{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FGOZ2KNYL47LWWEU3773ACAIYA","short_pith_number":"pith:FGOZ2KNY","schema_version":"1.0","canonical_sha256":"299d9d29b85f3ebb5894dfffb00808c00d245a6f39c4e3f36f27d725fad55e57","source":{"kind":"arxiv","id":"2407.16611","version":1},"attestation_state":"computed","paper":{"title":"Local vs Global continual learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin F. Grewe, Giulia Lanzillotta, Sidak Pal Singh, Thomas Hofmann","submitted_at":"2024-07-23T16:18:00Z","abstract_excerpt":"Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent years, the problem of continual learning is still an open one. A better understanding of the mechanisms behind the successes and failures of existing continual learning algorithms can unlock the development of new successful strategies. In this work, we view continual learning from the perspective of the multi-task loss approximation, and we compare two alternative strategies, namely local and global approximations."},"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":"2407.16611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-23T16:18:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c33d02361750abd23b232a6299b868fb090b6f5fc235b6d237ab50b72e42445c","abstract_canon_sha256":"5d9fd6fdf4dfc4c97d31868951b09408bfc10ec41e172adbcba26240c3a8b814"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:35.792230Z","signature_b64":"k2mLIQgBVo4vsZpbiGya1DqzJusX4D6xhnRJr+BHBuhdMFWsvL1If4/T8ZweNtnlC2guP07mOk3TSSGDuru8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"299d9d29b85f3ebb5894dfffb00808c00d245a6f39c4e3f36f27d725fad55e57","last_reissued_at":"2026-07-05T08:47:35.791763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:35.791763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local vs Global continual learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin F. Grewe, Giulia Lanzillotta, Sidak Pal Singh, Thomas Hofmann","submitted_at":"2024-07-23T16:18:00Z","abstract_excerpt":"Continual learning is the problem of integrating new information in a model while retaining the knowledge acquired in the past. Despite the tangible improvements achieved in recent years, the problem of continual learning is still an open one. A better understanding of the mechanisms behind the successes and failures of existing continual learning algorithms can unlock the development of new successful strategies. In this work, we view continual learning from the perspective of the multi-task loss approximation, and we compare two alternative strategies, namely local and global approximations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16611","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/2407.16611/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":"2407.16611","created_at":"2026-07-05T08:47:35.791824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16611v1","created_at":"2026-07-05T08:47:35.791824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16611","created_at":"2026-07-05T08:47:35.791824+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGOZ2KNYL47L","created_at":"2026-07-05T08:47:35.791824+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGOZ2KNYL47LWWEU","created_at":"2026-07-05T08:47:35.791824+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGOZ2KNY","created_at":"2026-07-05T08:47:35.791824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05609","citing_title":"To Retain or to Adapt? Generalizing Continual Learning","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA","json":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA.json","graph_json":"https://pith.science/api/pith-number/FGOZ2KNYL47LWWEU3773ACAIYA/graph.json","events_json":"https://pith.science/api/pith-number/FGOZ2KNYL47LWWEU3773ACAIYA/events.json","paper":"https://pith.science/paper/FGOZ2KNY"},"agent_actions":{"view_html":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA","download_json":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA.json","view_paper":"https://pith.science/paper/FGOZ2KNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16611&json=true","fetch_graph":"https://pith.science/api/pith-number/FGOZ2KNYL47LWWEU3773ACAIYA/graph.json","fetch_events":"https://pith.science/api/pith-number/FGOZ2KNYL47LWWEU3773ACAIYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA/action/storage_attestation","attest_author":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA/action/author_attestation","sign_citation":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA/action/citation_signature","submit_replication":"https://pith.science/pith/FGOZ2KNYL47LWWEU3773ACAIYA/action/replication_record"}},"created_at":"2026-07-05T08:47:35.791824+00:00","updated_at":"2026-07-05T08:47:35.791824+00:00"}