{"id":"W4410730191","doi":"10.1007/978-3-031-91585-7_7","title":"TF-OCM: Training-Free Optimal Community Matching for Domain Generalized Few-Shot Learning","year":2025,"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 British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Shot (pellet); Matching (statistics); Domain (mathematical analysis); Artificial intelligence; Training (meteorology); Pattern recognition (psychology); Machine learning; Statistics; Mathematics","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":[0.002124481,0.00214338,0.003782249,0.002680358,0.001339368,0.001607083,0.006672556,0.004517431,0.01178084],"category_scores_gemma":[0.008249316,0.001204647,0.001964054,0.003330318,0.00122278,0.004397563,0.004425575,0.004009373,0.006750173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001444153,"about_ca_system_score_gemma":0.002257684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01284461,"about_ca_topic_score_gemma":0.01836996,"domain_scores_codex":[0.9981033,0.0003712575,0.0000864673,0.0007712474,0.0004420251,0.0002256636],"domain_scores_gemma":[0.9973714,0.001035974,0.00009970574,0.0009001999,0.0004035176,0.000189063],"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":[0.0004322004,0.0003166099,0.0004612898,0.0003323049,0.0001533906,0.0001297726,0.00009771042,0.0796641,0.01009931,0.008647745,0.03559749,0.8640681],"study_design_scores_gemma":[0.00004213101,0.00005525534,0.0001375171,0.00001926833,0.00001944073,0.00008986011,0.00002696271,0.976994,0.003460015,0.01649585,0.002641717,0.00001798922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005482496,0.0006639773,0.9823161,0.0001404861,0.0001443005,0.0001630198,0.0005280327,0.009162528,0.001399124],"genre_scores_gemma":[0.09107719,0.000382998,0.8929681,0.0004208637,0.0001902233,0.0004019036,0.005019203,0.001707334,0.007832242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01284461,"threshold_uncertainty_score":0.03941077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04717910218694317,"score_gpt":0.2868922300215428,"score_spread":0.2397131278345997,"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."}}