{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSXWMSRRQVVJEPI6VBYR4YOHCB","short_pith_number":"pith:SSXWMSRR","schema_version":"1.0","canonical_sha256":"94af664a31856a923d1ea8711e61c7106b54d49d1d98b87cf24523fb41ce5013","source":{"kind":"arxiv","id":"2410.08143","version":2},"attestation_state":"computed","paper":{"title":"DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Fandong Meng, Jiali Zeng, Jie Zhou, Min Zhang, Xuebo Liu, Yutong Wang","submitted_at":"2024-10-10T17:30:09Z","abstract_excerpt":"Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DelTA, a Document-levEL Translation Agent designed to overcome these limitations. DelTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously"},"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":"2410.08143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:30:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"24f7e18da4f563156a09570bd389557c1d267a516ac38571da35127301a8c18b","abstract_canon_sha256":"7dd0279dd0cca846a9ff88d78d5ed67c115a2721a7e8766b9a2e972f7ace8a57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:54.895128Z","signature_b64":"yWEX72O8rMO0u7/+0e62MHSFitbbEL61mxtBUSTwDnhM44LvIQMFY9DqL7oyWkz9fWektuSCSeEONBFvppkKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94af664a31856a923d1ea8711e61c7106b54d49d1d98b87cf24523fb41ce5013","last_reissued_at":"2026-07-05T10:24:54.894489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:54.894489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Fandong Meng, Jiali Zeng, Jie Zhou, Min Zhang, Xuebo Liu, Yutong Wang","submitted_at":"2024-10-10T17:30:09Z","abstract_excerpt":"Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT). However, most current research on MT-LLMs still faces significant challenges in maintaining translation consistency and accuracy when processing entire documents. In this paper, we introduce DelTA, a Document-levEL Translation Agent designed to overcome these limitations. DelTA features a multi-level memory structure that stores information across various granularities and spans, including Proper Noun Records, Bilingual Summary, Long-Term Memory, and Short-Term Memory, which are continuously"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08143","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/2410.08143/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":"2410.08143","created_at":"2026-07-05T10:24:54.894558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08143v2","created_at":"2026-07-05T10:24:54.894558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08143","created_at":"2026-07-05T10:24:54.894558+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSXWMSRRQVVJ","created_at":"2026-07-05T10:24:54.894558+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSXWMSRRQVVJEPI6","created_at":"2026-07-05T10:24:54.894558+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSXWMSRR","created_at":"2026-07-05T10:24:54.894558+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":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17041","citing_title":"Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB","json":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB.json","graph_json":"https://pith.science/api/pith-number/SSXWMSRRQVVJEPI6VBYR4YOHCB/graph.json","events_json":"https://pith.science/api/pith-number/SSXWMSRRQVVJEPI6VBYR4YOHCB/events.json","paper":"https://pith.science/paper/SSXWMSRR"},"agent_actions":{"view_html":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB","download_json":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB.json","view_paper":"https://pith.science/paper/SSXWMSRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08143&json=true","fetch_graph":"https://pith.science/api/pith-number/SSXWMSRRQVVJEPI6VBYR4YOHCB/graph.json","fetch_events":"https://pith.science/api/pith-number/SSXWMSRRQVVJEPI6VBYR4YOHCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB/action/storage_attestation","attest_author":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB/action/author_attestation","sign_citation":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB/action/citation_signature","submit_replication":"https://pith.science/pith/SSXWMSRRQVVJEPI6VBYR4YOHCB/action/replication_record"}},"created_at":"2026-07-05T10:24:54.894558+00:00","updated_at":"2026-07-05T10:24:54.894558+00:00"}