{"id":"W4366307908","doi":"10.1109/ictai56018.2022.00091","title":"On Domain Generalization for Batched Prediction: the Benefit of Contextual Adversarial Training","year":2022,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Key Research and Development Program of China","keywords":"Computer science; Generalization; Adversarial system; Domain (mathematical analysis); Context (archaeology); Machine learning; Artificial intelligence; Training set; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004023716,0.001576467,0.001761533,0.0004779524,0.000601774,0.0008323332,0.002311444,0.001892792,0.00153547],"category_scores_gemma":[0.01308447,0.0005320723,0.0007069269,0.0006484771,0.001779002,0.003348996,0.003168383,0.00355365,0.0004269429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007899334,"about_ca_system_score_gemma":0.0009740628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003925187,"about_ca_topic_score_gemma":0.00346131,"domain_scores_codex":[0.9985377,0.0007178377,0.00004759707,0.0003787273,0.0002067592,0.0001114021],"domain_scores_gemma":[0.9931392,0.004745345,0.0002603122,0.001304546,0.0003607583,0.0001897907],"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":[0.0003649665,0.0001305212,0.001418824,0.00009557237,0.0000957646,0.0001280751,0.0001727341,0.8659108,0.005271325,0.02281224,0.002479622,0.1011195],"study_design_scores_gemma":[0.000006173776,0.00004295025,0.0001236702,0.000008202906,0.000009306579,0.00002572005,0.00001022548,0.989831,0.0007858574,0.008803771,0.0003457158,0.000007342127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02372078,0.0009224492,0.972669,0.0004677478,0.00005820336,0.00004758409,0.00005695819,0.000484613,0.001572707],"genre_scores_gemma":[0.7605143,0.001119485,0.2326417,0.0008963778,0.000305253,0.0001677497,0.0003688665,0.000235047,0.003751291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004023716,"threshold_uncertainty_score":0.02127969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03438473081869904,"score_gpt":0.2477133220996749,"score_spread":0.2133285912809759,"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."}}