{"id":"W2122909041","doi":"10.1145/1357054.1357074","title":"Usability evaluation considered harmful (some of the time)","year":2008,"lang":"en","type":"article","venue":"","topic":"Innovative Human-Technology Interaction","field":"Computer Science","cited_by":595,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Usability; 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":[0.0004838939,0.0000628225,0.00008968652,0.00006577607,0.0001155842,0.000008829179,0.0004701285,0.00005389342,0.0003994116],"category_scores_gemma":[0.0004267869,0.00004297101,0.00003936617,0.0003340401,0.0002666871,0.0004577737,0.0001756283,0.0001210322,0.0001682677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007703867,"about_ca_system_score_gemma":0.0001097189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001861915,"about_ca_topic_score_gemma":0.00000447419,"domain_scores_codex":[0.9990661,0.000132526,0.0002190317,0.0001934357,0.0002914235,0.0000974562],"domain_scores_gemma":[0.9986532,0.00009411409,0.00012458,0.0006168213,0.0005026165,0.00000870185],"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":[0.00001904913,0.0004235471,0.02056866,0.00001537886,0.00008615471,0.000003074564,0.002254189,0.0001537363,0.2396019,0.6830246,0.0313387,0.02251107],"study_design_scores_gemma":[0.0005432207,0.00009008234,0.1235543,0.00001243553,0.000009279905,0.00009280798,0.00003873005,0.09857734,0.6869058,0.08912557,0.0008897577,0.0001606665],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9682108,0.00001080682,0.01674382,0.003458824,0.0003736653,0.0003187312,6.644142e-7,0.000126303,0.01075637],"genre_scores_gemma":[0.995071,5.898276e-7,0.003833989,0.0003872792,0.00001328812,0.00001108449,5.116175e-7,0.000002171914,0.0006801175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.593899,"threshold_uncertainty_score":0.4373277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05395059130449414,"score_gpt":0.2973480894226259,"score_spread":0.2433974981181317,"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."}}