{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006170831,0.0004121017,0.0005077077,0.0002327421,0.000856869,0.0008478782,0.001037052,0.000253941,0.00005874618],"category_scores_gemma":[0.0002650358,0.0004135707,0.0001973843,0.00100049,0.000102329,0.0005210692,0.0005915855,0.001643391,0.0000282656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001165372,"about_ca_system_score_gemma":0.0001121308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002435019,"about_ca_topic_score_gemma":0.00001767209,"domain_scores_codex":[0.9964484,0.0006632337,0.0006346176,0.0009060351,0.0004976558,0.0008500751],"domain_scores_gemma":[0.9983393,0.0004572024,0.0003093887,0.0005337615,0.0001374053,0.0002229565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007005349,0.00007334081,0.002790096,0.00001761267,0.0001192683,0.0000784801,0.001302048,0.7099978,0.0028338,0.006703167,0.004728423,0.2712859],"study_design_scores_gemma":[0.001084983,0.0001070988,0.001047615,0.00008537251,0.00003224016,0.000007830378,0.0001435592,0.8915334,0.0003531752,0.0006158581,0.1045667,0.000422118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09475044,0.001891666,0.8951818,0.001881862,0.001548774,0.0002571318,0.000001295465,0.0008522855,0.003634763],"genre_scores_gemma":[0.9820367,0.000478366,0.01012454,0.001904485,0.00038808,0.00001892771,0.0000906678,0.00004469975,0.00491353],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8872862,"threshold_uncertainty_score":0.9998316,"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."}}