{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TTSJPPPNWBPLQ6YWXELUXP5TFE","short_pith_number":"pith:TTSJPPPN","schema_version":"1.0","canonical_sha256":"9ce497bdedb05eb87b16b9174bbfb329107aa92a9104596719e9d7b4f3343e20","source":{"kind":"arxiv","id":"1810.13409","version":1},"attestation_state":"computed","paper":{"title":"You May Not Need Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Noah A. Smith, Ofir Press","submitted_at":"2018-10-31T17:09:37Z","abstract_excerpt":"In NMT, how far can we get without attention and without separate encoding and decoding? To answer that question, we introduce a recurrent neural translation model that does not use attention and does not have a separate encoder and decoder. Our eager translation model is low-latency, writing target tokens as soon as it reads the first source token, and uses constant memory during decoding. It performs on par with the standard attention-based model of Bahdanau et al. (2014), and better on long sentences."},"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":"1810.13409","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-31T17:09:37Z","cross_cats_sorted":[],"title_canon_sha256":"4355904d90f1ba93c618947ece258b138908ee3687170f728d5b81189da3da28","abstract_canon_sha256":"04b090dc0c86b0613bf291bdd4d937031309d5f9dd6d7b406018ecf067605576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:49.393270Z","signature_b64":"1tR4pyFkZ88AacHbYU+vfQfcK7g1nEOstl17u/uYvbq2Y4+ojCgZclhT9FdI4Y7VPSb4ZGzJ3ADBUbgQfDvbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ce497bdedb05eb87b16b9174bbfb329107aa92a9104596719e9d7b4f3343e20","last_reissued_at":"2026-05-18T00:01:49.392600Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:49.392600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You May Not Need Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Noah A. Smith, Ofir Press","submitted_at":"2018-10-31T17:09:37Z","abstract_excerpt":"In NMT, how far can we get without attention and without separate encoding and decoding? To answer that question, we introduce a recurrent neural translation model that does not use attention and does not have a separate encoder and decoder. Our eager translation model is low-latency, writing target tokens as soon as it reads the first source token, and uses constant memory during decoding. It performs on par with the standard attention-based model of Bahdanau et al. (2014), and better on long sentences."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.13409","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":"1810.13409","created_at":"2026-05-18T00:01:49.392705+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.13409v1","created_at":"2026-05-18T00:01:49.392705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.13409","created_at":"2026-05-18T00:01:49.392705+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTSJPPPNWBPL","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTSJPPPNWBPLQ6YW","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTSJPPPN","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09444","citing_title":"Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE","json":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE.json","graph_json":"https://pith.science/api/pith-number/TTSJPPPNWBPLQ6YWXELUXP5TFE/graph.json","events_json":"https://pith.science/api/pith-number/TTSJPPPNWBPLQ6YWXELUXP5TFE/events.json","paper":"https://pith.science/paper/TTSJPPPN"},"agent_actions":{"view_html":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE","download_json":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE.json","view_paper":"https://pith.science/paper/TTSJPPPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.13409&json=true","fetch_graph":"https://pith.science/api/pith-number/TTSJPPPNWBPLQ6YWXELUXP5TFE/graph.json","fetch_events":"https://pith.science/api/pith-number/TTSJPPPNWBPLQ6YWXELUXP5TFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE/action/storage_attestation","attest_author":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE/action/author_attestation","sign_citation":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE/action/citation_signature","submit_replication":"https://pith.science/pith/TTSJPPPNWBPLQ6YWXELUXP5TFE/action/replication_record"}},"created_at":"2026-05-18T00:01:49.392705+00:00","updated_at":"2026-05-18T00:01:49.392705+00:00"}