{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GTYJ7SXECF3E3HCLWZGQRIHLNY","short_pith_number":"pith:GTYJ7SXE","schema_version":"1.0","canonical_sha256":"34f09fcae411764d9c4bb64d08a0eb6e1a6031beeff032f3f718d0b8740b80d9","source":{"kind":"arxiv","id":"2302.05836","version":1},"attestation_state":"computed","paper":{"title":"Theory on Forgetting and Generalization of Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ness Shroff, Peizhong Ju, Sen Lin, Yingbin Liang","submitted_at":"2023-02-12T02:14:14Z","abstract_excerpt":"Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL, and theoretical studies of CL are still limited. In particular, there is a lack of understanding on what factors are important and how they affect \"catastrophic forgetting\" and generalization performance. To fill this gap, our theoretical analysis, under overparameterized linear models, provides the first-known explicit form of the expected forgetting and generalization error. Further analysis of such a key result yi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.05836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-12T02:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"2b1c0c9b760186724edca05afcd7a81380bffd693ac36a533d041471e7f62825","abstract_canon_sha256":"8403aa7e5ec12cc973dd762d354e092fc03991823ef8b7150fd39bb8cf985379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:58.762020Z","signature_b64":"eNsdn4wLTJCGkoi5NgvjTFJjNNoijDhngbHu6uAkSKITpUXrNIWaYkUMWbICBQsAjTExvEsiQ+jAynWSwQY8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34f09fcae411764d9c4bb64d08a0eb6e1a6031beeff032f3f718d0b8740b80d9","last_reissued_at":"2026-07-05T05:40:58.761636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:58.761636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theory on Forgetting and Generalization of Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ness Shroff, Peizhong Ju, Sen Lin, Yingbin Liang","submitted_at":"2023-02-12T02:14:14Z","abstract_excerpt":"Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL, and theoretical studies of CL are still limited. In particular, there is a lack of understanding on what factors are important and how they affect \"catastrophic forgetting\" and generalization performance. To fill this gap, our theoretical analysis, under overparameterized linear models, provides the first-known explicit form of the expected forgetting and generalization error. Further analysis of such a key result yi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05836","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.05836/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.05836","created_at":"2026-07-05T05:40:58.761693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05836v1","created_at":"2026-07-05T05:40:58.761693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05836","created_at":"2026-07-05T05:40:58.761693+00:00"},{"alias_kind":"pith_short_12","alias_value":"GTYJ7SXECF3E","created_at":"2026-07-05T05:40:58.761693+00:00"},{"alias_kind":"pith_short_16","alias_value":"GTYJ7SXECF3E3HCL","created_at":"2026-07-05T05:40:58.761693+00:00"},{"alias_kind":"pith_short_8","alias_value":"GTYJ7SXE","created_at":"2026-07-05T05:40:58.761693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18231","citing_title":"Towards Macro-AUC oriented Imbalanced Multi-Label Continual Learning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY","json":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY.json","graph_json":"https://pith.science/api/pith-number/GTYJ7SXECF3E3HCLWZGQRIHLNY/graph.json","events_json":"https://pith.science/api/pith-number/GTYJ7SXECF3E3HCLWZGQRIHLNY/events.json","paper":"https://pith.science/paper/GTYJ7SXE"},"agent_actions":{"view_html":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY","download_json":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY.json","view_paper":"https://pith.science/paper/GTYJ7SXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05836&json=true","fetch_graph":"https://pith.science/api/pith-number/GTYJ7SXECF3E3HCLWZGQRIHLNY/graph.json","fetch_events":"https://pith.science/api/pith-number/GTYJ7SXECF3E3HCLWZGQRIHLNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY/action/storage_attestation","attest_author":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY/action/author_attestation","sign_citation":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY/action/citation_signature","submit_replication":"https://pith.science/pith/GTYJ7SXECF3E3HCLWZGQRIHLNY/action/replication_record"}},"created_at":"2026-07-05T05:40:58.761693+00:00","updated_at":"2026-07-05T05:40:58.761693+00:00"}