{"id":"W4406840514","doi":"10.48550/arxiv.2501.14048","title":"SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Oak Ridge Institute for Science and Education; Workforce Development for Teachers and Scientists; University of Toronto; FAS Division of Science, Harvard University; High Energy Physics; U.S. Department of Energy; Office of Science; Harvard University; National Science Foundation","keywords":"Equivariant map; Domain adaptation; Adaptation (eye); Domain (mathematical analysis); Computer science; Image (mathematics); Artificial neural network; Artificial intelligence; Mathematics; Pure mathematics; Psychology; Neuroscience; Mathematical analysis","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":[0.0006239235,0.0004265217,0.0004074081,0.0002472434,0.000347142,0.0004432918,0.001116985,0.0003229211,0.000009361331],"category_scores_gemma":[0.00009913094,0.0004060782,0.0001822393,0.0004693623,0.0001030414,0.0004796023,0.0005362021,0.0007874458,0.00002249757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002304358,"about_ca_system_score_gemma":0.0003238254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004084492,"about_ca_topic_score_gemma":0.00007961837,"domain_scores_codex":[0.9972041,0.0002306065,0.0005670715,0.001133751,0.0003426123,0.0005218557],"domain_scores_gemma":[0.9976122,0.0003237918,0.000564682,0.001072971,0.000291825,0.0001345124],"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":[0.0005306089,0.0004255109,0.01233104,0.0006500861,0.0004994381,0.0001010495,0.006557434,0.7376798,0.002177589,0.1263153,0.0008005075,0.1119316],"study_design_scores_gemma":[0.0007040043,0.0001003818,0.04747282,0.0001337467,0.00004484532,0.000007675827,0.0002639563,0.9472604,0.00001430352,0.002348677,0.001220445,0.0004287726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02631273,0.0001555029,0.9664922,0.003089816,0.00118459,0.00103485,0.00001745575,0.0004245338,0.001288274],"genre_scores_gemma":[0.8463862,0.00003145702,0.151071,0.0005745145,0.0001609752,0.0003270647,0.0003310438,0.00003552831,0.001082173],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8200735,"threshold_uncertainty_score":0.9998391,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05151855339565425,"score_gpt":0.2904914336194901,"score_spread":0.2389728802238359,"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."}}