{"id":"W4285134718","doi":"10.1109/tai.2022.3178065","title":"Toward Personalization of User Preferences in Partially Observable Smart Home Environments","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Military College of Canada; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Personalization; Reinforcement learning; Computer science; Preference; Home automation; Baseline (sea); Human–computer interaction; Machine learning; Artificial intelligence; World Wide Web; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004602309,0.000162666,0.0002375369,0.0002821205,0.0002147268,0.00006937226,0.0006491576,0.0000535031,0.0005086699],"category_scores_gemma":[0.000009074099,0.0001865736,0.0001068581,0.0008051732,0.00007066906,0.0005621335,0.00001418954,0.0002771378,0.0001167601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001667908,"about_ca_system_score_gemma":0.000106776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004138657,"about_ca_topic_score_gemma":0.0007472076,"domain_scores_codex":[0.9977864,0.0003168586,0.0005654765,0.000473523,0.0005936154,0.0002640984],"domain_scores_gemma":[0.9991679,0.0001730675,0.0001692469,0.0003765615,0.0000431078,0.00007013744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004133277,0.004373134,0.001840773,0.0001203036,0.0001434186,0.00004739455,0.01979757,0.2975625,0.04041241,0.01186955,0.00007848128,0.6233411],"study_design_scores_gemma":[0.0002973934,0.001268451,0.002658633,0.0001452079,0.00004178536,0.00004142616,0.004325345,0.3409694,0.6337355,0.01202908,0.003417769,0.001070073],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1034554,0.00002125663,0.8948918,0.0002232477,0.0008714435,0.0003186178,0.00003123497,0.00005758481,0.000129402],"genre_scores_gemma":[0.9984913,0.00002288009,0.0008905429,0.0001017979,0.0000148585,0.0002079354,0.000003087199,0.00001181481,0.0002558164],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8950358,"threshold_uncertainty_score":0.7608249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1171837084210457,"score_gpt":0.2788703902975181,"score_spread":0.1616866818764723,"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."}}