{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HFAXITDVDFV23WSKUOHFXOCOKA","short_pith_number":"pith:HFAXITDV","schema_version":"1.0","canonical_sha256":"3941744c75196badda4aa38e5bb84e5036159c82c07ae4c51491de1363a67e5f","source":{"kind":"arxiv","id":"1803.11389","version":1},"attestation_state":"computed","paper":{"title":"Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.DC","authors_text":"Jinhwan Park, Wonyong Sung","submitted_at":"2018-03-30T09:15:07Z","abstract_excerpt":"As neural network algorithms show high performance in many applications, their efficient inference on mobile and embedded systems are of great interests. When a single stream recurrent neural network (RNN) is executed for a personal user in embedded systems, it demands a large amount of DRAM accesses because the network size is usually much bigger than the cache size and the weights of an RNN are used only once at each time step. We overcome this problem by parallelizing the algorithm and executing it multiple time steps at a time. This approach also reduces the power consumption by lowering t"},"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":"1803.11389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-03-30T09:15:07Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"5e46f60954c6cec8604f9a76b3132bd94c6b3a33fa68c74fa600a4c699e7b38a","abstract_canon_sha256":"acb811df9a00c29d272183a34708584226ee64d5711e3e5b2117cd7a0837c6c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:43.803683Z","signature_b64":"1BvLkaXfpBHJ4yReMKqzpihtBR8ytKpkZQa2SBdIhKkfC7s7ql3+53KHloR+qAwQ0UEFYI+uI2PAkd+g+I7YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3941744c75196badda4aa38e5bb84e5036159c82c07ae4c51491de1363a67e5f","last_reissued_at":"2026-05-18T00:19:43.802886Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:43.802886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.DC","authors_text":"Jinhwan Park, Wonyong Sung","submitted_at":"2018-03-30T09:15:07Z","abstract_excerpt":"As neural network algorithms show high performance in many applications, their efficient inference on mobile and embedded systems are of great interests. When a single stream recurrent neural network (RNN) is executed for a personal user in embedded systems, it demands a large amount of DRAM accesses because the network size is usually much bigger than the cache size and the weights of an RNN are used only once at each time step. We overcome this problem by parallelizing the algorithm and executing it multiple time steps at a time. This approach also reduces the power consumption by lowering t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11389","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":"1803.11389","created_at":"2026-05-18T00:19:43.803011+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.11389v1","created_at":"2026-05-18T00:19:43.803011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11389","created_at":"2026-05-18T00:19:43.803011+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFAXITDVDFV2","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFAXITDVDFV23WSK","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFAXITDV","created_at":"2026-05-18T12:32:28.185984+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/HFAXITDVDFV23WSKUOHFXOCOKA","json":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA.json","graph_json":"https://pith.science/api/pith-number/HFAXITDVDFV23WSKUOHFXOCOKA/graph.json","events_json":"https://pith.science/api/pith-number/HFAXITDVDFV23WSKUOHFXOCOKA/events.json","paper":"https://pith.science/paper/HFAXITDV"},"agent_actions":{"view_html":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA","download_json":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA.json","view_paper":"https://pith.science/paper/HFAXITDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.11389&json=true","fetch_graph":"https://pith.science/api/pith-number/HFAXITDVDFV23WSKUOHFXOCOKA/graph.json","fetch_events":"https://pith.science/api/pith-number/HFAXITDVDFV23WSKUOHFXOCOKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA/action/storage_attestation","attest_author":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA/action/author_attestation","sign_citation":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA/action/citation_signature","submit_replication":"https://pith.science/pith/HFAXITDVDFV23WSKUOHFXOCOKA/action/replication_record"}},"created_at":"2026-05-18T00:19:43.803011+00:00","updated_at":"2026-05-18T00:19:43.803011+00:00"}