{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PGKRR7ILSB4GCMWCC7XIVCUNTY","short_pith_number":"pith:PGKRR7IL","schema_version":"1.0","canonical_sha256":"799518fd0b90786132c217ee8a8a8d9e31c5e383cba22e80a33c9837d1b02b55","source":{"kind":"arxiv","id":"1903.02647","version":2},"attestation_state":"computed","paper":{"title":"Continual Learning Using World Models for Pseudo-Rehearsal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nicholas Ketz, Praveen Pilly, Soheil Kolouri","submitted_at":"2019-03-06T22:58:36Z","abstract_excerpt":"The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or continual fashion. Current solutions to the continual learning problem require experience to be segmented and labeled as discrete tasks, however, in continuous experience it is generally unclear what a sufficient segmentation of tasks would be. Here we propose a method to continually learn these internal world models through the interleaving of internally generate"},"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":"1903.02647","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-06T22:58:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e0a7cdd8c3904f50a7e7965dcbed87eeaf84adca9d5990ba68bcddbd9cd8dbaa","abstract_canon_sha256":"1148e673e426bea06ceabffa5d9a2f56fdb6ebc7635d915168bfd8d34f332966"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:36.763345Z","signature_b64":"7D2hLoHrFd17HJll63iyKsbqiWeiNBbHtgDjd9uDB9gIM1fAcmAHLg3U+kuehFfSvqKfgoqnDVVM/Yw74e2XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"799518fd0b90786132c217ee8a8a8d9e31c5e383cba22e80a33c9837d1b02b55","last_reissued_at":"2026-05-17T23:43:36.762753Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:36.762753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning Using World Models for Pseudo-Rehearsal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Nicholas Ketz, Praveen Pilly, Soheil Kolouri","submitted_at":"2019-03-06T22:58:36Z","abstract_excerpt":"The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or continual fashion. Current solutions to the continual learning problem require experience to be segmented and labeled as discrete tasks, however, in continuous experience it is generally unclear what a sufficient segmentation of tasks would be. Here we propose a method to continually learn these internal world models through the interleaving of internally generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02647","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":"1903.02647","created_at":"2026-05-17T23:43:36.762841+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02647v2","created_at":"2026-05-17T23:43:36.762841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02647","created_at":"2026-05-17T23:43:36.762841+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGKRR7ILSB4G","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGKRR7ILSB4GCMWC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGKRR7IL","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY","json":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY.json","graph_json":"https://pith.science/api/pith-number/PGKRR7ILSB4GCMWCC7XIVCUNTY/graph.json","events_json":"https://pith.science/api/pith-number/PGKRR7ILSB4GCMWCC7XIVCUNTY/events.json","paper":"https://pith.science/paper/PGKRR7IL"},"agent_actions":{"view_html":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY","download_json":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY.json","view_paper":"https://pith.science/paper/PGKRR7IL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02647&json=true","fetch_graph":"https://pith.science/api/pith-number/PGKRR7ILSB4GCMWCC7XIVCUNTY/graph.json","fetch_events":"https://pith.science/api/pith-number/PGKRR7ILSB4GCMWCC7XIVCUNTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY/action/storage_attestation","attest_author":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY/action/author_attestation","sign_citation":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY/action/citation_signature","submit_replication":"https://pith.science/pith/PGKRR7ILSB4GCMWCC7XIVCUNTY/action/replication_record"}},"created_at":"2026-05-17T23:43:36.762841+00:00","updated_at":"2026-05-17T23:43:36.762841+00:00"}