{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYX4W2GQB6M7M3JINR5F6XODNI","short_pith_number":"pith:YYX4W2GQ","schema_version":"1.0","canonical_sha256":"c62fcb68d00f99f66d286c7a5f5dc36a2275f1fb63d79a2c916b338e79627306","source":{"kind":"arxiv","id":"2401.08088","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jing Jiang, Junhui Li, Min Zhang, Yachao Li","submitted_at":"2024-01-16T03:28:26Z","abstract_excerpt":"Existing large language models (LLMs) for machine translation are typically fine-tuned on sentence-level translation instructions and achieve satisfactory performance at the sentence level. However, when applied to document-level translation, these models face a significant challenge, particularly when dealing with documents containing over 512 tokens. This challenge arises from the issue of sentence-level coverage, where subsequent sentences in the document remain untranslated. As a result, the document-level translation capability of LLMs fine-tuned on sentence-level translation instructions"},"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":"2401.08088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-16T03:28:26Z","cross_cats_sorted":[],"title_canon_sha256":"565f181ed389d400862c4dc15dbbe86e778c185875a11140dbbddc9df61aff4b","abstract_canon_sha256":"91707910041a90c2b92cea0c7295a6f5d2fae91e726aac3b1c0464f6c36eb013"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:07.142382Z","signature_b64":"Qac+sJV8hN3J7izWGrr/P1XiX+wz67i7Qklj/ZmHxOLQARndb7RA8dGKNexuAMMqxevnYFw9WdR/LfTMfLooCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c62fcb68d00f99f66d286c7a5f5dc36a2275f1fb63d79a2c916b338e79627306","last_reissued_at":"2026-07-05T07:34:07.141884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:07.141884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jing Jiang, Junhui Li, Min Zhang, Yachao Li","submitted_at":"2024-01-16T03:28:26Z","abstract_excerpt":"Existing large language models (LLMs) for machine translation are typically fine-tuned on sentence-level translation instructions and achieve satisfactory performance at the sentence level. However, when applied to document-level translation, these models face a significant challenge, particularly when dealing with documents containing over 512 tokens. This challenge arises from the issue of sentence-level coverage, where subsequent sentences in the document remain untranslated. As a result, the document-level translation capability of LLMs fine-tuned on sentence-level translation instructions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08088","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/2401.08088/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":"2401.08088","created_at":"2026-07-05T07:34:07.141941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08088v1","created_at":"2026-07-05T07:34:07.141941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08088","created_at":"2026-07-05T07:34:07.141941+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYX4W2GQB6M7","created_at":"2026-07-05T07:34:07.141941+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYX4W2GQB6M7M3JI","created_at":"2026-07-05T07:34:07.141941+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYX4W2GQ","created_at":"2026-07-05T07:34:07.141941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07583","citing_title":"Beyond the Sentence: A Survey on Context-Aware Machine Translation with Large Language Models","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI","json":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI.json","graph_json":"https://pith.science/api/pith-number/YYX4W2GQB6M7M3JINR5F6XODNI/graph.json","events_json":"https://pith.science/api/pith-number/YYX4W2GQB6M7M3JINR5F6XODNI/events.json","paper":"https://pith.science/paper/YYX4W2GQ"},"agent_actions":{"view_html":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI","download_json":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI.json","view_paper":"https://pith.science/paper/YYX4W2GQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08088&json=true","fetch_graph":"https://pith.science/api/pith-number/YYX4W2GQB6M7M3JINR5F6XODNI/graph.json","fetch_events":"https://pith.science/api/pith-number/YYX4W2GQB6M7M3JINR5F6XODNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI/action/storage_attestation","attest_author":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI/action/author_attestation","sign_citation":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI/action/citation_signature","submit_replication":"https://pith.science/pith/YYX4W2GQB6M7M3JINR5F6XODNI/action/replication_record"}},"created_at":"2026-07-05T07:34:07.141941+00:00","updated_at":"2026-07-05T07:34:07.141941+00:00"}