{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005898516,0.00006668436,0.00009140075,0.00005689562,0.0004028798,0.00003927666,0.0003677407,0.00001931715,0.0002014981],"category_scores_gemma":[0.00005221205,0.00005278976,0.0000650198,0.0002322186,0.00002514273,0.0001214602,0.00008683214,0.00008487215,0.000001912316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003758166,"about_ca_system_score_gemma":0.00005488866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001091345,"about_ca_topic_score_gemma":0.000006278908,"domain_scores_codex":[0.9990945,0.00008679448,0.0002049123,0.0001875406,0.0002973574,0.0001288547],"domain_scores_gemma":[0.9993643,0.0002487556,0.0001069209,0.0001994555,0.00005120836,0.00002938953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005073609,0.00002429629,0.00002255414,0.000001844441,0.00001486272,3.471461e-7,0.00780111,0.0778462,0.0005142541,0.8989613,0.001343706,0.01341878],"study_design_scores_gemma":[0.002876657,0.0007726892,0.0008247965,0.000005788983,0.00001017854,0.000009168933,0.007991252,0.8878662,0.0003248198,0.03486115,0.06429138,0.0001659106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01407334,0.00001064248,0.9778982,0.001644092,0.0006659806,0.0002744942,0.00001295891,0.00008340937,0.005336871],"genre_scores_gemma":[0.9780844,8.082218e-7,0.01937538,0.001146615,0.00009880071,0.00008480994,0.00002252857,0.000006927368,0.001179693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9640111,"threshold_uncertainty_score":0.3098667,"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."}}