{"id":"W4407020881","doi":"10.2139/ssrn.5119484","title":"Consistency is Key: Evaluation of and Recommendations for Thermostat Usability Testing","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Usability and User Interface Design","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Usability; Consistency (knowledge bases); Key (lock); Computer science; Thermostat; Human–computer interaction; Engineering; Computer security; Mechanical engineering; Artificial intelligence","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":[0.0104475,0.0002012662,0.000325709,0.0001356168,0.0002483618,0.0001479302,0.0007647884,0.0001612338,0.00001238554],"category_scores_gemma":[0.001413001,0.0001920722,0.0001501147,0.0001971699,0.00008394509,0.0002252894,0.0003952507,0.001499556,7.796797e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009285253,"about_ca_system_score_gemma":0.008873293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001159341,"about_ca_topic_score_gemma":0.0002269957,"domain_scores_codex":[0.9971553,0.0004957466,0.0006372616,0.0004940417,0.0003727269,0.000844923],"domain_scores_gemma":[0.9966246,0.0007973521,0.000490064,0.000568715,0.001467297,0.0000519722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004636523,0.0002572136,0.003104111,0.0002874334,0.0004896594,1.173217e-7,0.003461387,0.0007132223,0.000188121,0.1433132,0.000549253,0.8475899],"study_design_scores_gemma":[0.0004571144,0.0002214646,0.0004573001,0.0001845004,0.0001562756,0.00002287352,0.0003742772,0.1012828,0.0003912304,0.896019,0.0002646749,0.0001683952],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1228649,0.004249959,0.8548668,0.01473811,0.0007494454,0.00141599,0.00008193987,0.00005944783,0.000973474],"genre_scores_gemma":[0.960498,0.0006404092,0.03829379,0.0001761195,0.00006847052,0.00008128611,0.000008242847,0.000009932373,0.0002237821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8474215,"threshold_uncertainty_score":0.9967455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1069850722421773,"score_gpt":0.3578284241006478,"score_spread":0.2508433518584705,"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."}}