{"id":"W3088471706","doi":"10.48550/arxiv.2009.12658","title":"Domain Generalization via Semi-supervised Meta Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Centroid; Generalization; Leverage (statistics); Semi-supervised learning; Machine learning; Pattern recognition (psychology); Domain (mathematical analysis); Benchmark (surveying); Supervised learning; Mathematics; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003632132,0.0003936739,0.0004924724,0.0002608379,0.0003115717,0.0002757731,0.001588471,0.000281711,0.0001841079],"category_scores_gemma":[0.00004818149,0.000455834,0.0003975256,0.0009214684,0.00006702561,0.0004922561,0.001659184,0.000914805,0.0002463402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001497251,"about_ca_system_score_gemma":0.0001582197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007590634,"about_ca_topic_score_gemma":0.00001210253,"domain_scores_codex":[0.9973149,0.0005495092,0.0002777059,0.0013032,0.0001817713,0.0003728669],"domain_scores_gemma":[0.9983401,0.00009585899,0.0003351174,0.0007880644,0.0001630438,0.0002778406],"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":[0.00001682024,0.00002995248,0.0008194068,0.00006263922,0.0004484827,0.0002316671,0.001081854,0.8010663,0.0004887212,0.1948012,0.0001473224,0.0008056649],"study_design_scores_gemma":[0.0004659859,0.00004238777,0.0003476545,0.00002544912,0.000239085,0.000004407731,0.0001108604,0.9576291,0.00009184493,0.03062562,0.009897702,0.0005198603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02015059,0.0001342872,0.9739684,0.0004136041,0.0003962121,0.0002481767,0.000002962825,0.0006502505,0.004035466],"genre_scores_gemma":[0.9748406,0.0001348341,0.02199277,0.0004539705,0.0001110957,0.000002119083,0.00006173059,0.00003568491,0.002367141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9546901,"threshold_uncertainty_score":0.9997894,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1110950348551131,"score_gpt":0.1965172022499819,"score_spread":0.08542216739486876,"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."}}