{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5EWXTZPEISCABVX6L2OVAC2UNX","short_pith_number":"pith:5EWXTZPE","schema_version":"1.0","canonical_sha256":"e92d79e5e4448400d6fe5e9d500b546de43f84ba72e53e12045b31fe5f10ea38","source":{"kind":"arxiv","id":"1802.03875","version":2},"attestation_state":"computed","paper":{"title":"Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthony Robins, Brendan McCane, Craig Atkinson, Lech Szymanski","submitted_at":"2018-02-12T03:51:41Z","abstract_excerpt":"In general, neural networks are not currently capable of learning tasks in a sequential fashion. When a novel, unrelated task is learnt by a neural network, it substantially forgets how to solve previously learnt tasks. One of the original solutions to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of the previous task/s. This is very effective for simple tasks. However, pseudo-rehearsal has not yet been successfully applied to very complex tasks because in these tasks it is difficult to generate representative items. We a"},"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":"1802.03875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T03:51:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"f0fe9a0de12073f39306288271e893c995869402df82d6fb7cee2327358ee9ed","abstract_canon_sha256":"058be523b1e57039b75e963187232a975c3127dc78e3db0aa4745c3177eb4e0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:42.223219Z","signature_b64":"i3qJt41cAWUvf+1KTgA3qBUtUERkpxdBbgZIa+ZN/njCokvlDWgNFSlsX99+AsLZOionillkXiTtWKDbpaitCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e92d79e5e4448400d6fe5e9d500b546de43f84ba72e53e12045b31fe5f10ea38","last_reissued_at":"2026-05-18T00:16:42.222682Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:42.222682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthony Robins, Brendan McCane, Craig Atkinson, Lech Szymanski","submitted_at":"2018-02-12T03:51:41Z","abstract_excerpt":"In general, neural networks are not currently capable of learning tasks in a sequential fashion. When a novel, unrelated task is learnt by a neural network, it substantially forgets how to solve previously learnt tasks. One of the original solutions to this problem is pseudo-rehearsal, which involves learning the new task while rehearsing generated items representative of the previous task/s. This is very effective for simple tasks. However, pseudo-rehearsal has not yet been successfully applied to very complex tasks because in these tasks it is difficult to generate representative items. We a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03875","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":""},"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":"1802.03875","created_at":"2026-05-18T00:16:42.222756+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03875v2","created_at":"2026-05-18T00:16:42.222756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03875","created_at":"2026-05-18T00:16:42.222756+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EWXTZPEISCA","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EWXTZPEISCABVX6","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EWXTZPE","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18320","citing_title":"Continual Learning in Machine Speech Chain Using Gradient Episodic Memory","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX","json":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX.json","graph_json":"https://pith.science/api/pith-number/5EWXTZPEISCABVX6L2OVAC2UNX/graph.json","events_json":"https://pith.science/api/pith-number/5EWXTZPEISCABVX6L2OVAC2UNX/events.json","paper":"https://pith.science/paper/5EWXTZPE"},"agent_actions":{"view_html":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX","download_json":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX.json","view_paper":"https://pith.science/paper/5EWXTZPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03875&json=true","fetch_graph":"https://pith.science/api/pith-number/5EWXTZPEISCABVX6L2OVAC2UNX/graph.json","fetch_events":"https://pith.science/api/pith-number/5EWXTZPEISCABVX6L2OVAC2UNX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX/action/storage_attestation","attest_author":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX/action/author_attestation","sign_citation":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX/action/citation_signature","submit_replication":"https://pith.science/pith/5EWXTZPEISCABVX6L2OVAC2UNX/action/replication_record"}},"created_at":"2026-05-18T00:16:42.222756+00:00","updated_at":"2026-05-18T00:16:42.222756+00:00"}