{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NDSW2WCJST6PVM5LLWXF7QYSUR","short_pith_number":"pith:NDSW2WCJ","schema_version":"1.0","canonical_sha256":"68e56d584994fcfab3ab5dae5fc312a46800277a0f9e5b91dc3a7bb694f0837c","source":{"kind":"arxiv","id":"2309.14174","version":1},"attestation_state":"computed","paper":{"title":"Only 5\\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingxuan Wang, Shanbo Cheng, Shujian Huang, Zewei Sun, Zihan Liu","submitted_at":"2023-09-25T14:33:47Z","abstract_excerpt":"Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to the standard Transformer model. In this case, efficiency becomes a critical concern due to the quadratic complexity of the attention module. Existing studies either focus on the encoder part, which cannot be deployed on sequence-to-sequence generation tasks, e.g., Machine Translation (MT), or suffer from a significant performance drop. In this work, we keep 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":"2309.14174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-25T14:33:47Z","cross_cats_sorted":[],"title_canon_sha256":"d92523cefbdd0fb5caa7be380c7ea077d0c46f91c6c7d7f0325f4d592b02c55d","abstract_canon_sha256":"34a4d776ae59b51722bcfb56534458f0db5425ea79a9bcb1dec3c5a3ec114cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:02.481994Z","signature_b64":"7c2C0yiau2VnExjvyfxXZPl5R6EmFUaAh4IFz0zBFOtG+9BwBSyIBCNEZ3nfhu1mO5V7wUt1Lw1IrNLGA0ujAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68e56d584994fcfab3ab5dae5fc312a46800277a0f9e5b91dc3a7bb694f0837c","last_reissued_at":"2026-07-05T06:54:02.481572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:02.481572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Only 5\\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mingxuan Wang, Shanbo Cheng, Shujian Huang, Zewei Sun, Zihan Liu","submitted_at":"2023-09-25T14:33:47Z","abstract_excerpt":"Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information. One of the most important directions is to input the whole document directly to the standard Transformer model. In this case, efficiency becomes a critical concern due to the quadratic complexity of the attention module. Existing studies either focus on the encoder part, which cannot be deployed on sequence-to-sequence generation tasks, e.g., Machine Translation (MT), or suffer from a significant performance drop. In this work, we keep t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14174","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.14174/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2309.14174","created_at":"2026-07-05T06:54:02.481627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14174v1","created_at":"2026-07-05T06:54:02.481627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14174","created_at":"2026-07-05T06:54:02.481627+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDSW2WCJST6P","created_at":"2026-07-05T06:54:02.481627+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDSW2WCJST6PVM5L","created_at":"2026-07-05T06:54:02.481627+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDSW2WCJ","created_at":"2026-07-05T06:54:02.481627+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/NDSW2WCJST6PVM5LLWXF7QYSUR","json":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR.json","graph_json":"https://pith.science/api/pith-number/NDSW2WCJST6PVM5LLWXF7QYSUR/graph.json","events_json":"https://pith.science/api/pith-number/NDSW2WCJST6PVM5LLWXF7QYSUR/events.json","paper":"https://pith.science/paper/NDSW2WCJ"},"agent_actions":{"view_html":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR","download_json":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR.json","view_paper":"https://pith.science/paper/NDSW2WCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14174&json=true","fetch_graph":"https://pith.science/api/pith-number/NDSW2WCJST6PVM5LLWXF7QYSUR/graph.json","fetch_events":"https://pith.science/api/pith-number/NDSW2WCJST6PVM5LLWXF7QYSUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR/action/storage_attestation","attest_author":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR/action/author_attestation","sign_citation":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR/action/citation_signature","submit_replication":"https://pith.science/pith/NDSW2WCJST6PVM5LLWXF7QYSUR/action/replication_record"}},"created_at":"2026-07-05T06:54:02.481627+00:00","updated_at":"2026-07-05T06:54:02.481627+00:00"}