{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R5ZNCLODPXYI37EUSDQKWKCIHS","short_pith_number":"pith:R5ZNCLOD","schema_version":"1.0","canonical_sha256":"8f72d12dc37df08dfc9490e0ab28483c84cf1ace92e6d9845adb30e26989cd5e","source":{"kind":"arxiv","id":"2010.05595","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Experience Replay: a Bag of Tricks for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Angelo Porrello, Matteo Boschini, Pietro Buzzega, Simone Calderara","submitted_at":"2020-10-12T10:59:37Z","abstract_excerpt":"In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate on previous ones. This is due to the infamous problem of catastrophic forgetting, which causes a quick performance degradation when the classifier focuses on learning new categories. Recent literature proposed various approaches to tackle this issue, often resorting to very sophisticated techniques. In this work, we show that naive rehearsal can be patched to"},"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":"2010.05595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T10:59:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"14f00b208ef3cdaa3882766229935aaf2831e07eb7e039a9f9ba18d711065f38","abstract_canon_sha256":"2ea717c5b86b43f1871c211115b3f6b6943fa6af889b3a360197b39619f3c962"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:08.321844Z","signature_b64":"LNZYTKejP4pRiEh6MJuT/h6YGFbSVZg6/nEAHR3o5g1rG412gVfUmaMXjLiIvZBi2LQBXaPi0Qe0tH+JgI+jAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f72d12dc37df08dfc9490e0ab28483c84cf1ace92e6d9845adb30e26989cd5e","last_reissued_at":"2026-07-05T01:42:08.321446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:08.321446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Experience Replay: a Bag of Tricks for Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Angelo Porrello, Matteo Boschini, Pietro Buzzega, Simone Calderara","submitted_at":"2020-10-12T10:59:37Z","abstract_excerpt":"In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate on previous ones. This is due to the infamous problem of catastrophic forgetting, which causes a quick performance degradation when the classifier focuses on learning new categories. Recent literature proposed various approaches to tackle this issue, often resorting to very sophisticated techniques. In this work, we show that naive rehearsal can be patched to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05595","kind":"arxiv","version":1},"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/2010.05595/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":"2010.05595","created_at":"2026-07-05T01:42:08.321508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.05595v1","created_at":"2026-07-05T01:42:08.321508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05595","created_at":"2026-07-05T01:42:08.321508+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5ZNCLODPXYI","created_at":"2026-07-05T01:42:08.321508+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5ZNCLODPXYI37EU","created_at":"2026-07-05T01:42:08.321508+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5ZNCLOD","created_at":"2026-07-05T01:42:08.321508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17664","citing_title":"What is the role of memorization in Continual Learning?","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS","json":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS.json","graph_json":"https://pith.science/api/pith-number/R5ZNCLODPXYI37EUSDQKWKCIHS/graph.json","events_json":"https://pith.science/api/pith-number/R5ZNCLODPXYI37EUSDQKWKCIHS/events.json","paper":"https://pith.science/paper/R5ZNCLOD"},"agent_actions":{"view_html":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS","download_json":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS.json","view_paper":"https://pith.science/paper/R5ZNCLOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.05595&json=true","fetch_graph":"https://pith.science/api/pith-number/R5ZNCLODPXYI37EUSDQKWKCIHS/graph.json","fetch_events":"https://pith.science/api/pith-number/R5ZNCLODPXYI37EUSDQKWKCIHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS/action/storage_attestation","attest_author":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS/action/author_attestation","sign_citation":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS/action/citation_signature","submit_replication":"https://pith.science/pith/R5ZNCLODPXYI37EUSDQKWKCIHS/action/replication_record"}},"created_at":"2026-07-05T01:42:08.321508+00:00","updated_at":"2026-07-05T01:42:08.321508+00:00"}