{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EOEB3NQTIH74T6QOWOOHUX55PV","short_pith_number":"pith:EOEB3NQT","canonical_record":{"source":{"id":"2412.04342","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T17:00:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbd005a349a948cd07b9368dc699230cc2f76556e19399478fb02785627448c6","abstract_canon_sha256":"a66a8bc05e874e7d904651a638bb83ef508a0e61036edae0b5b8e565a4e32146"},"schema_version":"1.0"},"canonical_sha256":"23881db61341ffc9fa0eb39c7a5fbd7d7ed913c150ea5ec06c552a688319d3f3","source":{"kind":"arxiv","id":"2412.04342","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EOEB3NQTIH74T6QOWOOHUX55PV","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04342","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T17:00:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbd005a349a948cd07b9368dc699230cc2f76556e19399478fb02785627448c6","abstract_canon_sha256":"a66a8bc05e874e7d904651a638bb83ef508a0e61036edae0b5b8e565a4e32146"},"schema_version":"1.0"},"canonical_sha256":"23881db61341ffc9fa0eb39c7a5fbd7d7ed913c150ea5ec06c552a688319d3f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:20.103534Z","signature_b64":"sPthHaXlzy0HGICu78Evmu2PYArATD2lKTiTlwAH4YqsRx/2HJiy6dWV8XMZb8eJL7PAxl9Ns8No3ixpFz5WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23881db61341ffc9fa0eb39c7a5fbd7d7ed913c150ea5ec06c552a688319d3f3","last_reissued_at":"2026-07-05T12:01:20.103045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:20.103045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04342","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ExjRvV+JtAopm0X38Qg8Mw05VULi8dyMjX2fzm6E8BqkfpA71gkxsW/zYWp6q8fOU3L7FHWk9fIGK9hn25f+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:37:29.074748Z"},"content_sha256":"923e879ba0e0372060be48ea891c7cbdb423a1306bf1a6c2ab09d7eee5b709a6","schema_version":"1.0","event_id":"sha256:923e879ba0e0372060be48ea891c7cbdb423a1306bf1a6c2ab09d7eee5b709a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EOEB3NQTIH74T6QOWOOHUX55PV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Machine Translation with Unstructured Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fandong Meng, Jiaan Wang, Jie Zhou, Yingxue Zhang","submitted_at":"2024-12-05T17:00:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04342","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/2412.04342/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HzKViDqAFK6+wd5tAfji9wwUURYgd5wpzTn8xFxQxSqKpAbWiiYk+Im0SgKBYqXdpKpm4VjRG+xZ5Ig9Pi5fCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:37:29.075238Z"},"content_sha256":"ee94a0c50fe15e4ca7e3345e0bff0f6ef2a08b212f7d239593e493a8d953c4ab","schema_version":"1.0","event_id":"sha256:ee94a0c50fe15e4ca7e3345e0bff0f6ef2a08b212f7d239593e493a8d953c4ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOEB3NQTIH74T6QOWOOHUX55PV/bundle.json","state_url":"https://pith.science/pith/EOEB3NQTIH74T6QOWOOHUX55PV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOEB3NQTIH74T6QOWOOHUX55PV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T03:37:29Z","links":{"resolver":"https://pith.science/pith/EOEB3NQTIH74T6QOWOOHUX55PV","bundle":"https://pith.science/pith/EOEB3NQTIH74T6QOWOOHUX55PV/bundle.json","state":"https://pith.science/pith/EOEB3NQTIH74T6QOWOOHUX55PV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOEB3NQTIH74T6QOWOOHUX55PV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xl73sD/WVhZS6Pq9chup5ehA5zQ3+dwfJ+5OwNYUnDOINREbadsMujgAXDVzwY4Gb/omV/XB5UCL1dzKSXx8Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:37:29.078401Z","bundle_sha256":"65b34bc8f8526a55d15615475d5219fd217639f3ed4807218e8d898c50754373"}}