{"id":"W4414870974","doi":"10.21203/rs.3.rs-7653038/v1","title":"Efficient Unsupervised Domain Adaptation via Self-Supervised Vision Transformer and Synergistic Cross-Domain Alignment","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University; University of Windsor","funders":"","keywords":"Bottleneck; Domain adaptation; Transformer; Domain (mathematical analysis); Adaptation (eye); Feature (linguistics); Software deployment","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004629876,0.0005821958,0.0006107563,0.001102654,0.001033495,0.001480103,0.00158634,0.0005208222,0.00009351665],"category_scores_gemma":[0.0001553535,0.0005650411,0.0002682256,0.001233768,0.0003038537,0.0002350502,0.001316114,0.001690265,0.00008151421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006793763,"about_ca_system_score_gemma":0.0008758532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001762631,"about_ca_topic_score_gemma":0.00003351552,"domain_scores_codex":[0.9917187,0.001683117,0.0008763426,0.001799671,0.002720403,0.001201729],"domain_scores_gemma":[0.9963459,0.0009109938,0.0001604464,0.001396217,0.0006533038,0.0005331851],"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":[0.001017747,0.003072428,0.00192974,0.01098899,0.0007980241,0.0006120965,0.1199428,0.3937369,0.0148464,0.203887,0.0009219451,0.2482459],"study_design_scores_gemma":[0.002150056,0.0004182335,0.004110188,0.001077126,0.00002024312,0.000007896394,0.001735773,0.9731107,0.0002422431,0.0112062,0.005210578,0.0007107506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1289315,0.001091392,0.8598551,0.001432751,0.0005354562,0.002277121,0.00005699358,0.000459938,0.005359767],"genre_scores_gemma":[0.8880869,0.0003005615,0.109861,0.0001706225,0.0001377137,0.0004754121,0.0001364674,0.00005204921,0.0007792313],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7591554,"threshold_uncertainty_score":0.9996801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03697592961712569,"score_gpt":0.3616425863044702,"score_spread":0.3246666566873445,"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."}}