{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NK64GHACPZRKFDUUFAAV7H5S4O","short_pith_number":"pith:NK64GHAC","schema_version":"1.0","canonical_sha256":"6abdc31c027e62a28e9428015f9fb2e3b95e1b116f8fcc01e00d432164c21c01","source":{"kind":"arxiv","id":"2404.04002","version":2},"attestation_state":"computed","paper":{"title":"Continual Learning with Weight Interpolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bartosz Krawczyk, Jan Wasilewski, J\\k{e}drzej Kozal, Micha{\\l} Wo\\'zniak","submitted_at":"2024-04-05T10:25:40Z","abstract_excerpt":"Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient algorithms capable of learning from data streams and accumulating knowledge over time. This paper proposes a novel approach to continual learning utilizing the weight consolidation method. Our method, a simple yet powerful technique, enhances robustness against catastrophic forgetting by interpolating between old and new model weights after each novel task, e"},"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":"2404.04002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T10:25:40Z","cross_cats_sorted":[],"title_canon_sha256":"7daf5a7538c8111d338f9c803dc6b46ce9a2eedbd20a3d730629cc08a8c9ef02","abstract_canon_sha256":"930b5bb6b9bb107a905bf9d17ab9c8461fdca191cabb92b11b129015f8f2f84b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:58.076712Z","signature_b64":"JI6PGEUI7HfDwTEWVqOcOqrUs+c0tN1UJu1CKYUP+MPD05Z3JhpzFH9+xrb+5i7qlBIoP0KysfkVfZlda/qgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6abdc31c027e62a28e9428015f9fb2e3b95e1b116f8fcc01e00d432164c21c01","last_reissued_at":"2026-07-05T08:05:58.076285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:58.076285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning with Weight Interpolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bartosz Krawczyk, Jan Wasilewski, J\\k{e}drzej Kozal, Micha{\\l} Wo\\'zniak","submitted_at":"2024-04-05T10:25:40Z","abstract_excerpt":"Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient algorithms capable of learning from data streams and accumulating knowledge over time. This paper proposes a novel approach to continual learning utilizing the weight consolidation method. Our method, a simple yet powerful technique, enhances robustness against catastrophic forgetting by interpolating between old and new model weights after each novel task, e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04002","kind":"arxiv","version":2},"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/2404.04002/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":"2404.04002","created_at":"2026-07-05T08:05:58.076353+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04002v2","created_at":"2026-07-05T08:05:58.076353+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04002","created_at":"2026-07-05T08:05:58.076353+00:00"},{"alias_kind":"pith_short_12","alias_value":"NK64GHACPZRK","created_at":"2026-07-05T08:05:58.076353+00:00"},{"alias_kind":"pith_short_16","alias_value":"NK64GHACPZRKFDUU","created_at":"2026-07-05T08:05:58.076353+00:00"},{"alias_kind":"pith_short_8","alias_value":"NK64GHAC","created_at":"2026-07-05T08:05:58.076353+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/NK64GHACPZRKFDUUFAAV7H5S4O","json":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O.json","graph_json":"https://pith.science/api/pith-number/NK64GHACPZRKFDUUFAAV7H5S4O/graph.json","events_json":"https://pith.science/api/pith-number/NK64GHACPZRKFDUUFAAV7H5S4O/events.json","paper":"https://pith.science/paper/NK64GHAC"},"agent_actions":{"view_html":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O","download_json":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O.json","view_paper":"https://pith.science/paper/NK64GHAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04002&json=true","fetch_graph":"https://pith.science/api/pith-number/NK64GHACPZRKFDUUFAAV7H5S4O/graph.json","fetch_events":"https://pith.science/api/pith-number/NK64GHACPZRKFDUUFAAV7H5S4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O/action/storage_attestation","attest_author":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O/action/author_attestation","sign_citation":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O/action/citation_signature","submit_replication":"https://pith.science/pith/NK64GHACPZRKFDUUFAAV7H5S4O/action/replication_record"}},"created_at":"2026-07-05T08:05:58.076353+00:00","updated_at":"2026-07-05T08:05:58.076353+00:00"}