{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WIT4DFNRIZ63M7OE3GN7KQVPYW","short_pith_number":"pith:WIT4DFNR","schema_version":"1.0","canonical_sha256":"b227c195b1467db67dc4d99bf542afc59e2db6ec6c06e5ed5f731d0158473f91","source":{"kind":"arxiv","id":"1905.13324","version":1},"attestation_state":"computed","paper":{"title":"A Lightweight Recurrent Network for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Rico Sennrich","submitted_at":"2019-05-30T21:40:46Z","abstract_excerpt":"Recurrent networks have achieved great success on various sequential tasks with the assistance of complex recurrent units, but suffer from severe computational inefficiency due to weak parallelization. One direction to alleviate this issue is to shift heavy computations outside the recurrence. In this paper, we propose a lightweight recurrent network, or LRN. LRN uses input and forget gates to handle long-range dependencies as well as gradient vanishing and explosion, with all parameter related calculations factored outside the recurrence. The recurrence in LRN only manipulates the weight assi"},"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":"1905.13324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-30T21:40:46Z","cross_cats_sorted":[],"title_canon_sha256":"4360df92df8d1f797cb0e94c960c9fd0f882475a69798f76f9939f9e0de1bec1","abstract_canon_sha256":"d7f7582c86eb10b8c2ea7cd93517cb252796f04231a004925bae848ab56a0b16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.297245Z","signature_b64":"fybicd9oX+LQH88K7O6aShA5CvLTmIS30qBKxGLdUBtpbDw/euyEwoNqjqtOi/YUNLV+ESETesMEcn60opcnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b227c195b1467db67dc4d99bf542afc59e2db6ec6c06e5ed5f731d0158473f91","last_reissued_at":"2026-05-17T23:44:35.296750Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.296750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Lightweight Recurrent Network for Sequence Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biao Zhang, Rico Sennrich","submitted_at":"2019-05-30T21:40:46Z","abstract_excerpt":"Recurrent networks have achieved great success on various sequential tasks with the assistance of complex recurrent units, but suffer from severe computational inefficiency due to weak parallelization. One direction to alleviate this issue is to shift heavy computations outside the recurrence. In this paper, we propose a lightweight recurrent network, or LRN. LRN uses input and forget gates to handle long-range dependencies as well as gradient vanishing and explosion, with all parameter related calculations factored outside the recurrence. The recurrence in LRN only manipulates the weight assi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13324","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":"1905.13324","created_at":"2026-05-17T23:44:35.296841+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13324v1","created_at":"2026-05-17T23:44:35.296841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13324","created_at":"2026-05-17T23:44:35.296841+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIT4DFNRIZ63","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIT4DFNRIZ63M7OE","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIT4DFNR","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.07467","citing_title":"Root Mean Square Layer Normalization","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW","json":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW.json","graph_json":"https://pith.science/api/pith-number/WIT4DFNRIZ63M7OE3GN7KQVPYW/graph.json","events_json":"https://pith.science/api/pith-number/WIT4DFNRIZ63M7OE3GN7KQVPYW/events.json","paper":"https://pith.science/paper/WIT4DFNR"},"agent_actions":{"view_html":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW","download_json":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW.json","view_paper":"https://pith.science/paper/WIT4DFNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13324&json=true","fetch_graph":"https://pith.science/api/pith-number/WIT4DFNRIZ63M7OE3GN7KQVPYW/graph.json","fetch_events":"https://pith.science/api/pith-number/WIT4DFNRIZ63M7OE3GN7KQVPYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW/action/storage_attestation","attest_author":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW/action/author_attestation","sign_citation":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW/action/citation_signature","submit_replication":"https://pith.science/pith/WIT4DFNRIZ63M7OE3GN7KQVPYW/action/replication_record"}},"created_at":"2026-05-17T23:44:35.296841+00:00","updated_at":"2026-05-17T23:44:35.296841+00:00"}