{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VB623B6O4QVISOLJ3JD6ZUXKZT","short_pith_number":"pith:VB623B6O","schema_version":"1.0","canonical_sha256":"a87dad87cee42a893969da47ecd2eacce677c7e5c6676cda09acebfd72503397","source":{"kind":"arxiv","id":"2409.12941","version":3},"attestation_state":"computed","paper":{"title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Stambler, Anhad Mohananey, Kalpesh Krishna, Manaal Faruqui, Satyapriya Krishna, Shyam Upadhyay, Steven Schwarcz","submitted_at":"2024-09-19T17:52:07Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require LLMs to understand user queries, retrieve relevant information, and synthesize coherent and accurate responses. Given the increasing real-world deployment of such systems, comprehensive evaluation becomes crucial. To this end, we propose FRAMES (Factuality, Retrieval, And reasoning MEasurement Set), a high-quality evaluation dataset designed to test LLMs' abil"},"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":"2409.12941","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T17:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"787d21dc240e0d137997761d63f32d685a311c7d2fb93d858bfefb2e2f1bfde6","abstract_canon_sha256":"581640afc1b7d71ffff5d8ecb86eb120f179af26e91421c0ea22d74759e74481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:12.874015Z","signature_b64":"ZhC6a+Nlf131WQyB+m0OfVKd7Oo2a/bXIW4TGiDTMsx+46L7kNVn0tiSIBeZT880rFu22vt2nk0bNeWTyu6wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a87dad87cee42a893969da47ecd2eacce677c7e5c6676cda09acebfd72503397","last_reissued_at":"2026-07-05T10:05:12.873578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:12.873578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Stambler, Anhad Mohananey, Kalpesh Krishna, Manaal Faruqui, Satyapriya Krishna, Shyam Upadhyay, Steven Schwarcz","submitted_at":"2024-09-19T17:52:07Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant performance improvements across various cognitive tasks. An emerging application is using LLMs to enhance retrieval-augmented generation (RAG) capabilities. These systems require LLMs to understand user queries, retrieve relevant information, and synthesize coherent and accurate responses. Given the increasing real-world deployment of such systems, comprehensive evaluation becomes crucial. To this end, we propose FRAMES (Factuality, Retrieval, And reasoning MEasurement Set), a high-quality evaluation dataset designed to test LLMs' abil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12941","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/2409.12941/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":"2409.12941","created_at":"2026-07-05T10:05:12.873636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12941v3","created_at":"2026-07-05T10:05:12.873636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12941","created_at":"2026-07-05T10:05:12.873636+00:00"},{"alias_kind":"pith_short_12","alias_value":"VB623B6O4QVI","created_at":"2026-07-05T10:05:12.873636+00:00"},{"alias_kind":"pith_short_16","alias_value":"VB623B6O4QVISOLJ","created_at":"2026-07-05T10:05:12.873636+00:00"},{"alias_kind":"pith_short_8","alias_value":"VB623B6O","created_at":"2026-07-05T10:05:12.873636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09916","citing_title":"IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27595","citing_title":"Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14786","citing_title":"Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22154","citing_title":"IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2411.04368","citing_title":"Measuring short-form factuality in large language models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26692","citing_title":"Kimi Linear: An Expressive, Efficient Attention Architecture","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07927","citing_title":"EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20534","citing_title":"Kimi K2: Open Agentic Intelligence","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT","json":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT.json","graph_json":"https://pith.science/api/pith-number/VB623B6O4QVISOLJ3JD6ZUXKZT/graph.json","events_json":"https://pith.science/api/pith-number/VB623B6O4QVISOLJ3JD6ZUXKZT/events.json","paper":"https://pith.science/paper/VB623B6O"},"agent_actions":{"view_html":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT","download_json":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT.json","view_paper":"https://pith.science/paper/VB623B6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12941&json=true","fetch_graph":"https://pith.science/api/pith-number/VB623B6O4QVISOLJ3JD6ZUXKZT/graph.json","fetch_events":"https://pith.science/api/pith-number/VB623B6O4QVISOLJ3JD6ZUXKZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT/action/storage_attestation","attest_author":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT/action/author_attestation","sign_citation":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT/action/citation_signature","submit_replication":"https://pith.science/pith/VB623B6O4QVISOLJ3JD6ZUXKZT/action/replication_record"}},"created_at":"2026-07-05T10:05:12.873636+00:00","updated_at":"2026-07-05T10:05:12.873636+00:00"}