{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GDQNQYGZLWITF5RDROAHEYEB5V","short_pith_number":"pith:GDQNQYGZ","schema_version":"1.0","canonical_sha256":"30e0d860d95d9132f6238b80726081ed46f67c18bd670255d34b0baaf18cb7ae","source":{"kind":"arxiv","id":"2606.08452","version":1},"attestation_state":"computed","paper":{"title":"Theoretical Foundations of Continual Learning via Drift-Plus-Penalty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bharath B.N., Govinda Arya, Nazreen Shah, Ranjitha Prasad","submitted_at":"2026-06-07T04:51:32Z","abstract_excerpt":"In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch. Continual learning (CL) addresses this challenge by incorporating new tasks while mitigating catastrophic forgetting, where learning new information degrades performance on previously acquired knowledge. We introduce a control-theoretic perspective on CL that explicitly regulates the evolution of forgetting, framing adaptation as a controlled process subject to long-term stability constraints. We focus on replay-based CL, where a"},"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":"2606.08452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-07T04:51:32Z","cross_cats_sorted":[],"title_canon_sha256":"c980c01fc1d6723d1b3ed6d577df928708a04cf01dd0c52b8eb49adf57ac9cb7","abstract_canon_sha256":"1c847cba1593759879d79519fad26e623b85a4ccf3dd7c87c75bacac702e54f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:37.031947Z","signature_b64":"aU56UevMB8YD5PRrOvT61e/9UoUsB2Jnz0wzhBv2jknldkfifJ+zzrmvBqv5UTbak4Grku0aNGlbA9dtATQGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e0d860d95d9132f6238b80726081ed46f67c18bd670255d34b0baaf18cb7ae","last_reissued_at":"2026-06-09T01:05:37.031551Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:37.031551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Foundations of Continual Learning via Drift-Plus-Penalty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bharath B.N., Govinda Arya, Nazreen Shah, Ranjitha Prasad","submitted_at":"2026-06-07T04:51:32Z","abstract_excerpt":"In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch. Continual learning (CL) addresses this challenge by incorporating new tasks while mitigating catastrophic forgetting, where learning new information degrades performance on previously acquired knowledge. We introduce a control-theoretic perspective on CL that explicitly regulates the evolution of forgetting, framing adaptation as a controlled process subject to long-term stability constraints. We focus on replay-based CL, where a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08452","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/2606.08452/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":"2606.08452","created_at":"2026-06-09T01:05:37.031614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08452v1","created_at":"2026-06-09T01:05:37.031614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08452","created_at":"2026-06-09T01:05:37.031614+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDQNQYGZLWIT","created_at":"2026-06-09T01:05:37.031614+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDQNQYGZLWITF5RD","created_at":"2026-06-09T01:05:37.031614+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDQNQYGZ","created_at":"2026-06-09T01:05:37.031614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V","json":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V.json","graph_json":"https://pith.science/api/pith-number/GDQNQYGZLWITF5RDROAHEYEB5V/graph.json","events_json":"https://pith.science/api/pith-number/GDQNQYGZLWITF5RDROAHEYEB5V/events.json","paper":"https://pith.science/paper/GDQNQYGZ"},"agent_actions":{"view_html":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V","download_json":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V.json","view_paper":"https://pith.science/paper/GDQNQYGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08452&json=true","fetch_graph":"https://pith.science/api/pith-number/GDQNQYGZLWITF5RDROAHEYEB5V/graph.json","fetch_events":"https://pith.science/api/pith-number/GDQNQYGZLWITF5RDROAHEYEB5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V/action/storage_attestation","attest_author":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V/action/author_attestation","sign_citation":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V/action/citation_signature","submit_replication":"https://pith.science/pith/GDQNQYGZLWITF5RDROAHEYEB5V/action/replication_record"}},"created_at":"2026-06-09T01:05:37.031614+00:00","updated_at":"2026-06-09T01:05:37.031614+00:00"}