{"id":"W4221152138","doi":"10.1609/aaai.v36i8.20890","title":"Interpretable Domain Adaptation for Hidden Subdomain Alignment in the Context of Pre-trained Source Models","year":2022,"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":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Exploit; Leverage (statistics); Interpretability; Domain adaptation; Domain (mathematical analysis); Artificial intelligence; Machine learning; Transformation (genetics); Context (archaeology); Maximization; Data mining; Adaptation (eye); Pattern recognition (psychology); Classifier (UML); Mathematics; Mathematical optimization","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930214,0.001230892,0.001159713,0.001139274,0.0005730347,0.00121061,0.001484305,0.001270653,0.00170185],"category_scores_gemma":[0.00570201,0.0004646803,0.001237699,0.0009959674,0.00107678,0.002093049,0.002244293,0.003321623,0.001016259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008598406,"about_ca_system_score_gemma":0.0009908114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001939717,"about_ca_topic_score_gemma":0.002346042,"domain_scores_codex":[0.9988849,0.0004253302,0.00004962373,0.0003976418,0.0001654885,0.0000770306],"domain_scores_gemma":[0.9975452,0.001299342,0.0002093379,0.0005196382,0.0003032551,0.0001233122],"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":[0.0004586565,0.0003710989,0.004742235,0.0002465436,0.0002142734,0.0004404031,0.0007514026,0.4219111,0.02487678,0.0244053,0.00756548,0.5140167],"study_design_scores_gemma":[0.000008363771,0.00002552754,0.0003684356,0.00001206333,0.00001294636,0.00005232704,0.00004229147,0.9797848,0.002826479,0.01576126,0.001094092,0.00001131269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01219176,0.0002175268,0.9858372,0.0001148794,0.00003143289,0.00003947515,0.00005715346,0.0008389066,0.0006716349],"genre_scores_gemma":[0.5423358,0.0003977578,0.4507351,0.0003856162,0.0001283212,0.0002388015,0.001287654,0.0005296894,0.003961259],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001939717,"threshold_uncertainty_score":0.01020801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07656031427760422,"score_gpt":0.2852360733920337,"score_spread":0.2086757591144294,"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."}}