{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UVEHBHP4VAE242OIIBZTUUL4MP","short_pith_number":"pith:UVEHBHP4","schema_version":"1.0","canonical_sha256":"a548709dfca809ae69c840733a517c63f15fe4e2dc75e9e839cbbb6049770dec","source":{"kind":"arxiv","id":"1812.10230","version":1},"attestation_state":"computed","paper":{"title":"Learning to Refine Source Representations for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Longyue Wang, Ting Liu, Xing Wang, Xinwei Geng, Zhaopeng Tu","submitted_at":"2018-12-26T05:17:03Z","abstract_excerpt":"Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if the sentence is ambiguous. When translating a text, humans often create an initial understanding of the source sentence and then incrementally refine it along the translation on the target side. Starting from this intuition, we propose a novel encoder-refiner-decoder framework, which dynamically refines the source representations based on the generated targ"},"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":"1812.10230","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-26T05:17:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"36160e7c10b2db18b8130185b23b9280af16b2617dbdfe267dbf4e718d6c562e","abstract_canon_sha256":"f3f78c4f8e0de120cf0948db32482c5c6487f39362d22b8449bf550f489765c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:24.744169Z","signature_b64":"Rynf6vgqVj7OSSrlL7zaKCvFv+T8vf/3uL/CnvZQ1rdEN+ilOuI81ZYaQp6CFrnh7CW1AKCnbTpnN+H5XPYvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a548709dfca809ae69c840733a517c63f15fe4e2dc75e9e839cbbb6049770dec","last_reissued_at":"2026-05-17T23:57:24.743499Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:24.743499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Refine Source Representations for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bing Qin, Longyue Wang, Ting Liu, Xing Wang, Xinwei Geng, Zhaopeng Tu","submitted_at":"2018-12-26T05:17:03Z","abstract_excerpt":"Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if the sentence is ambiguous. When translating a text, humans often create an initial understanding of the source sentence and then incrementally refine it along the translation on the target side. Starting from this intuition, we propose a novel encoder-refiner-decoder framework, which dynamically refines the source representations based on the generated targ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10230","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":"1812.10230","created_at":"2026-05-17T23:57:24.743613+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10230v1","created_at":"2026-05-17T23:57:24.743613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10230","created_at":"2026-05-17T23:57:24.743613+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVEHBHP4VAE2","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVEHBHP4VAE242OI","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVEHBHP4","created_at":"2026-05-18T12:32:56.356000+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/UVEHBHP4VAE242OIIBZTUUL4MP","json":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP.json","graph_json":"https://pith.science/api/pith-number/UVEHBHP4VAE242OIIBZTUUL4MP/graph.json","events_json":"https://pith.science/api/pith-number/UVEHBHP4VAE242OIIBZTUUL4MP/events.json","paper":"https://pith.science/paper/UVEHBHP4"},"agent_actions":{"view_html":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP","download_json":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP.json","view_paper":"https://pith.science/paper/UVEHBHP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10230&json=true","fetch_graph":"https://pith.science/api/pith-number/UVEHBHP4VAE242OIIBZTUUL4MP/graph.json","fetch_events":"https://pith.science/api/pith-number/UVEHBHP4VAE242OIIBZTUUL4MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP/action/storage_attestation","attest_author":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP/action/author_attestation","sign_citation":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP/action/citation_signature","submit_replication":"https://pith.science/pith/UVEHBHP4VAE242OIIBZTUUL4MP/action/replication_record"}},"created_at":"2026-05-17T23:57:24.743613+00:00","updated_at":"2026-05-17T23:57:24.743613+00:00"}