{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MX2SKUNXJ7VBMB3TTRJGZR323I","short_pith_number":"pith:MX2SKUNX","schema_version":"1.0","canonical_sha256":"65f52551b74fea1607739c526cc77ada3e1dad6979be5d24a4aaf8af9adc891a","source":{"kind":"arxiv","id":"1610.06602","version":3},"attestation_state":"computed","paper":{"title":"Iterative Refinement for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Grangier, Michael Auli, Roman Novak","submitted_at":"2016-10-20T20:54:07Z","abstract_excerpt":"Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a translation scheme that starts from an initial guess and then makes iterative improvements that may revisit previous decisions. We parameterize our model as a convolutional neural network that predicts discrete substitutions to an existing translation based on an attention mechanism over both the source sentence as well as the current translation output. By mak"},"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":"1610.06602","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-20T20:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"a098dbcd39bc85d9585e2af8bcc6f72892f3b8166763e4e694b0f806d7338bcd","abstract_canon_sha256":"38770f9bf25c472ee96395ebf4cffb10c0227b154b9f0a43d99a41c46b8ab261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:32.058924Z","signature_b64":"b9ZG1ljRc9Xic5HdGciQUaz1jUvpM7Nbyjv4hth+PxZ6UJ36bUJDRRDM0Wl59GZQiKpsELgzBefySquc3AkoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f52551b74fea1607739c526cc77ada3e1dad6979be5d24a4aaf8af9adc891a","last_reissued_at":"2026-05-18T00:18:32.058529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:32.058529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Refinement for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Grangier, Michael Auli, Roman Novak","submitted_at":"2016-10-20T20:54:07Z","abstract_excerpt":"Existing machine translation decoding algorithms generate translations in a strictly monotonic fashion and never revisit previous decisions. As a result, earlier mistakes cannot be corrected at a later stage. In this paper, we present a translation scheme that starts from an initial guess and then makes iterative improvements that may revisit previous decisions. We parameterize our model as a convolutional neural network that predicts discrete substitutions to an existing translation based on an attention mechanism over both the source sentence as well as the current translation output. By mak"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.06602","kind":"arxiv","version":3},"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":"1610.06602","created_at":"2026-05-18T00:18:32.058593+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.06602v3","created_at":"2026-05-18T00:18:32.058593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.06602","created_at":"2026-05-18T00:18:32.058593+00:00"},{"alias_kind":"pith_short_12","alias_value":"MX2SKUNXJ7VB","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MX2SKUNXJ7VBMB3T","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MX2SKUNX","created_at":"2026-05-18T12:30:32.724797+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/MX2SKUNXJ7VBMB3TTRJGZR323I","json":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I.json","graph_json":"https://pith.science/api/pith-number/MX2SKUNXJ7VBMB3TTRJGZR323I/graph.json","events_json":"https://pith.science/api/pith-number/MX2SKUNXJ7VBMB3TTRJGZR323I/events.json","paper":"https://pith.science/paper/MX2SKUNX"},"agent_actions":{"view_html":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I","download_json":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I.json","view_paper":"https://pith.science/paper/MX2SKUNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.06602&json=true","fetch_graph":"https://pith.science/api/pith-number/MX2SKUNXJ7VBMB3TTRJGZR323I/graph.json","fetch_events":"https://pith.science/api/pith-number/MX2SKUNXJ7VBMB3TTRJGZR323I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I/action/storage_attestation","attest_author":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I/action/author_attestation","sign_citation":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I/action/citation_signature","submit_replication":"https://pith.science/pith/MX2SKUNXJ7VBMB3TTRJGZR323I/action/replication_record"}},"created_at":"2026-05-18T00:18:32.058593+00:00","updated_at":"2026-05-18T00:18:32.058593+00:00"}