{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001086297,0.0009260337,0.0007671827,0.0005665303,0.0004151232,0.0007607946,0.001678127,0.0009833823,0.002063475],"category_scores_gemma":[0.003286908,0.0004042404,0.0009223,0.000505545,0.0007940808,0.001081005,0.001610994,0.002469338,0.000885202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008036803,"about_ca_system_score_gemma":0.0007980369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002690387,"about_ca_topic_score_gemma":0.003993187,"domain_scores_codex":[0.9995804,0.0001347918,0.00002511324,0.0001240877,0.00009671167,0.00003872529],"domain_scores_gemma":[0.9992423,0.0002939533,0.00007706712,0.0001741035,0.0001548395,0.0000577758],"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":[0.0001502722,0.0001035027,0.002080634,0.00009126909,0.0001048179,0.000116002,0.0001517141,0.6782467,0.01166587,0.01473554,0.004303294,0.2882503],"study_design_scores_gemma":[0.000002991745,0.00001347789,0.00006378145,0.000002505931,0.000001938544,0.00001114908,0.000006839949,0.9947898,0.001162772,0.003393529,0.0005466206,0.000004475945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0152089,0.0001604467,0.9821852,0.0001054478,0.00004738904,0.00003311242,0.00005101445,0.001307371,0.0009010196],"genre_scores_gemma":[0.4470738,0.0002031537,0.5468288,0.0003910486,0.00005507109,0.0002058741,0.0006698509,0.0004212653,0.004150994],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002690387,"threshold_uncertainty_score":0.006903052,"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."}}