{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YJ7O5KE37MM4SDSNV4S4Z7ELUQ","short_pith_number":"pith:YJ7O5KE3","schema_version":"1.0","canonical_sha256":"c27eeea89bfb19c90e4daf25ccfc8ba405030d7ae3c00aebeaccde3f8a953d75","source":{"kind":"arxiv","id":"2304.12959","version":2},"attestation_state":"computed","paper":{"title":"Escaping the sentence-level paradigm in machine translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcin Junczys-Dowmunt, Matt Post","submitted_at":"2023-04-25T16:09:02Z","abstract_excerpt":"It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation -- both research and production -- largely remains stuck in a decades-old sentence-level translation paradigm. It is also an increasingly glaring problem in light of competitive pressure from large language models, which are natively document-based. Much work in document-context machine translation exists, but for various reasons has been unable to catch hol"},"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":"2304.12959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-25T16:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"b91c5713f59b91c12a7ed04c4fe31b3a93b28ef6a3564b75049e4609f1e4f301","abstract_canon_sha256":"46cd8931a7a62f0e356d0ec694f67356e62f503d1f9f937221245a40c2a04ac3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:34.437259Z","signature_b64":"zO6QfS1d+fbK6o3RO2wC9EdeoxziKvF96kLVHI8GCZUFZjByWF1lr6DxpE7j8Q9ZT41HHamC+dC9vd2OzwrKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c27eeea89bfb19c90e4daf25ccfc8ba405030d7ae3c00aebeaccde3f8a953d75","last_reissued_at":"2026-07-05T08:19:34.436723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:34.436723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Escaping the sentence-level paradigm in machine translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcin Junczys-Dowmunt, Matt Post","submitted_at":"2023-04-25T16:09:02Z","abstract_excerpt":"It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation -- both research and production -- largely remains stuck in a decades-old sentence-level translation paradigm. It is also an increasingly glaring problem in light of competitive pressure from large language models, which are natively document-based. Much work in document-context machine translation exists, but for various reasons has been unable to catch hol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12959","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.12959/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":"2304.12959","created_at":"2026-07-05T08:19:34.436783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12959v2","created_at":"2026-07-05T08:19:34.436783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12959","created_at":"2026-07-05T08:19:34.436783+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJ7O5KE37MM4","created_at":"2026-07-05T08:19:34.436783+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJ7O5KE37MM4SDSN","created_at":"2026-07-05T08:19:34.436783+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJ7O5KE3","created_at":"2026-07-05T08:19:34.436783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29489","citing_title":"Which Tokens Need Context? A Reference-Based Analysis of Translation Responsibility Using Fertility and Entropy","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2505.06120","citing_title":"LLMs Get Lost In Multi-Turn Conversation","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ","json":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ.json","graph_json":"https://pith.science/api/pith-number/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/graph.json","events_json":"https://pith.science/api/pith-number/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/events.json","paper":"https://pith.science/paper/YJ7O5KE3"},"agent_actions":{"view_html":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ","download_json":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ.json","view_paper":"https://pith.science/paper/YJ7O5KE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12959&json=true","fetch_graph":"https://pith.science/api/pith-number/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/action/storage_attestation","attest_author":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/action/author_attestation","sign_citation":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/action/citation_signature","submit_replication":"https://pith.science/pith/YJ7O5KE37MM4SDSNV4S4Z7ELUQ/action/replication_record"}},"created_at":"2026-07-05T08:19:34.436783+00:00","updated_at":"2026-07-05T08:19:34.436783+00:00"}