{"id":"W4320014598","doi":"10.2139/ssrn.4331203","title":"Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Simple (philosophy); Computer science; Active learning (machine learning); Domain (mathematical analysis); Shot (pellet); One shot; Artificial intelligence; Machine learning; Engineering; Mathematics; 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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003279247,0.0003719834,0.000548226,0.0003982034,0.001209409,0.0004221149,0.0006344734,0.0001491335,0.00001781207],"category_scores_gemma":[0.0004547384,0.0003385074,0.0003479415,0.0006234363,0.0001076275,0.001155429,0.0002500055,0.00279037,0.00004051246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003204012,"about_ca_system_score_gemma":0.0007962174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002424641,"about_ca_topic_score_gemma":0.000172471,"domain_scores_codex":[0.9952039,0.0004620117,0.0005048228,0.0006558,0.0004645702,0.002708879],"domain_scores_gemma":[0.9983667,0.0004335405,0.0004310505,0.0002093193,0.000285172,0.0002742112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003385867,0.000282973,0.0008701252,0.00003719073,0.00330955,0.00006200278,0.02017431,0.08245129,0.003976591,0.6904739,0.0003223347,0.1977012],"study_design_scores_gemma":[0.004331913,0.0007657469,0.0003298285,0.00001163894,0.0002076174,0.0002844171,0.0145984,0.8480518,0.0001731209,0.1137248,0.01691001,0.0006106667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03215714,0.001202954,0.9646833,0.0006607781,0.0001817756,0.0004182787,0.000003774033,0.000364834,0.0003271454],"genre_scores_gemma":[0.9570519,0.001283827,0.03186921,0.0002420252,0.0001768275,0.00008959229,0.00002774958,0.00008448734,0.009174337],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9328141,"threshold_uncertainty_score":0.9999067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06906769261902579,"score_gpt":0.3132469360734912,"score_spread":0.2441792434544655,"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."}}