{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OPRXACCNNGQSB3DJORAJHQKCT4","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":"f3f218f6513f90dafa9a599339a83a6bb3a5166d624eb29f0b87890dd1076126","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T16:56:50Z","title_canon_sha256":"a837e0f62d28462cf9fe9bf9f221ba0a2fa3c93f5779e82039a7490962e479de"},"schema_version":"1.0","source":{"id":"2407.01463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01463","created_at":"2026-07-05T08:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01463v1","created_at":"2026-07-05T08:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01463","created_at":"2026-07-05T08:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"OPRXACCNNGQS","created_at":"2026-07-05T08:38:48Z"},{"alias_kind":"pith_short_16","alias_value":"OPRXACCNNGQSB3DJ","created_at":"2026-07-05T08:38:48Z"},{"alias_kind":"pith_short_8","alias_value":"OPRXACCN","created_at":"2026-07-05T08:38:48Z"}],"graph_snapshots":[{"event_id":"sha256:96544fb55a81e62faa84f7785ab482113a04c1f05469e1fa347834bc815fc2af","target":"graph","created_at":"2026-07-05T08:38:48Z","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/2407.01463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e. with user queries and the datastore in 13 languages, and investigate which components and with which adjustments are needed to build a well-performing mRAG pipeline, that can be used as a strong baseline in future works. Our findings highlight that despite the availabil","authors_text":"David Rau, Herv\\'e D\\'ejean, Nadezhda Chirkova, St\\'ephane Clinchant, Thibault Formal, Vassilina Nikoulina","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T16:56:50Z","title":"Retrieval-augmented generation in multilingual settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01463","kind":"arxiv","version":1},"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":"sha256:3380b823b87e0f3a5729ce484d22a37d8135a32962e89771aab1be53e55c750c","target":"record","created_at":"2026-07-05T08:38:48Z","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":"f3f218f6513f90dafa9a599339a83a6bb3a5166d624eb29f0b87890dd1076126","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T16:56:50Z","title_canon_sha256":"a837e0f62d28462cf9fe9bf9f221ba0a2fa3c93f5779e82039a7490962e479de"},"schema_version":"1.0","source":{"id":"2407.01463","kind":"arxiv","version":1}},"canonical_sha256":"73e370084d69a120ec69744093c1429f1f1966ea81c374031dad90b8c4539aca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73e370084d69a120ec69744093c1429f1f1966ea81c374031dad90b8c4539aca","first_computed_at":"2026-07-05T08:38:48.371181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:48.371181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eH+MpauEuV+4qun6V7jMBLsgdHfX9lVj9N+IVgz63errNHuldj02IsNpGRVh2i2/XdE9hDJgTg8X+HtjhcgiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:48.371621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3380b823b87e0f3a5729ce484d22a37d8135a32962e89771aab1be53e55c750c","sha256:96544fb55a81e62faa84f7785ab482113a04c1f05469e1fa347834bc815fc2af"],"state_sha256":"037321f9e7bf968a04afc258512c600fb77f9d4e9a7228cb71a973288b8c55df"}