{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EOEB3NQTIH74T6QOWOOHUX55PV","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":"a66a8bc05e874e7d904651a638bb83ef508a0e61036edae0b5b8e565a4e32146","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T17:00:32Z","title_canon_sha256":"bbd005a349a948cd07b9368dc699230cc2f76556e19399478fb02785627448c6"},"schema_version":"1.0","source":{"id":"2412.04342","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04342","created_at":"2026-07-05T12:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04342v2","created_at":"2026-07-05T12:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04342","created_at":"2026-07-05T12:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"EOEB3NQTIH74","created_at":"2026-07-05T12:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"EOEB3NQTIH74T6QO","created_at":"2026-07-05T12:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"EOEB3NQT","created_at":"2026-07-05T12:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:ee94a0c50fe15e4ca7e3345e0bff0f6ef2a08b212f7d239593e493a8d953c4ab","target":"graph","created_at":"2026-07-05T12:01:20Z","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/2412.04342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) introduces additional information to enhance large language models (LLMs). In machine translation (MT), previous work typically retrieves in-context examples from paired MT corpora, or domain-specific knowledge from knowledge graphs, to enhance MT models. However, a large amount of world knowledge is organized in unstructured documents, and might not be fully paired across different languages. In this paper, we study retrieval-augmented MT using unstructured documents. Specifically, we build RAGtrans, the first benchmark to train and evaluate LLMs' retrieva","authors_text":"Fandong Meng, Jiaan Wang, Jie Zhou, Yingxue Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T17:00:32Z","title":"Retrieval-Augmented Machine Translation with Unstructured Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04342","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":"sha256:923e879ba0e0372060be48ea891c7cbdb423a1306bf1a6c2ab09d7eee5b709a6","target":"record","created_at":"2026-07-05T12:01:20Z","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":"a66a8bc05e874e7d904651a638bb83ef508a0e61036edae0b5b8e565a4e32146","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T17:00:32Z","title_canon_sha256":"bbd005a349a948cd07b9368dc699230cc2f76556e19399478fb02785627448c6"},"schema_version":"1.0","source":{"id":"2412.04342","kind":"arxiv","version":2}},"canonical_sha256":"23881db61341ffc9fa0eb39c7a5fbd7d7ed913c150ea5ec06c552a688319d3f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23881db61341ffc9fa0eb39c7a5fbd7d7ed913c150ea5ec06c552a688319d3f3","first_computed_at":"2026-07-05T12:01:20.103045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:20.103045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sPthHaXlzy0HGICu78Evmu2PYArATD2lKTiTlwAH4YqsRx/2HJiy6dWV8XMZb8eJL7PAxl9Ns8No3ixpFz5WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:20.103534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04342","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:923e879ba0e0372060be48ea891c7cbdb423a1306bf1a6c2ab09d7eee5b709a6","sha256:ee94a0c50fe15e4ca7e3345e0bff0f6ef2a08b212f7d239593e493a8d953c4ab"],"state_sha256":"d56ca55cb5527ef4bb8d47ef62fafc515ec5ba5babc68d46601a4d83f25ce62c"}