{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01145332,0.00121413,0.002666289,0.001716477,0.001061038,0.001903967,0.003099041,0.00438611,0.001607533],"category_scores_gemma":[0.03897172,0.000940364,0.001107467,0.001376424,0.005066813,0.01042122,0.004172697,0.005948238,0.0001998267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00169529,"about_ca_system_score_gemma":0.0009487506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00597164,"about_ca_topic_score_gemma":0.005221859,"domain_scores_codex":[0.9962924,0.002262284,0.0001714108,0.0007104338,0.0003890269,0.0001744185],"domain_scores_gemma":[0.945478,0.04828491,0.0009703165,0.003139414,0.001329264,0.0007980944],"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":[0.0009666954,0.0005141654,0.005592929,0.0003818182,0.0005076246,0.0001865494,0.0003688884,0.6345077,0.003641263,0.1281531,0.005087759,0.2200915],"study_design_scores_gemma":[0.00001840636,0.00003766479,0.0004489993,0.0000237731,0.00003367015,0.0000216685,0.00002400095,0.9050915,0.0005012452,0.09360614,0.0001765967,0.00001640688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09787005,0.004060542,0.8904508,0.003620371,0.0001339643,0.00007280966,0.0002122276,0.0003709254,0.003208301],"genre_scores_gemma":[0.8746709,0.00187426,0.1182297,0.0009709601,0.000419645,0.00009547213,0.000371563,0.0001497754,0.003217714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01145332,"threshold_uncertainty_score":0.06057173,"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."}}