{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BQPOMELTDGS2EM5WHCDJYKJB2G","short_pith_number":"pith:BQPOMELT","schema_version":"1.0","canonical_sha256":"0c1ee6117319a5a233b638869c2921d1ab5e32e8be3a9274ad1c13569878eafa","source":{"kind":"arxiv","id":"2409.18006","version":3},"attestation_state":"computed","paper":{"title":"Evaluating Multilingual Long-Context Models for Retrieval and Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ameeta Agrawal, Andy Dang, Rhitabrat Pokharel, Russell Scheinberg, Sina Bagheri Nezhad","submitted_at":"2024-09-26T16:15:14Z","abstract_excerpt":"Recent large language models (LLMs) demonstrate impressive capabilities in handling long contexts, some exhibiting near-perfect recall on synthetic retrieval tasks. However, these evaluations have mainly focused on English text and involved a single target sentence within lengthy contexts. Our work investigates how LLM performance generalizes to multilingual settings with multiple hidden target sentences. We create a new dataset -- mLongRR -- to comprehensively evaluate several multilingual long-context LLMs on retrieval and reasoning tasks across five languages: English, Vietnamese, Indonesia"},"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":"2409.18006","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:15:14Z","cross_cats_sorted":[],"title_canon_sha256":"fd8cbef4b8b9074d4248da80e5dcacedc7a75341661c44ebeae2fcb59e44b488","abstract_canon_sha256":"1c2ce2379c524e528dd5e684ee154b087fe60d368f5cc9a6b29d95b3c43e6874"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:32.150410Z","signature_b64":"y2vplJRIKOsnRcVPrOF4G5unwjZFoHnxmOgabBH438TYf53dK+vastEVU5E2DqTH4v3ZSjQ95edtjWYps1elAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1ee6117319a5a233b638869c2921d1ab5e32e8be3a9274ad1c13569878eafa","last_reissued_at":"2026-07-05T09:19:32.149864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:32.149864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Multilingual Long-Context Models for Retrieval and Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ameeta Agrawal, Andy Dang, Rhitabrat Pokharel, Russell Scheinberg, Sina Bagheri Nezhad","submitted_at":"2024-09-26T16:15:14Z","abstract_excerpt":"Recent large language models (LLMs) demonstrate impressive capabilities in handling long contexts, some exhibiting near-perfect recall on synthetic retrieval tasks. However, these evaluations have mainly focused on English text and involved a single target sentence within lengthy contexts. Our work investigates how LLM performance generalizes to multilingual settings with multiple hidden target sentences. We create a new dataset -- mLongRR -- to comprehensively evaluate several multilingual long-context LLMs on retrieval and reasoning tasks across five languages: English, Vietnamese, Indonesia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18006","kind":"arxiv","version":3},"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/2409.18006/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":"2409.18006","created_at":"2026-07-05T09:19:32.149921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18006v3","created_at":"2026-07-05T09:19:32.149921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18006","created_at":"2026-07-05T09:19:32.149921+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQPOMELTDGS2","created_at":"2026-07-05T09:19:32.149921+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQPOMELTDGS2EM5W","created_at":"2026-07-05T09:19:32.149921+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQPOMELT","created_at":"2026-07-05T09:19:32.149921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G","json":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G.json","graph_json":"https://pith.science/api/pith-number/BQPOMELTDGS2EM5WHCDJYKJB2G/graph.json","events_json":"https://pith.science/api/pith-number/BQPOMELTDGS2EM5WHCDJYKJB2G/events.json","paper":"https://pith.science/paper/BQPOMELT"},"agent_actions":{"view_html":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G","download_json":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G.json","view_paper":"https://pith.science/paper/BQPOMELT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18006&json=true","fetch_graph":"https://pith.science/api/pith-number/BQPOMELTDGS2EM5WHCDJYKJB2G/graph.json","fetch_events":"https://pith.science/api/pith-number/BQPOMELTDGS2EM5WHCDJYKJB2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G/action/storage_attestation","attest_author":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G/action/author_attestation","sign_citation":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G/action/citation_signature","submit_replication":"https://pith.science/pith/BQPOMELTDGS2EM5WHCDJYKJB2G/action/replication_record"}},"created_at":"2026-07-05T09:19:32.149921+00:00","updated_at":"2026-07-05T09:19:32.149921+00:00"}