{"id":"W3122996481","doi":"10.48550/arxiv.2101.09825","title":"Improving Few-Shot Learning with Auxiliary Self-Supervised Pretext Tasks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Leverage (statistics); Pretext; Exploit; Machine learning; Complementarity (molecular biology); Artificial intelligence; Supervised learning; Task (project management); Training set; Semi-supervised learning; Class (philosophy); Labeled data","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":[0.0004672889,0.0005356453,0.0005105618,0.0003388134,0.0004897091,0.0006778123,0.001843652,0.0003825516,0.0001405567],"category_scores_gemma":[0.0000853546,0.0006003767,0.0002624574,0.0009829659,0.0001048632,0.0009355543,0.002281002,0.00179183,0.00009137392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003042333,"about_ca_system_score_gemma":0.0007513395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001995226,"about_ca_topic_score_gemma":0.00005057519,"domain_scores_codex":[0.9964451,0.0004886907,0.0003023166,0.001857972,0.0002596809,0.0006462046],"domain_scores_gemma":[0.997349,0.0001927566,0.0004281054,0.001357028,0.0003353593,0.0003378159],"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":[0.0001183932,0.0003012521,0.01257279,0.0005322252,0.0005493207,0.003152322,0.007988631,0.9239621,0.0007845718,0.03426403,0.0001070445,0.01566729],"study_design_scores_gemma":[0.0009619707,0.0001315065,0.001396017,0.0001961288,0.0001054243,0.00002747583,0.00135211,0.9932245,0.0001374431,0.000387272,0.0012152,0.0008649637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2589345,0.0001229807,0.7306683,0.00007932465,0.0004114453,0.0003323421,0.000002248094,0.000918552,0.008530315],"genre_scores_gemma":[0.9666789,0.0001027725,0.02966348,0.0001968211,0.00008156922,0.000002870804,0.00004318361,0.00005110365,0.00317927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7077444,"threshold_uncertainty_score":0.9996448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05132379531189979,"score_gpt":0.1775479464571536,"score_spread":0.1262241511452538,"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."}}