{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QMNNS74KCTKQKP5YL3ELBCV2FQ","short_pith_number":"pith:QMNNS74K","schema_version":"1.0","canonical_sha256":"831ad97f8a14d5053fb85ec8b08aba2c320a855bc52e7b69b1d760252b014cc5","source":{"kind":"arxiv","id":"2106.05390","version":3},"attestation_state":"computed","paper":{"title":"Optimizing Reusable Knowledge for Continual Learning via Metalearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alain Raymond-Saez, Alvaro Soto, Julio Hurtado","submitted_at":"2021-06-09T21:09:21Z","abstract_excerpt":"When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing forgetting of old information. To address this issue, we propose MetA Reusable Knowledge or MARK, a new method that fosters weight reusability instead of overwriting when learning a new task. Specifically, MARK keeps a set of shared weights among tasks. We envision these shared weights as a common Knowledge Base (KB) that is not only used to learn new tasks, but also enriched w"},"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":"2106.05390","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T21:09:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d59839f1bdbf43b9cfbf54581964960eaad54f3974391d08c4fc8dbe5375f2e9","abstract_canon_sha256":"0ca04a8b336091f4a926452290e30c228f513142d49d44de3b7a2f73ea2e5197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:38.195948Z","signature_b64":"J4tRDhavQ934kiu3ecRAEXsU/wiEf+JphNrLAi6Q/gHFG4VmXz5v2YFJ9hEqEhyg5ywqvpslbuPub8ZghiXIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"831ad97f8a14d5053fb85ec8b08aba2c320a855bc52e7b69b1d760252b014cc5","last_reissued_at":"2026-07-05T03:36:38.195482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:38.195482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Reusable Knowledge for Continual Learning via Metalearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alain Raymond-Saez, Alvaro Soto, Julio Hurtado","submitted_at":"2021-06-09T21:09:21Z","abstract_excerpt":"When learning tasks over time, artificial neural networks suffer from a problem known as Catastrophic Forgetting (CF). This happens when the weights of a network are overwritten during the training of a new task causing forgetting of old information. To address this issue, we propose MetA Reusable Knowledge or MARK, a new method that fosters weight reusability instead of overwriting when learning a new task. Specifically, MARK keeps a set of shared weights among tasks. We envision these shared weights as a common Knowledge Base (KB) that is not only used to learn new tasks, but also enriched w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05390","kind":"arxiv","version":3},"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/2106.05390/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":"2106.05390","created_at":"2026-07-05T03:36:38.195535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.05390v3","created_at":"2026-07-05T03:36:38.195535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05390","created_at":"2026-07-05T03:36:38.195535+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMNNS74KCTKQ","created_at":"2026-07-05T03:36:38.195535+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMNNS74KCTKQKP5Y","created_at":"2026-07-05T03:36:38.195535+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMNNS74K","created_at":"2026-07-05T03:36:38.195535+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/QMNNS74KCTKQKP5YL3ELBCV2FQ","json":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ.json","graph_json":"https://pith.science/api/pith-number/QMNNS74KCTKQKP5YL3ELBCV2FQ/graph.json","events_json":"https://pith.science/api/pith-number/QMNNS74KCTKQKP5YL3ELBCV2FQ/events.json","paper":"https://pith.science/paper/QMNNS74K"},"agent_actions":{"view_html":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ","download_json":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ.json","view_paper":"https://pith.science/paper/QMNNS74K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.05390&json=true","fetch_graph":"https://pith.science/api/pith-number/QMNNS74KCTKQKP5YL3ELBCV2FQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QMNNS74KCTKQKP5YL3ELBCV2FQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ/action/storage_attestation","attest_author":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ/action/author_attestation","sign_citation":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ/action/citation_signature","submit_replication":"https://pith.science/pith/QMNNS74KCTKQKP5YL3ELBCV2FQ/action/replication_record"}},"created_at":"2026-07-05T03:36:38.195535+00:00","updated_at":"2026-07-05T03:36:38.195535+00:00"}