{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:K7CXLUGAHVAVHQGV5VLLGRIMUD","short_pith_number":"pith:K7CXLUGA","schema_version":"1.0","canonical_sha256":"57c575d0c03d4153c0d5ed56b3450ca0f0b2f2ee6b3ef5e39e75c9db0dade21b","source":{"kind":"arxiv","id":"1805.05758","version":1},"attestation_state":"computed","paper":{"title":"Continuous Learning in a Hierarchical Multiscale Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Clement Delangue, Julien Chaumond, Thomas Wolf","submitted_at":"2018-05-15T13:37:33Z","abstract_excerpt":"We reformulate the problem of encoding a multi-scale representation of a sequence in a language model by casting it in a continuous learning framework. We propose a hierarchical multi-scale language model in which short time-scale dependencies are encoded in the hidden state of a lower-level recurrent neural network while longer time-scale dependencies are encoded in the dynamic of the lower-level network by having a meta-learner update the weights of the lower-level neural network in an online meta-learning fashion. We use elastic weights consolidation as a higher-level to prevent catastrophi"},"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":"1805.05758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-15T13:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"d937b9efb7a6dccfa18ee128a304f570fece31602025a07efd5bbcf0e5d508dc","abstract_canon_sha256":"70a9093308f22f1491390b4e9c78fd63c586cf0e3c65ffb83fd214ff4d2c99ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:53.779950Z","signature_b64":"ilsyQALxFbfWk7x7iRIjUvUp5IHhGhPu4uZ+kW/6EibPREAM/ayMSM0iE91pzmjjRyqmLVHQb8Ph8sV/6NFhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57c575d0c03d4153c0d5ed56b3450ca0f0b2f2ee6b3ef5e39e75c9db0dade21b","last_reissued_at":"2026-05-18T00:15:53.779197Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:53.779197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Learning in a Hierarchical Multiscale Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Clement Delangue, Julien Chaumond, Thomas Wolf","submitted_at":"2018-05-15T13:37:33Z","abstract_excerpt":"We reformulate the problem of encoding a multi-scale representation of a sequence in a language model by casting it in a continuous learning framework. We propose a hierarchical multi-scale language model in which short time-scale dependencies are encoded in the hidden state of a lower-level recurrent neural network while longer time-scale dependencies are encoded in the dynamic of the lower-level network by having a meta-learner update the weights of the lower-level neural network in an online meta-learning fashion. We use elastic weights consolidation as a higher-level to prevent catastrophi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.05758","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":""},"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":"1805.05758","created_at":"2026-05-18T00:15:53.779305+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.05758v1","created_at":"2026-05-18T00:15:53.779305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.05758","created_at":"2026-05-18T00:15:53.779305+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7CXLUGAHVAV","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7CXLUGAHVAVHQGV","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7CXLUGA","created_at":"2026-05-18T12:32:33.847187+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/K7CXLUGAHVAVHQGV5VLLGRIMUD","json":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD.json","graph_json":"https://pith.science/api/pith-number/K7CXLUGAHVAVHQGV5VLLGRIMUD/graph.json","events_json":"https://pith.science/api/pith-number/K7CXLUGAHVAVHQGV5VLLGRIMUD/events.json","paper":"https://pith.science/paper/K7CXLUGA"},"agent_actions":{"view_html":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD","download_json":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD.json","view_paper":"https://pith.science/paper/K7CXLUGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.05758&json=true","fetch_graph":"https://pith.science/api/pith-number/K7CXLUGAHVAVHQGV5VLLGRIMUD/graph.json","fetch_events":"https://pith.science/api/pith-number/K7CXLUGAHVAVHQGV5VLLGRIMUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD/action/storage_attestation","attest_author":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD/action/author_attestation","sign_citation":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD/action/citation_signature","submit_replication":"https://pith.science/pith/K7CXLUGAHVAVHQGV5VLLGRIMUD/action/replication_record"}},"created_at":"2026-05-18T00:15:53.779305+00:00","updated_at":"2026-05-18T00:15:53.779305+00:00"}