{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PIWOMMOGHRGUNSTYANSECY353U","short_pith_number":"pith:PIWOMMOG","schema_version":"1.0","canonical_sha256":"7a2ce631c63c4d46ca78036441637ddd241b0800cdc218d5df7dbaed4508458c","source":{"kind":"arxiv","id":"2003.05856","version":3},"attestation_state":"computed","paper":{"title":"Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alexandre Lacoste, David Vazquez, Fabrice Normandin, Irina Rish, Issam Laradji, Laurent Charlin, Lucas Caccia, Massimo Caccia, Min Lin, Oleksiy Ostapenko, Pau Rodriguez","submitted_at":"2020-03-12T15:47:16Z","abstract_excerpt":"Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new"},"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":"2003.05856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-03-12T15:47:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6258f3605e026519984371a139da5a8726524784c6b70f7b907d3269fe6e0cfe","abstract_canon_sha256":"46ec95639c9c4db8eac916d8d940d01099dfc43bdee6474fb6bb12705813ff27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:29.280236Z","signature_b64":"vgphGoycciWZp50+GrKlrgfC2GtMJ51QKg3XnRzW6dpridUmZ/DXvfpPrSEHRjIdxtbBjkdSa+yVZBjK1gQuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a2ce631c63c4d46ca78036441637ddd241b0800cdc218d5df7dbaed4508458c","last_reissued_at":"2026-07-05T02:08:29.279813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:29.279813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alexandre Lacoste, David Vazquez, Fabrice Normandin, Irina Rish, Issam Laradji, Laurent Charlin, Lucas Caccia, Massimo Caccia, Min Lin, Oleksiy Ostapenko, Pau Rodriguez","submitted_at":"2020-03-12T15:47:16Z","abstract_excerpt":"Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.05856","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/2003.05856/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":"2003.05856","created_at":"2026-07-05T02:08:29.279872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.05856v3","created_at":"2026-07-05T02:08:29.279872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.05856","created_at":"2026-07-05T02:08:29.279872+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIWOMMOGHRGU","created_at":"2026-07-05T02:08:29.279872+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIWOMMOGHRGUNSTY","created_at":"2026-07-05T02:08:29.279872+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIWOMMOG","created_at":"2026-07-05T02:08:29.279872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19080","citing_title":"MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U","json":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U.json","graph_json":"https://pith.science/api/pith-number/PIWOMMOGHRGUNSTYANSECY353U/graph.json","events_json":"https://pith.science/api/pith-number/PIWOMMOGHRGUNSTYANSECY353U/events.json","paper":"https://pith.science/paper/PIWOMMOG"},"agent_actions":{"view_html":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U","download_json":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U.json","view_paper":"https://pith.science/paper/PIWOMMOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.05856&json=true","fetch_graph":"https://pith.science/api/pith-number/PIWOMMOGHRGUNSTYANSECY353U/graph.json","fetch_events":"https://pith.science/api/pith-number/PIWOMMOGHRGUNSTYANSECY353U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U/action/storage_attestation","attest_author":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U/action/author_attestation","sign_citation":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U/action/citation_signature","submit_replication":"https://pith.science/pith/PIWOMMOGHRGUNSTYANSECY353U/action/replication_record"}},"created_at":"2026-07-05T02:08:29.279872+00:00","updated_at":"2026-07-05T02:08:29.279872+00:00"}