{"id":"W2229912692","doi":"10.1080/10447318.2015.1065697","title":"Challenges to Assessing Usability in the Wild: A Case Study","year":2015,"lang":"en","type":"article","venue":"International Journal of Human-Computer Interaction","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Swinburne University of Technology","keywords":"Usability; Seriousness; Interview; Pluralistic walkthrough; Cognitive walkthrough; Computer science; Product (mathematics); Construct (python library); Usability inspection; Usability lab; Usability engineering; Knowledge management; Engineering; Human–computer interaction; Software engineering","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":[0.00318711,0.0001685989,0.0002393125,0.0004761016,0.00006850054,0.0008357151,0.001934005,0.00004597871,0.000007989635],"category_scores_gemma":[0.0001668266,0.0001244242,0.000121182,0.0002112904,0.00002694459,0.002478477,0.0002785733,0.0004884287,0.00002169375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003969729,"about_ca_system_score_gemma":0.00009032679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002836211,"about_ca_topic_score_gemma":0.0005388486,"domain_scores_codex":[0.9970774,0.0006933868,0.0008121733,0.0003286136,0.0009090741,0.0001793462],"domain_scores_gemma":[0.9977852,0.0003813705,0.0003670154,0.0004266824,0.0009236431,0.0001161222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000347052,0.009565389,0.02275553,0.00002618157,0.0005282216,0.02305207,0.3322689,0.0153563,0.0005214456,0.004296531,0.00608695,0.5851954],"study_design_scores_gemma":[0.01674106,0.0256912,0.2174852,0.001854377,0.0002014543,0.2371723,0.2667944,0.1631556,0.002743129,0.03564832,0.02959258,0.002920323],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.849494,0.00003911756,0.1422106,0.004289293,0.003340787,0.0002169741,3.757243e-7,0.00002260361,0.0003861693],"genre_scores_gemma":[0.9920621,0.000002092385,0.00665567,0.0005463221,0.0007091804,0.000009515968,3.348263e-7,0.000007155983,0.000007642281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5822751,"threshold_uncertainty_score":0.805882,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2075931374202254,"score_gpt":0.4274936382817451,"score_spread":0.2199005008615197,"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."}}