{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CZ6JMYVHHTYR4D3TOO5COJ3QPL","short_pith_number":"pith:CZ6JMYVH","schema_version":"1.0","canonical_sha256":"167c9662a73cf11e0f7373ba2727707acfdffc52fe49efb480fd88fd9cb7c818","source":{"kind":"arxiv","id":"1905.12340","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Full Connectivity in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Keller, Matthijs Van keirsbilck, Xiaodong Yang","submitted_at":"2019-05-29T11:35:18Z","abstract_excerpt":"Recurrent neural networks (RNNs) are omnipresent in sequence modeling tasks. Practical models usually consist of several layers of hundreds or thousands of neurons which are fully connected. This places a heavy computational and memory burden on hardware, restricting adoption in practical low-cost and low-power devices. Compared to fully convolutional models, the costly sequential operation of RNNs severely hinders performance on parallel hardware. This paper challenges the convention of full connectivity in RNNs. We study structurally sparse RNNs, showing that they are well suited for acceler"},"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":"1905.12340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-29T11:35:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5742a4a96d4f7a04bdf7b2a4c3eafade2c5d5fbe5b6e05c9edf852ae9d5c2c61","abstract_canon_sha256":"2f9ce33760da68244e66a62b376b80a44ba0d002e7ebcdae1bd9b5f73e0be001"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:44.600557Z","signature_b64":"2WSkC36RjuSdvV+nlt0hPjozWLX7gox1zCOqxlrpMqnmbvO4fYiew58g7euzrgKjFLevPoiOyVGf1VaksGxXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167c9662a73cf11e0f7373ba2727707acfdffc52fe49efb480fd88fd9cb7c818","last_reissued_at":"2026-05-17T23:44:44.600039Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:44.600039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Full Connectivity in Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Keller, Matthijs Van keirsbilck, Xiaodong Yang","submitted_at":"2019-05-29T11:35:18Z","abstract_excerpt":"Recurrent neural networks (RNNs) are omnipresent in sequence modeling tasks. Practical models usually consist of several layers of hundreds or thousands of neurons which are fully connected. This places a heavy computational and memory burden on hardware, restricting adoption in practical low-cost and low-power devices. Compared to fully convolutional models, the costly sequential operation of RNNs severely hinders performance on parallel hardware. This paper challenges the convention of full connectivity in RNNs. We study structurally sparse RNNs, showing that they are well suited for acceler"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12340","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":"1905.12340","created_at":"2026-05-17T23:44:44.600120+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12340v1","created_at":"2026-05-17T23:44:44.600120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12340","created_at":"2026-05-17T23:44:44.600120+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ6JMYVHHTYR","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ6JMYVHHTYR4D3T","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ6JMYVH","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2301.04104","citing_title":"Mastering Diverse Domains through World Models","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL","json":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL.json","graph_json":"https://pith.science/api/pith-number/CZ6JMYVHHTYR4D3TOO5COJ3QPL/graph.json","events_json":"https://pith.science/api/pith-number/CZ6JMYVHHTYR4D3TOO5COJ3QPL/events.json","paper":"https://pith.science/paper/CZ6JMYVH"},"agent_actions":{"view_html":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL","download_json":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL.json","view_paper":"https://pith.science/paper/CZ6JMYVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12340&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ6JMYVHHTYR4D3TOO5COJ3QPL/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ6JMYVHHTYR4D3TOO5COJ3QPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL/action/storage_attestation","attest_author":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL/action/author_attestation","sign_citation":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL/action/citation_signature","submit_replication":"https://pith.science/pith/CZ6JMYVHHTYR4D3TOO5COJ3QPL/action/replication_record"}},"created_at":"2026-05-17T23:44:44.600120+00:00","updated_at":"2026-05-17T23:44:44.600120+00:00"}