{"id":"W4382240129","doi":"10.1609/aaai.v37i3.25407","title":"Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Categorical variable; Discriminator; Mutual information; Pattern recognition (psychology); Conditional probability distribution; Computer science; Artificial intelligence; Classifier (UML); Domain (mathematical analysis); Feature (linguistics); Mathematics; Machine learning; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000807762,0.0002304185,0.0002359142,0.0002698386,0.0003428213,0.0003085125,0.001500063,0.0001053069,0.0001724852],"category_scores_gemma":[0.0004451757,0.0001928057,0.0001432973,0.001336177,0.0002763324,0.0006659565,0.0003118333,0.0003528938,0.0008809593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006230851,"about_ca_system_score_gemma":0.0001998045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001249792,"about_ca_topic_score_gemma":0.000005943454,"domain_scores_codex":[0.9975576,0.00004053322,0.0005721945,0.0005378874,0.0008649657,0.0004268011],"domain_scores_gemma":[0.9984581,0.0001957941,0.0004129486,0.0002554126,0.0005593246,0.0001183759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003924948,0.00006345323,0.0001080762,0.00001863952,0.00001652243,0.000001371274,0.002815014,0.002104405,0.01352201,0.9666176,0.0007202714,0.01397337],"study_design_scores_gemma":[0.00005980957,0.0001374898,0.0008945417,0.0000887257,0.000005978185,0.000005415638,0.003073369,0.44916,0.05018153,0.4939967,0.002146543,0.0002499199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.143142,0.00003355185,0.7444814,0.02243938,0.002048087,0.001192683,0.00004838003,0.001176765,0.08543769],"genre_scores_gemma":[0.9890271,0.0000201114,0.0093079,0.0004242579,0.00009648503,0.00003957905,0.000007594233,0.0000157313,0.001061263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.845885,"threshold_uncertainty_score":0.9998969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08402993613928378,"score_gpt":0.2946167539703175,"score_spread":0.2105868178310337,"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."}}