{"id":"W3131265523","doi":"10.48550/arxiv.2102.06253","title":"Continuum: Simple Management of Complex Continual Learning Scenarios","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Loader; Field (mathematics); Machine learning; Key (lock); Simple (philosophy); Data pre-processing; Preprocessor; Artificial intelligence; Set (abstract data type); Data mining; Test data; Software engineering","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":[0.0003775196,0.0002975301,0.0004850367,0.0002165624,0.0001810757,0.0001946062,0.001395848,0.0001809151,0.0002033747],"category_scores_gemma":[0.00002854939,0.0003797197,0.0002683894,0.0005969706,0.000119943,0.0002863075,0.002605469,0.0006762982,0.00004344531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001056908,"about_ca_system_score_gemma":0.0001047532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008751445,"about_ca_topic_score_gemma":0.00003772406,"domain_scores_codex":[0.9978154,0.0002991647,0.0003373791,0.0009901006,0.000175577,0.0003823859],"domain_scores_gemma":[0.998112,0.0001119967,0.0004949545,0.0008520425,0.0002755018,0.0001534897],"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":[0.00007045618,0.0003212443,0.01027463,0.000618024,0.0008067613,0.002136305,0.003030944,0.7085423,0.0005654439,0.2578233,0.001070507,0.01474006],"study_design_scores_gemma":[0.001974774,0.0001022309,0.01869552,0.0003924413,0.0001604273,0.000009739779,0.004604921,0.9507253,0.000207503,0.004204141,0.01798449,0.0009385481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2509418,0.00006051658,0.7332659,0.00005336774,0.0003064314,0.0002530905,0.000003732298,0.0002258475,0.01488939],"genre_scores_gemma":[0.984681,0.0001242492,0.009243228,0.00007999611,0.00002956788,8.837314e-7,0.00006170761,0.00001941354,0.005759958],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7337393,"threshold_uncertainty_score":0.9998655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08511764575923818,"score_gpt":0.2045172860039454,"score_spread":0.1193996402447072,"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."}}