{"id":"W4391591778","doi":"10.48550/arxiv.2402.01887","title":"On $f$-Divergence Principled Domain Adaptation: An Improved Framework","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Divergence (linguistics); Adaptation (eye); Domain adaptation; Domain (mathematical analysis); Computer science; Mathematics; Artificial intelligence; Psychology; Philosophy; Neuroscience; Mathematical analysis; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004644631,0.0004359398,0.0003365721,0.0003908248,0.000276443,0.0004243827,0.002157369,0.0004386556,0.0001338562],"category_scores_gemma":[0.0001078777,0.000495695,0.0002423155,0.0009353277,0.00010552,0.0003864392,0.002094672,0.001562839,0.0006874697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002779463,"about_ca_system_score_gemma":0.0003733886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006000795,"about_ca_topic_score_gemma":0.00002936757,"domain_scores_codex":[0.9970148,0.0002902747,0.0002920336,0.001745157,0.0002072384,0.0004505291],"domain_scores_gemma":[0.9973715,0.0002335729,0.0002739005,0.001615048,0.0001709539,0.0003350015],"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":[0.00004063723,0.00007227236,0.00007430256,0.00004830536,0.0000571013,0.0002804897,0.001674434,0.2572116,0.00003455178,0.7392659,0.00004798439,0.001192484],"study_design_scores_gemma":[0.0001962626,0.0001080397,0.0003279248,0.0001297057,0.00002399258,0.000002517283,0.0002626634,0.6208338,0.00001707428,0.3768802,0.0008225088,0.000395263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.129194,0.00005869118,0.8625942,0.0002124591,0.001789498,0.0003565633,0.00001120086,0.0007486701,0.005034679],"genre_scores_gemma":[0.9572698,0.00004968597,0.03936462,0.0003554488,0.0001432873,0.000003446873,0.00002092738,0.00003491854,0.002757828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8280758,"threshold_uncertainty_score":0.9997495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07917987523748386,"score_gpt":0.2161960191340352,"score_spread":0.1370161438965513,"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."}}