{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G3EE4BLUOQYOPP6VDLSUQYLI3S","short_pith_number":"pith:G3EE4BLU","schema_version":"1.0","canonical_sha256":"36c84e05747430e7bfd51ae5486168dc86172a0a6599b86620ec277ec16959d2","source":{"kind":"arxiv","id":"2104.04132","version":2},"attestation_state":"computed","paper":{"title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Christopher Kanan, Giri P. Krishnan, Hava T. Siegelmann, Maxim Bazhenov, Terrence J. Sejnowski, Tyler L. Hayes","submitted_at":"2021-04-01T15:19:08Z","abstract_excerpt":"Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated into deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and r"},"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":"2104.04132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2021-04-01T15:19:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1179885132d2394ad62778799193299310be2cd0965363432547b9c0fa4c344a","abstract_canon_sha256":"f6c6549178d5b5c33cd32c047cca4b8b53867810fe1c6e41c47a61ee7017a5f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:18.394824Z","signature_b64":"NQiI82qwCkJCDNoAzsdvwZlUQisEDjuk871gc0N3Fm/7MPpr+EVq0fzDjUjh8tgkpuYZQvwbsOdI+PS4dLZ8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36c84e05747430e7bfd51ae5486168dc86172a0a6599b86620ec277ec16959d2","last_reissued_at":"2026-07-05T02:44:18.394271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:18.394271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Christopher Kanan, Giri P. Krishnan, Hava T. Siegelmann, Maxim Bazhenov, Terrence J. Sejnowski, Tyler L. Hayes","submitted_at":"2021-04-01T15:19:08Z","abstract_excerpt":"Replay is the reactivation of one or more neural patterns, which are similar to the activation patterns experienced during past waking experiences. Replay was first observed in biological neural networks during sleep, and it is now thought to play a critical role in memory formation, retrieval, and consolidation. Replay-like mechanisms have been incorporated into deep artificial neural networks that learn over time to avoid catastrophic forgetting of previous knowledge. Replay algorithms have been successfully used in a wide range of deep learning methods within supervised, unsupervised, and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04132","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/2104.04132/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":"2104.04132","created_at":"2026-07-05T02:44:18.394343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04132v2","created_at":"2026-07-05T02:44:18.394343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04132","created_at":"2026-07-05T02:44:18.394343+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3EE4BLUOQYO","created_at":"2026-07-05T02:44:18.394343+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3EE4BLUOQYOPP6V","created_at":"2026-07-05T02:44:18.394343+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3EE4BLU","created_at":"2026-07-05T02:44:18.394343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12512","citing_title":"Scalable Strategies for Continual Learning with Replay","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S","json":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S.json","graph_json":"https://pith.science/api/pith-number/G3EE4BLUOQYOPP6VDLSUQYLI3S/graph.json","events_json":"https://pith.science/api/pith-number/G3EE4BLUOQYOPP6VDLSUQYLI3S/events.json","paper":"https://pith.science/paper/G3EE4BLU"},"agent_actions":{"view_html":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S","download_json":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S.json","view_paper":"https://pith.science/paper/G3EE4BLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04132&json=true","fetch_graph":"https://pith.science/api/pith-number/G3EE4BLUOQYOPP6VDLSUQYLI3S/graph.json","fetch_events":"https://pith.science/api/pith-number/G3EE4BLUOQYOPP6VDLSUQYLI3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S/action/storage_attestation","attest_author":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S/action/author_attestation","sign_citation":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S/action/citation_signature","submit_replication":"https://pith.science/pith/G3EE4BLUOQYOPP6VDLSUQYLI3S/action/replication_record"}},"created_at":"2026-07-05T02:44:18.394343+00:00","updated_at":"2026-07-05T02:44:18.394343+00:00"}