{"id":"W4225620948","doi":"10.48550/arxiv.2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Forgetting; Computer science; Lifelong learning; Artificial intelligence; Context (archaeology); Task (project management); Machine learning; Popularity; Set (abstract data type); Variety (cybernetics); Training (meteorology); Cognitive psychology; Psychology; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008888658,0.0008801389,0.0007595685,0.0005449698,0.0008791659,0.001179873,0.001668865,0.001534916,0.001886968],"category_scores_gemma":[0.06778619,0.0003600406,0.0005083307,0.0007312431,0.001433742,0.004257157,0.001544968,0.003231346,0.0005312825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009141667,"about_ca_system_score_gemma":0.0008124367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003098602,"about_ca_topic_score_gemma":0.005327322,"domain_scores_codex":[0.9975905,0.001262333,0.0001449849,0.0005194522,0.0002827221,0.0002000436],"domain_scores_gemma":[0.9392347,0.04700454,0.002453528,0.007750722,0.00219685,0.001359586],"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":[0.002070546,0.002095333,0.1238289,0.001418543,0.0004427457,0.0004652606,0.001099475,0.3655855,0.006658011,0.01307246,0.01651191,0.4667513],"study_design_scores_gemma":[0.0001990271,0.001902591,0.03685848,0.0002650603,0.0001388874,0.0006102278,0.0006712644,0.910575,0.007737376,0.03444931,0.006500309,0.00009238617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8969706,0.005839295,0.08839776,0.001646161,0.0001374042,0.0001718443,0.0004995528,0.0008608407,0.0054766],"genre_scores_gemma":[0.9825321,0.000421658,0.01528785,0.0002433983,0.00003678066,0.00007268217,0.0004872591,0.00009212673,0.000826098],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008888658,"threshold_uncertainty_score":0.04700828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07271094776994619,"score_gpt":0.2187424208096863,"score_spread":0.1460314730397401,"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."}}