{"id":"W4361228676","doi":"10.1016/j.neunet.2023.03.023","title":"On the value of label and semantic information in domain generalization","year":2023,"lang":"en","type":"article","venue":"Neural Networks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval; Vector Institute; Western University","funders":"National Key Research and Development Program of China; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Generalization; Conditional probability distribution; Domain (mathematical analysis); Artificial intelligence; Feature (linguistics); Marginal distribution; Machine learning; Baseline (sea); Process (computing); Data mining; Mathematics; Random variable","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":[0.0003126561,0.00004970944,0.00005818673,0.00008580277,0.00005977608,0.00006240484,0.0001458914,0.00003010977,0.000002828439],"category_scores_gemma":[0.0000398975,0.00003636054,0.00001112686,0.0005846089,0.00001938241,0.0002884417,0.00005992119,0.00009337228,0.000008256826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006790054,"about_ca_system_score_gemma":0.000005181564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001068587,"about_ca_topic_score_gemma":0.000004929761,"domain_scores_codex":[0.9994414,0.00009410402,0.0001488973,0.00007561856,0.000127638,0.0001123586],"domain_scores_gemma":[0.9996157,0.0001604173,0.0000655559,0.0001219183,0.00001781299,0.00001860184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005370074,0.000005658319,0.0008181803,0.000006025182,0.00000198956,0.000001601923,0.001132994,0.695824,0.0000500928,0.2762655,0.0006812048,0.02520733],"study_design_scores_gemma":[0.0001877844,0.00002550344,0.01408023,0.00001277273,5.659102e-7,0.000001230952,0.0000437084,0.9819173,0.000009120557,0.003461841,0.000221663,0.0000382989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7050107,0.00002397092,0.2921427,0.001916922,0.0002007343,0.0001345013,2.495582e-7,0.00007257358,0.0004976861],"genre_scores_gemma":[0.9982079,0.00002517836,0.0006784544,0.001031007,0.00001720711,0.000005187618,0.000005302338,0.000002525074,0.00002724931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2931972,"threshold_uncertainty_score":0.148274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01629253378111227,"score_gpt":0.2369832622420537,"score_spread":0.2206907284609414,"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."}}