{"id":"W4399554982","doi":"10.48550/arxiv.2406.05631","title":"CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Impression; Class (philosophy); Computer science; Psychology; Artificial intelligence; World Wide Web","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004754797,0.0003960588,0.0003767574,0.0004283577,0.0002877135,0.000565751,0.006800949,0.000482546,0.00003799588],"category_scores_gemma":[0.0001372039,0.0004215608,0.0002007537,0.000513182,0.0001890476,0.0006842327,0.01915888,0.001120179,0.0001569827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000285675,"about_ca_system_score_gemma":0.0001750311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003908186,"about_ca_topic_score_gemma":0.00002362751,"domain_scores_codex":[0.9969453,0.0001038609,0.0003383677,0.001978428,0.0001767171,0.0004573347],"domain_scores_gemma":[0.9956885,0.0002398908,0.0003563335,0.003457032,0.0001439757,0.000114248],"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":[0.00007069651,0.0001205835,0.0005847074,0.0001878159,0.0001634657,0.0000961945,0.000208792,0.002674678,0.001366233,0.8904415,0.08482052,0.01926483],"study_design_scores_gemma":[0.001181143,0.000136043,0.0001909886,0.0002165766,0.00009796947,0.000004379716,0.0005736719,0.613084,0.001732684,0.1440545,0.2379145,0.000813507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07548391,0.000936283,0.9066275,0.002622754,0.003094809,0.001243143,0.0002760437,0.003609697,0.006105865],"genre_scores_gemma":[0.9873415,0.0004579672,0.005397283,0.00004668996,0.0001350823,0.000007786232,0.0002957777,0.00003420766,0.00628372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9118576,"threshold_uncertainty_score":0.9998236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1322242034962122,"score_gpt":0.2323602036804696,"score_spread":0.1001360001842574,"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."}}