{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UMNJE5BZAP7CE4EM2OIT3O5Y76","short_pith_number":"pith:UMNJE5BZ","schema_version":"1.0","canonical_sha256":"a31a92743903fe22708cd3913dbbb8ff9790d10e57bc88e7890fbdee64372686","source":{"kind":"arxiv","id":"1908.04742","version":3},"attestation_state":"computed","paper":{"title":"Online Continual Learning with Maximally Interfered Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eugene Belilovsky, Laurent Charlin, Lucas Caccia, Massimo Caccia, Min Lin, Rahaf Aljundi, Tinne Tuytelaars","submitted_at":"2019-08-11T21:16:44Z","abstract_excerpt":"Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or \"single-pass through the data\" setting has gained attention recently as a natural setting that is difficult to tackle. Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks. These approaches typically rely on randomly selecting samples from t"},"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":"1908.04742","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-11T21:16:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"32d123a5859da4dbaa7a30e69f6d37fee1fce2690e6f36a891ddc58918231199","abstract_canon_sha256":"fe8d6131dca9c4b0735cede2a5732fd5e5e9b912109bbddaa0a1f343c455b002"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:49.849093Z","signature_b64":"6Konc9keFScXBlsyW0vhCzIkAkJF613/knKeVlysNuHR6W1VyLOv/gqZDcS4aFWEHfX+bzaNnBe8ARAM9eVvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a31a92743903fe22708cd3913dbbb8ff9790d10e57bc88e7890fbdee64372686","last_reissued_at":"2026-07-05T00:15:49.848576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:49.848576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Continual Learning with Maximally Interfered Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eugene Belilovsky, Laurent Charlin, Lucas Caccia, Massimo Caccia, Min Lin, Rahaf Aljundi, Tinne Tuytelaars","submitted_at":"2019-08-11T21:16:44Z","abstract_excerpt":"Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or \"single-pass through the data\" setting has gained attention recently as a natural setting that is difficult to tackle. Methods based on replay, either generative or from a stored memory, have been shown to be effective approaches for continual learning, matching or exceeding the state of the art in a number of standard benchmarks. These approaches typically rely on randomly selecting samples from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04742","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/1908.04742/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":"1908.04742","created_at":"2026-07-05T00:15:49.848639+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.04742v3","created_at":"2026-07-05T00:15:49.848639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04742","created_at":"2026-07-05T00:15:49.848639+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMNJE5BZAP7C","created_at":"2026-07-05T00:15:49.848639+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMNJE5BZAP7CE4EM","created_at":"2026-07-05T00:15:49.848639+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMNJE5BZ","created_at":"2026-07-05T00:15:49.848639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07319","citing_title":"MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76","json":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76.json","graph_json":"https://pith.science/api/pith-number/UMNJE5BZAP7CE4EM2OIT3O5Y76/graph.json","events_json":"https://pith.science/api/pith-number/UMNJE5BZAP7CE4EM2OIT3O5Y76/events.json","paper":"https://pith.science/paper/UMNJE5BZ"},"agent_actions":{"view_html":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76","download_json":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76.json","view_paper":"https://pith.science/paper/UMNJE5BZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.04742&json=true","fetch_graph":"https://pith.science/api/pith-number/UMNJE5BZAP7CE4EM2OIT3O5Y76/graph.json","fetch_events":"https://pith.science/api/pith-number/UMNJE5BZAP7CE4EM2OIT3O5Y76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76/action/storage_attestation","attest_author":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76/action/author_attestation","sign_citation":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76/action/citation_signature","submit_replication":"https://pith.science/pith/UMNJE5BZAP7CE4EM2OIT3O5Y76/action/replication_record"}},"created_at":"2026-07-05T00:15:49.848639+00:00","updated_at":"2026-07-05T00:15:49.848639+00:00"}