{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JM7GCQRCVSUU6O5CRP3B435A54","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ecd12f5600996cc7e0464c232bf0a5083a87130cf2355c587bd30058fa546c20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T14:52:22Z","title_canon_sha256":"f08e5f150beeae707a9774391afc5a1c1e8b0d28da6aedc1a3d997d65a373d88"},"schema_version":"1.0","source":{"id":"2504.12140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12140","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12140v2","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12140","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"JM7GCQRCVSUU","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"JM7GCQRCVSUU6O5C","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"JM7GCQRC","created_at":"2026-07-05T12:00:49Z"}],"graph_snapshots":[{"event_id":"sha256:812a3cc1892d9e18204262a7b1b64e7921c25fc224a3b039feaee5f8b5c3ce2b","target":"graph","created_at":"2026-07-05T12:00:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.12140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena across sentences and paragraphs. In this work, we propose a method to improve LLM-based long-document translation through targeted fine-tuning on high-quality document-level data, which we curate and introduce as DocBlocks. Our approach supports multiple translation paradigms, including direct document-to-document and chunk-level translation, by integrating","authors_text":"Andr\\'e F. T. Martins, Miguel Moura Ramos, Patrick Fernandes, Sweta Agrawal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T14:52:22Z","title":"Multilingual Contextualization of Large Language Models for Document-Level Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12140","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:467cac2b43cd12294fc514e2231ced8c0769208c987fc1f45cc68baf3b8870d1","target":"record","created_at":"2026-07-05T12:00:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ecd12f5600996cc7e0464c232bf0a5083a87130cf2355c587bd30058fa546c20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-16T14:52:22Z","title_canon_sha256":"f08e5f150beeae707a9774391afc5a1c1e8b0d28da6aedc1a3d997d65a373d88"},"schema_version":"1.0","source":{"id":"2504.12140","kind":"arxiv","version":2}},"canonical_sha256":"4b3e614222aca94f3ba28bf61e6fa0ef0ca6637eb1f57d1814213ff51f7fbce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b3e614222aca94f3ba28bf61e6fa0ef0ca6637eb1f57d1814213ff51f7fbce8","first_computed_at":"2026-07-05T12:00:49.507390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:49.507390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FWlWYYtTgYcfD+5vAUhjbfZlSwvOd0woGkShUo5PVmIxA2RYn7jKJcPVw68RjvzOoecXLl6uNNQQGCF3z0J7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:49.507881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:467cac2b43cd12294fc514e2231ced8c0769208c987fc1f45cc68baf3b8870d1","sha256:812a3cc1892d9e18204262a7b1b64e7921c25fc224a3b039feaee5f8b5c3ce2b"],"state_sha256":"e5d024594874d63755478575339b28f37d1958f27763df6bef7a73946f3739ff"}