{"id":"W2604992821","doi":"10.1609/aaai.v31i1.10898","title":"Unsupervised Domain Adaptation with a Relaxed Covariate Shift Assumption","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Computer science; Inference; Domain (mathematical analysis); Domain adaptation; Adaptation (eye); Generative model; Machine learning; Artificial intelligence; Generative grammar; Algorithm; Data mining; 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":[0.0007800834,0.0002251776,0.0002364969,0.0001168138,0.0008117011,0.0009809994,0.002322072,0.00009409693,0.00004834684],"category_scores_gemma":[0.0004032297,0.0001630671,0.00008728104,0.0002748538,0.000316964,0.001107033,0.0002799654,0.0003286227,0.000123776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004734717,"about_ca_system_score_gemma":0.0001301754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000924702,"about_ca_topic_score_gemma":0.00004827337,"domain_scores_codex":[0.9980655,0.0000335113,0.0004398798,0.0005122117,0.0006288518,0.0003200268],"domain_scores_gemma":[0.9979809,0.00007363888,0.0007737519,0.0005594192,0.0005101893,0.0001020897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001394952,0.00007817901,0.000573143,0.00001835867,0.00002028165,0.000001089035,0.004708686,0.0002636398,0.009523825,0.9474856,0.00001309604,0.03717461],"study_design_scores_gemma":[0.0003242975,0.0006844813,0.03047406,0.0006286687,0.00003923544,0.00001196047,0.002805052,0.3801227,0.08413083,0.4995685,0.0004918163,0.0007184538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3011773,0.00001262747,0.65804,0.01100833,0.0005570016,0.0007433165,0.000003598957,0.0002098185,0.02824792],"genre_scores_gemma":[0.97716,0.00001482923,0.02231292,0.0001675815,0.00004821101,0.00002970677,7.083389e-7,0.00001430263,0.0002517809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6759827,"threshold_uncertainty_score":0.94598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1235750346124303,"score_gpt":0.3013951643751564,"score_spread":0.1778201297627261,"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."}}