{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7KI3OSOPXNOW7FDADT2R2WBPLI","short_pith_number":"pith:7KI3OSOP","schema_version":"1.0","canonical_sha256":"fa91b749cfbb5d6f94601cf51d582f5a2f2b44d567967d4dbb2c73d0d4dfdd0f","source":{"kind":"arxiv","id":"2503.00353","version":1},"attestation_state":"computed","paper":{"title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Bohan Li, Haofen Wang, Wenlong Wu, Yunfan Gao, Yun Xiong, Zijing Huang","submitted_at":"2025-03-01T05:05:24Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have expanded their context windows to unprecedented lengths, sparking debates about the necessity of Retrieval-Augmented Generation (RAG). To address the fragmented evaluation paradigms and limited cases in existing Needle-in-a-Haystack (NIAH), this paper introduces U-NIAH, a unified framework that systematically compares LLMs and RAG methods in controlled long context settings. Our framework extends beyond traditional NIAH by incorporating multi-needle, long-needle, and needle-in-needle configurations, along with different retrieval setting"},"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":"2503.00353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-01T05:05:24Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b058ee1f3df1a529162c483812174befa71e177a89b655bbf0d5b054d74ed625","abstract_canon_sha256":"cdd15d37a1dcb5b4d229873a9d5dd7316ca300a95e2238599a8b989a65eeb704"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:21.244592Z","signature_b64":"I7oAKMGyS5d4BDCgCbKJlKIKts7lbEQXBa2+WUcO1/Q8TUkukm2uGgJz5H2WbTS+ty/u5iESiVtRmz0DmdfZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa91b749cfbb5d6f94601cf51d582f5a2f2b44d567967d4dbb2c73d0d4dfdd0f","last_reissued_at":"2026-07-05T10:22:21.244069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:21.244069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Bohan Li, Haofen Wang, Wenlong Wu, Yunfan Gao, Yun Xiong, Zijing Huang","submitted_at":"2025-03-01T05:05:24Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have expanded their context windows to unprecedented lengths, sparking debates about the necessity of Retrieval-Augmented Generation (RAG). To address the fragmented evaluation paradigms and limited cases in existing Needle-in-a-Haystack (NIAH), this paper introduces U-NIAH, a unified framework that systematically compares LLMs and RAG methods in controlled long context settings. Our framework extends beyond traditional NIAH by incorporating multi-needle, long-needle, and needle-in-needle configurations, along with different retrieval setting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00353","kind":"arxiv","version":1},"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/2503.00353/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":"2503.00353","created_at":"2026-07-05T10:22:21.244137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00353v1","created_at":"2026-07-05T10:22:21.244137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00353","created_at":"2026-07-05T10:22:21.244137+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KI3OSOPXNOW","created_at":"2026-07-05T10:22:21.244137+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KI3OSOPXNOW7FDA","created_at":"2026-07-05T10:22:21.244137+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KI3OSOP","created_at":"2026-07-05T10:22:21.244137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI","json":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI.json","graph_json":"https://pith.science/api/pith-number/7KI3OSOPXNOW7FDADT2R2WBPLI/graph.json","events_json":"https://pith.science/api/pith-number/7KI3OSOPXNOW7FDADT2R2WBPLI/events.json","paper":"https://pith.science/paper/7KI3OSOP"},"agent_actions":{"view_html":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI","download_json":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI.json","view_paper":"https://pith.science/paper/7KI3OSOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00353&json=true","fetch_graph":"https://pith.science/api/pith-number/7KI3OSOPXNOW7FDADT2R2WBPLI/graph.json","fetch_events":"https://pith.science/api/pith-number/7KI3OSOPXNOW7FDADT2R2WBPLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI/action/storage_attestation","attest_author":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI/action/author_attestation","sign_citation":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI/action/citation_signature","submit_replication":"https://pith.science/pith/7KI3OSOPXNOW7FDADT2R2WBPLI/action/replication_record"}},"created_at":"2026-07-05T10:22:21.244137+00:00","updated_at":"2026-07-05T10:22:21.244137+00:00"}