{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002060305,0.0001867031,0.0002715483,0.0001668152,0.0003005379,0.0001445837,0.002314379,0.00004549216,0.00004038382],"category_scores_gemma":[0.0002853214,0.0001393846,0.0001455958,0.0006775861,0.0001732972,0.0003890072,0.0003608939,0.0002966074,0.00000286213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000944181,"about_ca_system_score_gemma":0.0001241002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088589,"about_ca_topic_score_gemma":0.00002812107,"domain_scores_codex":[0.9977183,0.0001062653,0.0007107689,0.0004145015,0.0007284268,0.0003217673],"domain_scores_gemma":[0.9983669,0.0004321644,0.0005816831,0.0002941259,0.0002810001,0.00004413625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000253172,0.0001864848,0.00003437652,0.00002755744,0.00001334899,2.273775e-7,0.05384325,0.007583339,0.01150275,0.8760386,0.00008058855,0.05043633],"study_design_scores_gemma":[0.0001136904,0.0003867943,0.00005829861,0.00007368306,0.000008457107,0.000003820579,0.0407399,0.6558512,0.02193299,0.2802498,0.0004223714,0.0001590046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1820597,0.00003995012,0.8069924,0.004909123,0.000333151,0.001498115,0.0000158339,0.00005427495,0.004097439],"genre_scores_gemma":[0.9910137,0.000006782017,0.007980516,0.0004717618,0.00002081215,0.0002772736,0.000001802464,0.0000120826,0.0002152605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8089541,"threshold_uncertainty_score":0.5683938,"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."}}