{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:523G7N5VDQIQOZDAONRF5ZQIME","short_pith_number":"pith:523G7N5V","schema_version":"1.0","canonical_sha256":"eeb66fb7b51c1107646073625ee608612fc769b95989269992f09e47d3a0a064","source":{"kind":"arxiv","id":"2411.14202","version":1},"attestation_state":"computed","paper":{"title":"Revised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Biplab Banerjee, Sanchar Palit, Subhasis Chaudhuri","submitted_at":"2024-11-21T15:11:02Z","abstract_excerpt":"We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each step to retain knowledge poses challenges. This is compounded by the crucial need to mitigate catastrophic forgetting, particularly given the limited access to past datasets, which complicates maintaining correspondence between network parameters and datasets across all sessions. Current methods using Variational Inference with KL divergence risk catastroph"},"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":"2411.14202","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T15:11:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"13d18f2fe921a2d6b9930c0764d3501f9be64f3e0398e72e661e7781e8719a3b","abstract_canon_sha256":"b04fc8e6aef61f3de66cdc118037ad3f9f20a02fd6656f15e45da9ac69ea15e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:43.253992Z","signature_b64":"mUr4NcrrkhzJ96xuunFbcssFP92Ayih8X6gp1ZSX15mI1OU7XLYl7J9yvdJT1K2iMQ1bfO3jwdBnUXvwFQwgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb66fb7b51c1107646073625ee608612fc769b95989269992f09e47d3a0a064","last_reissued_at":"2026-07-05T09:38:43.253498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:43.253498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Biplab Banerjee, Sanchar Palit, Subhasis Chaudhuri","submitted_at":"2024-11-21T15:11:02Z","abstract_excerpt":"We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each step to retain knowledge poses challenges. This is compounded by the crucial need to mitigate catastrophic forgetting, particularly given the limited access to past datasets, which complicates maintaining correspondence between network parameters and datasets across all sessions. Current methods using Variational Inference with KL divergence risk catastroph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14202","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/2411.14202/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":"2411.14202","created_at":"2026-07-05T09:38:43.253557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14202v1","created_at":"2026-07-05T09:38:43.253557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14202","created_at":"2026-07-05T09:38:43.253557+00:00"},{"alias_kind":"pith_short_12","alias_value":"523G7N5VDQIQ","created_at":"2026-07-05T09:38:43.253557+00:00"},{"alias_kind":"pith_short_16","alias_value":"523G7N5VDQIQOZDA","created_at":"2026-07-05T09:38:43.253557+00:00"},{"alias_kind":"pith_short_8","alias_value":"523G7N5V","created_at":"2026-07-05T09:38:43.253557+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/523G7N5VDQIQOZDAONRF5ZQIME","json":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME.json","graph_json":"https://pith.science/api/pith-number/523G7N5VDQIQOZDAONRF5ZQIME/graph.json","events_json":"https://pith.science/api/pith-number/523G7N5VDQIQOZDAONRF5ZQIME/events.json","paper":"https://pith.science/paper/523G7N5V"},"agent_actions":{"view_html":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME","download_json":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME.json","view_paper":"https://pith.science/paper/523G7N5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14202&json=true","fetch_graph":"https://pith.science/api/pith-number/523G7N5VDQIQOZDAONRF5ZQIME/graph.json","fetch_events":"https://pith.science/api/pith-number/523G7N5VDQIQOZDAONRF5ZQIME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME/action/storage_attestation","attest_author":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME/action/author_attestation","sign_citation":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME/action/citation_signature","submit_replication":"https://pith.science/pith/523G7N5VDQIQOZDAONRF5ZQIME/action/replication_record"}},"created_at":"2026-07-05T09:38:43.253557+00:00","updated_at":"2026-07-05T09:38:43.253557+00:00"}