{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2WOQ47LTFPA7HI7UXA3KHSYLRU","short_pith_number":"pith:2WOQ47LT","schema_version":"1.0","canonical_sha256":"d59d0e7d732bc1f3a3f4b836a3cb0b8d221213b16c5c8758dac5b02e67f0676c","source":{"kind":"arxiv","id":"2207.01145","version":3},"attestation_state":"computed","paper":{"title":"Memory Population in Continual Learning via Outlier Elimination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alain Raymond-Saez, Alvaro Soto, Davide Bacciu, Julio Hurtado, Vincenzo Lomonaco, Vladimir Araujo","submitted_at":"2022-07-04T00:09:33Z","abstract_excerpt":"Catastrophic forgetting, the phenomenon of forgetting previously learned tasks when learning a new one, is a major hurdle in developing continual learning algorithms. A popular method to alleviate forgetting is to use a memory buffer, which stores a subset of previously learned task examples for use during training on new tasks. The de facto method of filling memory is by randomly selecting previous examples. However, this process could introduce outliers or noisy samples that could hurt the generalization of the model. This paper introduces Memory Outlier Elimination (MOE), a method for ident"},"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":"2207.01145","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-04T00:09:33Z","cross_cats_sorted":[],"title_canon_sha256":"ff960264c05b8993e5e021ef99e451336953cea3c8ece577e1e99cd353dfb5aa","abstract_canon_sha256":"16de57073a5f1c84d59693cbe0f88aef6e6a599776193063aba62b324d3b6172"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:29.337961Z","signature_b64":"gXNG4zB6XIOR64VDHASoAJVvGWH2js+z41mZk86Kpa3BMzfnz8yaseA/xujC3gClIa9UoWuAd9IMXPMRHZTZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d59d0e7d732bc1f3a3f4b836a3cb0b8d221213b16c5c8758dac5b02e67f0676c","last_reissued_at":"2026-07-05T06:56:29.337549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:29.337549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory Population in Continual Learning via Outlier Elimination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alain Raymond-Saez, Alvaro Soto, Davide Bacciu, Julio Hurtado, Vincenzo Lomonaco, Vladimir Araujo","submitted_at":"2022-07-04T00:09:33Z","abstract_excerpt":"Catastrophic forgetting, the phenomenon of forgetting previously learned tasks when learning a new one, is a major hurdle in developing continual learning algorithms. A popular method to alleviate forgetting is to use a memory buffer, which stores a subset of previously learned task examples for use during training on new tasks. The de facto method of filling memory is by randomly selecting previous examples. However, this process could introduce outliers or noisy samples that could hurt the generalization of the model. This paper introduces Memory Outlier Elimination (MOE), a method for ident"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01145","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/2207.01145/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":"2207.01145","created_at":"2026-07-05T06:56:29.337602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01145v3","created_at":"2026-07-05T06:56:29.337602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01145","created_at":"2026-07-05T06:56:29.337602+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WOQ47LTFPA7","created_at":"2026-07-05T06:56:29.337602+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WOQ47LTFPA7HI7U","created_at":"2026-07-05T06:56:29.337602+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WOQ47LT","created_at":"2026-07-05T06:56:29.337602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10861","citing_title":"Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU","json":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU.json","graph_json":"https://pith.science/api/pith-number/2WOQ47LTFPA7HI7UXA3KHSYLRU/graph.json","events_json":"https://pith.science/api/pith-number/2WOQ47LTFPA7HI7UXA3KHSYLRU/events.json","paper":"https://pith.science/paper/2WOQ47LT"},"agent_actions":{"view_html":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU","download_json":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU.json","view_paper":"https://pith.science/paper/2WOQ47LT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01145&json=true","fetch_graph":"https://pith.science/api/pith-number/2WOQ47LTFPA7HI7UXA3KHSYLRU/graph.json","fetch_events":"https://pith.science/api/pith-number/2WOQ47LTFPA7HI7UXA3KHSYLRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU/action/storage_attestation","attest_author":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU/action/author_attestation","sign_citation":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU/action/citation_signature","submit_replication":"https://pith.science/pith/2WOQ47LTFPA7HI7UXA3KHSYLRU/action/replication_record"}},"created_at":"2026-07-05T06:56:29.337602+00:00","updated_at":"2026-07-05T06:56:29.337602+00:00"}