{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CMXRPNHWNZR4RGUAHPJUXH64QA","short_pith_number":"pith:CMXRPNHW","schema_version":"1.0","canonical_sha256":"132f17b4f66e63c89a803bd34b9fdc80110a08f46ab09b9e9860bac019ac7156","source":{"kind":"arxiv","id":"2403.05175","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning and Catastrophic Forgetting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dhireesha Kudithipudi, Gido M. van de Ven, Nicholas Soures","submitted_at":"2024-03-08T09:32:43Z","abstract_excerpt":"This book chapter delves into the dynamics of continual learning, which is the process of incrementally learning from a non-stationary stream of data. Although continual learning is a natural skill for the human brain, it is very challenging for artificial neural networks. An important reason is that, when learning something new, these networks tend to quickly and drastically forget what they had learned before, a phenomenon known as catastrophic forgetting. Especially in the last decade, continual learning has become an extensively studied topic in deep learning. This book chapter reviews the"},"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":"2403.05175","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-08T09:32:43Z","cross_cats_sorted":["cs.AI","cs.CV","q-bio.NC","stat.ML"],"title_canon_sha256":"9ab0eccb26ba269b124067b33879ccbd9c39030c3aca0d5dc2453408fc565dbf","abstract_canon_sha256":"24b426548f15788201c824b036a82beea811096d96a353e78546f9b228679478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:53.381769Z","signature_b64":"ZEJ9asf2S1t05FcIR9nLiwxWT07AJrLlSDpDD+KCyZszdQaBt3fDt3SJ4Urli2T0qh1WmddDubDjyj4b46PUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"132f17b4f66e63c89a803bd34b9fdc80110a08f46ab09b9e9860bac019ac7156","last_reissued_at":"2026-07-05T12:07:53.381307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:53.381307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning and Catastrophic Forgetting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","q-bio.NC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dhireesha Kudithipudi, Gido M. van de Ven, Nicholas Soures","submitted_at":"2024-03-08T09:32:43Z","abstract_excerpt":"This book chapter delves into the dynamics of continual learning, which is the process of incrementally learning from a non-stationary stream of data. Although continual learning is a natural skill for the human brain, it is very challenging for artificial neural networks. An important reason is that, when learning something new, these networks tend to quickly and drastically forget what they had learned before, a phenomenon known as catastrophic forgetting. Especially in the last decade, continual learning has become an extensively studied topic in deep learning. This book chapter reviews the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05175","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/2403.05175/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":"2403.05175","created_at":"2026-07-05T12:07:53.381375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05175v1","created_at":"2026-07-05T12:07:53.381375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05175","created_at":"2026-07-05T12:07:53.381375+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMXRPNHWNZR4","created_at":"2026-07-05T12:07:53.381375+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMXRPNHWNZR4RGUA","created_at":"2026-07-05T12:07:53.381375+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMXRPNHW","created_at":"2026-07-05T12:07:53.381375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19993","citing_title":"Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05285","citing_title":"Toward decision-aware AI for LSST-scale time-domain astronomy","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17830","citing_title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2601.13844","citing_title":"Optimal L2 Regularization in High-dimensional Continual Linear Regression","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09608","citing_title":"Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23954","citing_title":"An empirical evaluation of the risks of AI model updates using clinical data: stability, arbitrariness, and fairness","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05776","citing_title":"HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20721","citing_title":"ALAS: Adaptive Long-Horizon Action Synthesis via Async-pathway Stream Disentanglement","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06894","citing_title":"McNdroid: A Longitudinal Multimodal Benchmark for Robust Drift Detection in Android Malware","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16496","citing_title":"Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18857","citing_title":"Task Switching Without Forgetting via Proximal Decoupling","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA","json":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA.json","graph_json":"https://pith.science/api/pith-number/CMXRPNHWNZR4RGUAHPJUXH64QA/graph.json","events_json":"https://pith.science/api/pith-number/CMXRPNHWNZR4RGUAHPJUXH64QA/events.json","paper":"https://pith.science/paper/CMXRPNHW"},"agent_actions":{"view_html":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA","download_json":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA.json","view_paper":"https://pith.science/paper/CMXRPNHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05175&json=true","fetch_graph":"https://pith.science/api/pith-number/CMXRPNHWNZR4RGUAHPJUXH64QA/graph.json","fetch_events":"https://pith.science/api/pith-number/CMXRPNHWNZR4RGUAHPJUXH64QA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA/action/storage_attestation","attest_author":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA/action/author_attestation","sign_citation":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA/action/citation_signature","submit_replication":"https://pith.science/pith/CMXRPNHWNZR4RGUAHPJUXH64QA/action/replication_record"}},"created_at":"2026-07-05T12:07:53.381375+00:00","updated_at":"2026-07-05T12:07:53.381375+00:00"}