{"id":"W2964026991","doi":"","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":203,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Shot (pellet); Meta learning (computer science); Machine learning; Supervised learning; Pattern recognition (psychology); Task (project management); Engineering; Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.0004164807,0.000160129,0.0001998015,0.0001672214,0.0004584618,0.0001246529,0.0007198473,0.00008582165,0.0001589794],"category_scores_gemma":[0.00009153694,0.0001686486,0.0001890842,0.0007232167,0.0001043691,0.0006843685,0.0001274782,0.0001595084,0.0002750341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006890851,"about_ca_system_score_gemma":0.00006282481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277668,"about_ca_topic_score_gemma":0.00001122298,"domain_scores_codex":[0.9986907,0.000145333,0.0001566104,0.0006099342,0.00008656258,0.000310913],"domain_scores_gemma":[0.9988078,0.0001982276,0.0001411535,0.0004599851,0.0002519618,0.0001408441],"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":[0.00009767344,0.0001175672,0.002465189,0.00002838647,0.0005782939,0.00002494513,0.00196556,0.02213953,0.004982813,0.9588682,0.001126117,0.007605711],"study_design_scores_gemma":[0.0006495261,0.0001504913,0.001625987,0.000005582046,0.0001654392,0.000002683723,0.0003530032,0.9577838,0.0004631116,0.003999951,0.03455585,0.0002445503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03819903,0.00002245507,0.9502466,0.0002538606,0.0002053902,0.0001959271,0.000001077566,0.0003054049,0.01057021],"genre_scores_gemma":[0.9847363,0.00001497673,0.007814325,0.0002998265,0.00008952367,0.00000250277,0.000007862644,0.00001410675,0.007020599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9548683,"threshold_uncertainty_score":0.6877289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2584993892308796,"score_gpt":0.2278402295002752,"score_spread":0.03065915973060446,"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."}}