{"id":"W3118797298","doi":"","title":"Exploring representation learning for flexible few-shot tasks","year":2021,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Flexibility (engineering); Representation (politics); Task (project management); Benchmark (surveying); Class (philosophy); Set (abstract data type); Machine learning; Feature learning; Context (archaeology); Feature (linguistics); Shot (pellet); Mathematics","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":[0.0003021056,0.0001000944,0.0001256887,0.00008867872,0.0002812147,0.0003307087,0.0002527087,0.00003097754,0.000129782],"category_scores_gemma":[0.0003560363,0.0001054686,0.00008744955,0.0005031292,0.00001353147,0.001091941,0.0001376558,0.0001442129,0.00009753569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003121843,"about_ca_system_score_gemma":0.00007255374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001442434,"about_ca_topic_score_gemma":0.000004254156,"domain_scores_codex":[0.9987744,0.00008596462,0.0002142942,0.0004267433,0.0002313057,0.0002672604],"domain_scores_gemma":[0.9991003,0.0002488476,0.00007313553,0.0003127599,0.0001760448,0.00008888866],"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":[0.00002744542,0.0001021838,0.002260253,0.00005467547,0.00006133279,0.00004803899,0.006735175,0.04728292,0.04322692,0.4778043,0.002461611,0.4199351],"study_design_scores_gemma":[0.001731912,0.0001586058,0.005920938,0.00005406171,0.00001598124,0.00005287009,0.005547981,0.5621657,0.150024,0.00580059,0.2678604,0.0006669984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007841476,0.00005610533,0.9584684,0.001127494,0.0004504029,0.0001126563,1.973837e-7,0.0005081141,0.03143518],"genre_scores_gemma":[0.72262,0.00005969758,0.2469102,0.0006966429,0.0001645728,0.000131233,0.00002652887,0.0000217815,0.0293693],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7147785,"threshold_uncertainty_score":0.4300885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3081980911387858,"score_gpt":0.34669765633298,"score_spread":0.03849956519419423,"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."}}