{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RRDQAK5EDUQGOPQ2Y4INDMKB57","short_pith_number":"pith:RRDQAK5E","schema_version":"1.0","canonical_sha256":"8c47002ba41d20673e1ac710d1b141efeace153b2f9cbd51dc1a8211ff52bb9d","source":{"kind":"arxiv","id":"1610.10099","version":2},"attestation_state":"computed","paper":{"title":"Neural Machine Translation in Linear Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron van den Oord, Alex Graves, Karen Simonyan, Koray Kavukcuoglu, Lasse Espeholt, Nal Kalchbrenner","submitted_at":"2016-10-31T19:56:39Z","abstract_excerpt":"We present a novel neural network for processing sequences. The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the target sequence. The two network parts are connected by stacking the decoder on top of the encoder and preserving the temporal resolution of the sequences. To address the differing lengths of the source and the target, we introduce an efficient mechanism by which the decoder is dynamically unfolded over the representation of the encoder. The ByteNet uses dilation in the convolutiona"},"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":"1610.10099","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-31T19:56:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"437c1d0a38546aa1f8c9e3fb2ce2fef027b35956bbbfad5d4d89f42245f3b920","abstract_canon_sha256":"bac99e77cf90b52c1a6ec9ab1f945f8998887865016f0ff976e2068f29edccf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:37.020344Z","signature_b64":"a4TsBov+N6XnS06l6z2eqnV4JaGyGgicYJlsk7A7HuQzt9/2onk7ERd+2N4oD1SiqObjif+eoRB0k6w+ZsvtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c47002ba41d20673e1ac710d1b141efeace153b2f9cbd51dc1a8211ff52bb9d","last_reissued_at":"2026-05-18T00:48:37.019664Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:37.019664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Machine Translation in Linear Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron van den Oord, Alex Graves, Karen Simonyan, Koray Kavukcuoglu, Lasse Espeholt, Nal Kalchbrenner","submitted_at":"2016-10-31T19:56:39Z","abstract_excerpt":"We present a novel neural network for processing sequences. The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the target sequence. The two network parts are connected by stacking the decoder on top of the encoder and preserving the temporal resolution of the sequences. To address the differing lengths of the source and the target, we introduce an efficient mechanism by which the decoder is dynamically unfolded over the representation of the encoder. The ByteNet uses dilation in the convolutiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.10099","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":"1610.10099","created_at":"2026-05-18T00:48:37.019772+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.10099v2","created_at":"2026-05-18T00:48:37.019772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.10099","created_at":"2026-05-18T00:48:37.019772+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRDQAK5EDUQG","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRDQAK5EDUQGOPQ2","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRDQAK5E","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.08584","citing_title":"Improving Zero-shot Translation with Language-Independent Constraints","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01300","citing_title":"Learning to Reformulate the Queries on the WEB","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1911.05507","citing_title":"Compressive Transformers for Long-Range Sequence Modelling","ref_index":118,"is_internal_anchor":true},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19343","citing_title":"Scalable Memristive-Friendly Reservoir Computing for Time Series Classification","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07588","citing_title":"Revisiting Transformer Layer Parameterization Through Causal Energy Minimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"1706.03762","citing_title":"Attention Is All You Need","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57","json":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57.json","graph_json":"https://pith.science/api/pith-number/RRDQAK5EDUQGOPQ2Y4INDMKB57/graph.json","events_json":"https://pith.science/api/pith-number/RRDQAK5EDUQGOPQ2Y4INDMKB57/events.json","paper":"https://pith.science/paper/RRDQAK5E"},"agent_actions":{"view_html":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57","download_json":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57.json","view_paper":"https://pith.science/paper/RRDQAK5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.10099&json=true","fetch_graph":"https://pith.science/api/pith-number/RRDQAK5EDUQGOPQ2Y4INDMKB57/graph.json","fetch_events":"https://pith.science/api/pith-number/RRDQAK5EDUQGOPQ2Y4INDMKB57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57/action/storage_attestation","attest_author":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57/action/author_attestation","sign_citation":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57/action/citation_signature","submit_replication":"https://pith.science/pith/RRDQAK5EDUQGOPQ2Y4INDMKB57/action/replication_record"}},"created_at":"2026-05-18T00:48:37.019772+00:00","updated_at":"2026-05-18T00:48:37.019772+00:00"}