{"id":"W4221159290","doi":"10.48550/arxiv.2203.13381","title":"Probing Representation Forgetting in Supervised and Unsupervised Continual Learning","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Forgetting; Representation (politics); Computer science; Artificial intelligence; Task (project management); Classifier (UML); Machine learning; 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":[0.006330721,0.0008022602,0.0009893501,0.000704504,0.0005064592,0.001065758,0.002065911,0.001462348,0.0007790092],"category_scores_gemma":[0.04181553,0.0004084932,0.0004985228,0.000544527,0.002340769,0.003384148,0.001990356,0.002457328,0.0001626959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217741,"about_ca_system_score_gemma":0.0008050661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00180867,"about_ca_topic_score_gemma":0.001847678,"domain_scores_codex":[0.9980026,0.0006655948,0.0001181625,0.0006329238,0.000417704,0.0001630928],"domain_scores_gemma":[0.9755657,0.01593448,0.002115204,0.004470935,0.001256259,0.0006574804],"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":[0.001079813,0.0008385264,0.02222232,0.0005721147,0.0002722775,0.000252229,0.0007274545,0.6996227,0.01617629,0.0209494,0.002036332,0.2352505],"study_design_scores_gemma":[0.00002106087,0.0003250135,0.003588014,0.00002639625,0.0000191179,0.0001073843,0.00005758206,0.9620641,0.007841563,0.02545355,0.0004646759,0.00003148729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5892345,0.00112753,0.4059384,0.0005739784,0.00007592214,0.00009913018,0.0001943623,0.0009252324,0.001830999],"genre_scores_gemma":[0.9687107,0.0001259935,0.0301288,0.00008337851,0.00003244996,0.00005959839,0.0002019755,0.00006010513,0.0005970441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006330721,"threshold_uncertainty_score":0.03348041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07666561706497431,"score_gpt":0.208297278180521,"score_spread":0.1316316611155467,"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."}}