,0.0001547844],"category_scores_gemma":[0.002472228,0.00004633532,0.00005460191,0.0004311938,0.0001289259,0.0001867965,0.0001548278,0.0001250902,0.00006387724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003030364,"about_ca_system_score_gemma":0.00003780974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001461037,"about_ca_topic_score_gemma":0.00001183622,"domain_scores_codex":[0.9988967,0.0001791662,0.0002449928,0.0002963691,0.0002196314,0.0001631008],"domain_scores_gemma":[0.9960198,0.002522229,0.00005534305,0.001200789,0.0001633732,0.00003847401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007846359,0.00149592,0.2146589,0.00005986716,0.00001932085,0.00000514271,0.001757353,0.003857399,0.00546756,0.7312489,0.00509585,0.03625532],"study_design_scores_gemma":[0.0003334828,0.0009341102,0.1661659,0.00005372356,0.000007350478,0.00001704855,0.0001218736,0.2435772,0.05425544,0.5317422,0.00240201,0.0003896715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8231191,0.00000284094,0.1463096,0.003445355,0.00008201692,0.0001498588,4.490603e-7,0.00009946411,0.02679131],"genre_scores_gemma":[0.9850504,4.417147e-7,0.01430924,0.0004200867,0.000009321901,0.000006502451,5.122892e-8,0.00000214185,0.0002017413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2397198,"threshold_uncertainty_score":0.2959666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07039233972694191,"score_gpt":0.2691552036774766,"score_spread":0.1987628639505347,"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."}}