{"id":"W4413275917","doi":"10.1016/j.neunet.2025.107997","title":"Enabling generalized zero-shot learning towards unseen domains by intrinsic learning from redundant LLM semantics","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Science Fund for Distinguished Young Scholars; State Key Laboratory of Industrial Control Technology; National Natural Science Foundation of China","keywords":"Zero (linguistics); Computer science; Artificial intelligence; Semantics (computer science); Shot (pellet); Mathematics; Theoretical computer science; Algorithm; Programming language; Materials science","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":[0.001592943,0.001418725,0.001842536,0.001179108,0.0006423618,0.001558447,0.002909478,0.002104145,0.002192206],"category_scores_gemma":[0.005920496,0.0006538613,0.00120616,0.001062181,0.001458012,0.004382495,0.005090882,0.003484212,0.001145704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008989778,"about_ca_system_score_gemma":0.001077368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003793533,"about_ca_topic_score_gemma":0.005843669,"domain_scores_codex":[0.9989409,0.0003130839,0.00005382871,0.0003808572,0.0002019184,0.0001093788],"domain_scores_gemma":[0.998273,0.0007628365,0.0001034113,0.0005300636,0.0002224717,0.0001082204],"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":[0.0007178357,0.0006445036,0.002040355,0.0006898173,0.0003113829,0.0003814175,0.0004398713,0.2430486,0.05351254,0.03323895,0.01295127,0.6520234],"study_design_scores_gemma":[0.00001140958,0.00004974178,0.0002510842,0.0000268128,0.00001870665,0.00006341371,0.00004755196,0.9579334,0.006965651,0.03357041,0.00104448,0.00001737784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02030278,0.0004581036,0.9756736,0.0002603441,0.00005555382,0.00004686795,0.0002039129,0.002052282,0.0009466246],"genre_scores_gemma":[0.6409301,0.000597513,0.3497105,0.000902593,0.0001589684,0.000195232,0.002247941,0.0005957784,0.004661304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003793533,"threshold_uncertainty_score":0.008424401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01962579135143407,"score_gpt":0.256180253714007,"score_spread":0.236554462362573,"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."}}