{"id":"W171557998","doi":"10.1007/978-3-642-34106-9_14","title":"On the Hardness of Domain Adaptation and the Utility of Unlabeled Target Samples","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Realizability; Domain adaptation; Task (project management); Domain (mathematical analysis); Matching (statistics); Generalization; Artificial intelligence; Labeled data; Class (philosophy); Sample (material); Adaptation (eye); Dimension (graph theory); Function (biology); Concept class; Test data; Machine learning; Pattern recognition (psychology); Algorithm; Mathematics; Statistics; Classifier (UML)","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":[0.01335766,0.001888789,0.005098782,0.002085367,0.001945162,0.004124695,0.005277823,0.005439061,0.005359332],"category_scores_gemma":[0.07632598,0.001574611,0.002654477,0.003326449,0.008678501,0.01696634,0.009564209,0.01220221,0.0008699185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002513777,"about_ca_system_score_gemma":0.001853133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00462932,"about_ca_topic_score_gemma":0.002472861,"domain_scores_codex":[0.9923718,0.003946234,0.0003979341,0.001667014,0.001164372,0.0004526353],"domain_scores_gemma":[0.8367797,0.1524449,0.001287858,0.006576298,0.001892082,0.001019063],"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":[0.001289463,0.0003108653,0.00292814,0.001349204,0.0003476494,0.0004242714,0.0009869474,0.3337194,0.002848933,0.491299,0.01932373,0.1451724],"study_design_scores_gemma":[0.00006558982,0.00006702144,0.0006491721,0.00009797435,0.0000465168,0.0002083429,0.00008071234,0.4058876,0.000763247,0.5904912,0.001607075,0.00003540692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02860886,0.005260432,0.947241,0.005613533,0.0001916926,0.0001200832,0.0005229478,0.0003588321,0.01208271],"genre_scores_gemma":[0.641255,0.009979898,0.3216396,0.003607728,0.002379961,0.0008277284,0.002172562,0.0009401387,0.01719734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01335766,"threshold_uncertainty_score":0.07064289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03702890300038376,"score_gpt":0.2421709051910609,"score_spread":0.2051420021906771,"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."}}