{"id":"W4387688000","doi":"10.48550/arxiv.2310.09213","title":"A Sampling-Based Domain Generalization Study with Diffusion Generative Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Domain (mathematical analysis); Generalization; Computer science; Artificial intelligence; Generative model; Pattern recognition (psychology); Subspace topology; Gaussian; Representation (politics); Sample (material); Statistical model; Algorithm; Mathematics; Generative grammar","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":[0.0003587266,0.0004912203,0.0004690129,0.000351414,0.0004178,0.0003058682,0.001324708,0.0002120027,0.00001162401],"category_scores_gemma":[0.00001652843,0.0004623389,0.0001667949,0.001015352,0.00009211028,0.0004780283,0.00132762,0.0003842748,0.00002672224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002222273,"about_ca_system_score_gemma":0.0002898956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004190812,"about_ca_topic_score_gemma":0.000619575,"domain_scores_codex":[0.9969347,0.0005066948,0.0002597988,0.001663805,0.0002155081,0.000419466],"domain_scores_gemma":[0.9977351,0.0001187036,0.00031594,0.00132792,0.0003301634,0.0001721379],"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":[0.00006147649,0.00025337,0.001094036,0.00001568342,0.0001276188,0.0001761489,0.0006097823,0.985922,0.00008137227,0.0113752,0.0001395712,0.0001437854],"study_design_scores_gemma":[0.0009403346,0.0002630024,0.000618501,0.00006888482,0.00008532913,6.963095e-7,0.0002171811,0.9691091,0.0001201304,0.02798372,0.00004359807,0.000549589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1516445,0.00001818541,0.8464977,0.000140136,0.0003975883,0.0008026007,0.0000176161,0.0003405958,0.0001411375],"genre_scores_gemma":[0.9617512,0.00003317585,0.03720122,0.000124673,0.0001640582,0.000009782824,0.00005467728,0.00004616058,0.0006151091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8101066,"threshold_uncertainty_score":0.9997829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1104075731901478,"score_gpt":0.2087363050380569,"score_spread":0.0983287318479091,"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."}}