{"id":"W1885448067","doi":"10.48550/arxiv.1506.04573","title":"A New PAC-Bayesian Perspective on Domain Adaptation","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Bayesian probability; Divergence (linguistics); Perspective (graphical); Computer science; Domain (mathematical analysis); Generalization; Upper and lower bounds; Domain adaptation; Measure (data warehouse); Adaptation (eye); Generalization error; Artificial intelligence; Focus (optics); Machine learning; Econometrics; Data mining; Mathematics; Psychology","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":[0.0003750527,0.0003502687,0.0003087728,0.0004120624,0.0001721839,0.0002340243,0.001327957,0.0002738365,0.00005486989],"category_scores_gemma":[0.00008817633,0.0004110647,0.0001964349,0.000682299,0.00006255098,0.0004190804,0.0007013629,0.0007555612,0.0003534069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009027135,"about_ca_system_score_gemma":0.0008338073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005489074,"about_ca_topic_score_gemma":0.0001159379,"domain_scores_codex":[0.9977337,0.0002865274,0.0001892001,0.001214365,0.000214111,0.0003621462],"domain_scores_gemma":[0.9978639,0.0001068174,0.0003044873,0.0009941759,0.0003140983,0.0004165022],"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":[0.00005508904,0.00004593168,0.00007773715,0.000008157065,0.00005281315,0.0001839682,0.005826082,0.2886946,0.000005825259,0.7023291,0.001027383,0.001693357],"study_design_scores_gemma":[0.001003235,0.0001596331,0.00051323,0.000083959,0.00003047269,0.000005207402,0.004697999,0.5787708,0.00001131078,0.4107213,0.003447949,0.0005548858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006573896,0.00005159345,0.9458706,0.0006502137,0.000606599,0.0002924499,0.000004779975,0.0003743795,0.04557546],"genre_scores_gemma":[0.9659425,0.00002781237,0.02704391,0.0002749124,0.0001551473,6.079699e-7,0.00001394008,0.00002488094,0.006516297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9593686,"threshold_uncertainty_score":0.9998341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09015163841440388,"score_gpt":0.2134027382900402,"score_spread":0.1232510998756363,"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."}}