{"id":"W4413143844","doi":"10.1016/j.iswa.2025.200567","title":"LWR-Net: Learning without retraining for scalable multi-task adaptation and domain-agnostic generalisation","year":2025,"lang":"en","type":"article","venue":"Intelligent Systems with Applications","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kensington Health","funders":"Australian Research Council","keywords":"Retraining; Scalability; Computer science; Domain adaptation; Adaptation (eye); Task (project management); Net (polyhedron); Domain (mathematical analysis); Artificial intelligence; Machine learning; Database; Engineering; Systems engineering; Mathematics; Psychology","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":[0.002679172,0.002723928,0.00179473,0.000861778,0.0006039462,0.0009591084,0.004613943,0.002320779,0.003064761],"category_scores_gemma":[0.004581041,0.001079521,0.001823283,0.0008397159,0.0009451448,0.002631911,0.00323573,0.004173935,0.002263116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001260662,"about_ca_system_score_gemma":0.001517978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008159791,"about_ca_topic_score_gemma":0.008983616,"domain_scores_codex":[0.9988062,0.000206328,0.00007869291,0.0004877671,0.0002482274,0.0001727615],"domain_scores_gemma":[0.9987452,0.0003951407,0.0001222658,0.0003214913,0.0003155889,0.0001002924],"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":[0.0003592131,0.0004871211,0.001452062,0.0002527526,0.0002399381,0.0003930335,0.0001807578,0.4314398,0.01950325,0.003659818,0.01401137,0.528021],"study_design_scores_gemma":[0.00002389698,0.00008634496,0.0001959299,0.00001189192,0.00002095377,0.00004469438,0.00001389986,0.9917426,0.003370935,0.003007503,0.001463927,0.00001737761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02289757,0.001099691,0.9581904,0.0003895071,0.0002141153,0.000213563,0.000265931,0.01436786,0.002361492],"genre_scores_gemma":[0.4578463,0.0007581408,0.5248525,0.001444046,0.0002233008,0.0009770925,0.002267144,0.001442513,0.01018889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008159791,"threshold_uncertainty_score":0.01622456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03788459108865515,"score_gpt":0.2838944364537177,"score_spread":0.2460098453650625,"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."}}