{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NQNAJPFFDHQ4EOU5F7UVCYKL3N","short_pith_number":"pith:NQNAJPFF","schema_version":"1.0","canonical_sha256":"6c1a04bca519e1c23a9d2fe951614bdb4c8511c8b6fb34d85a65f1f328046681","source":{"kind":"arxiv","id":"2108.09020","version":2},"attestation_state":"computed","paper":{"title":"Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ozan Sener, Vladlen Koltun, Zhipeng Cai","submitted_at":"2021-08-20T06:17:20Z","abstract_excerpt":"Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classification setting, where new tasks/classes are added at discrete time intervals. Such an \"offline\" setting does not evaluate the ability of agents to learn effectively and efficiently, since an agent can perform multiple learning epochs without any time limitation when a task is added. We argue that \"online\" continual learning, where data is a single continuous stream without task boundaries, enables evaluating both info"},"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":"2108.09020","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-20T06:17:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"246aa357b647dcd19c20589d8ad6f2b3b146133316202b2d76fa323421722dd4","abstract_canon_sha256":"d0c5ca87109ab7fe1ff418bad8075ae6b4b9fde41b56612f5a9bdcec0903a4be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:33.866937Z","signature_b64":"cFdDWROdBTxzJmzhJsHXr0m1YqJ2g728VwrmkC6AaZjXbYpi/ZxL1yxkSV1tqcpLPori13snBYHa2dcweOdzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c1a04bca519e1c23a9d2fe951614bdb4c8511c8b6fb34d85a65f1f328046681","last_reissued_at":"2026-07-05T03:16:33.866454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:33.866454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ozan Sener, Vladlen Koltun, Zhipeng Cai","submitted_at":"2021-08-20T06:17:20Z","abstract_excerpt":"Continual learning is the problem of learning and retaining knowledge through time over multiple tasks and environments. Research has primarily focused on the incremental classification setting, where new tasks/classes are added at discrete time intervals. Such an \"offline\" setting does not evaluate the ability of agents to learn effectively and efficiently, since an agent can perform multiple learning epochs without any time limitation when a task is added. We argue that \"online\" continual learning, where data is a single continuous stream without task boundaries, enables evaluating both info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09020","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/2108.09020/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":"2108.09020","created_at":"2026-07-05T03:16:33.866511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.09020v2","created_at":"2026-07-05T03:16:33.866511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09020","created_at":"2026-07-05T03:16:33.866511+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQNAJPFFDHQ4","created_at":"2026-07-05T03:16:33.866511+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQNAJPFFDHQ4EOU5","created_at":"2026-07-05T03:16:33.866511+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQNAJPFF","created_at":"2026-07-05T03:16:33.866511+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/NQNAJPFFDHQ4EOU5F7UVCYKL3N","json":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N.json","graph_json":"https://pith.science/api/pith-number/NQNAJPFFDHQ4EOU5F7UVCYKL3N/graph.json","events_json":"https://pith.science/api/pith-number/NQNAJPFFDHQ4EOU5F7UVCYKL3N/events.json","paper":"https://pith.science/paper/NQNAJPFF"},"agent_actions":{"view_html":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N","download_json":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N.json","view_paper":"https://pith.science/paper/NQNAJPFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.09020&json=true","fetch_graph":"https://pith.science/api/pith-number/NQNAJPFFDHQ4EOU5F7UVCYKL3N/graph.json","fetch_events":"https://pith.science/api/pith-number/NQNAJPFFDHQ4EOU5F7UVCYKL3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N/action/storage_attestation","attest_author":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N/action/author_attestation","sign_citation":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N/action/citation_signature","submit_replication":"https://pith.science/pith/NQNAJPFFDHQ4EOU5F7UVCYKL3N/action/replication_record"}},"created_at":"2026-07-05T03:16:33.866511+00:00","updated_at":"2026-07-05T03:16:33.866511+00:00"}