{"id":"W4404884731","doi":"10.1007/978-3-031-78128-5_13","title":"Label-Expanded Feature Debiasing for Single Domain Generalization","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Debiasing; Computer science; Generalization; Feature (linguistics); Domain (mathematical analysis); Artificial intelligence; Pattern recognition (psychology); Mathematics; Cognitive science","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":[0.0008104217,0.0004958088,0.0004297414,0.0008246048,0.0003730663,0.001404693,0.001725311,0.000377969,0.00001219472],"category_scores_gemma":[0.00009904933,0.0004636386,0.0001484705,0.0007668354,0.0002960486,0.0005818881,0.0006006548,0.0006291845,0.00004036458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003844306,"about_ca_system_score_gemma":0.0003417782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004493657,"about_ca_topic_score_gemma":0.00003975695,"domain_scores_codex":[0.9966228,0.00003264158,0.0004212262,0.001507393,0.0007792068,0.000636748],"domain_scores_gemma":[0.9981565,0.0003758013,0.000236429,0.0008050298,0.0002638557,0.0001624041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001302887,0.00004057059,0.000008343469,0.0001321501,0.0000262978,0.00008117263,0.002527342,0.03797232,0.004500154,0.2958997,0.0001860888,0.6586128],"study_design_scores_gemma":[0.000398658,0.0001703991,0.000006346595,0.0004489776,0.00001168818,0.00008772714,6.124605e-7,0.6527786,0.001345534,0.3183955,0.02573598,0.0006200402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003465984,0.001005124,0.9860222,0.001967398,0.002748545,0.0005289008,0.000006390884,0.0003430829,0.007343744],"genre_scores_gemma":[0.01963641,0.00002773212,0.9726889,0.002500164,0.0008411352,0.00002235034,0.00003247982,0.00007736172,0.004173467],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6579928,"threshold_uncertainty_score":0.9997815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0289085202236165,"score_gpt":0.2673624240164627,"score_spread":0.2384539037928461,"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."}}