{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VB623B6O4QVISOLJ3JD6ZUXKZT","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":"581640afc1b7d71ffff5d8ecb86eb120f179af26e91421c0ea22d74759e74481","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T17:52:07Z","title_canon_sha256":"787d21dc240e0d137997761d63f32d685a311c7d2fb93d858bfefb2e2f1bfde6"},"schema_version":"1.0","source":{"id":"2409.12941","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12941","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12941v3","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12941","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"VB623B6O4QVI","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"VB623B6O4QVISOLJ","created_at":"2026-07-05T10:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"VB623B6O","created_at":"2026-07-05T10:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:ec5b51936c66f5f5f7e95e1c89807114b5093306d2b6f361e12feb328fda161d","target":"graph","created_at":"2026-07-05T10:05:12Z","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/2409.12941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adam Stambler, Anhad Mohananey, Kalpesh Krishna, Manaal Faruqui, Satyapriya Krishna, Shyam Upadhyay, Steven Schwarcz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T17:52:07Z","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12941","kind":"arxiv","version":3},"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":"sha256:9fa10d845f4625abf40cdb88d145a0a39d88b9ac3462dd190398889d7af60852","target":"record","created_at":"2026-07-05T10:05:12Z","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":"581640afc1b7d71ffff5d8ecb86eb120f179af26e91421c0ea22d74759e74481","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-19T17:52:07Z","title_canon_sha256":"787d21dc240e0d137997761d63f32d685a311c7d2fb93d858bfefb2e2f1bfde6"},"schema_version":"1.0","source":{"id":"2409.12941","kind":"arxiv","version":3}},"canonical_sha256":"a87dad87cee42a893969da47ecd2eacce677c7e5c6676cda09acebfd72503397","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a87dad87cee42a893969da47ecd2eacce677c7e5c6676cda09acebfd72503397","first_computed_at":"2026-07-05T10:05:12.873578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:12.873578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhC6a+Nlf131WQyB+m0OfVKd7Oo2a/bXIW4TGiDTMsx+46L7kNVn0tiSIBeZT880rFu22vt2nk0bNeWTyu6wBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:12.874015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12941","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fa10d845f4625abf40cdb88d145a0a39d88b9ac3462dd190398889d7af60852","sha256:ec5b51936c66f5f5f7e95e1c89807114b5093306d2b6f361e12feb328fda161d"],"state_sha256":"0f223509d2784d7fea9abc4daea03fc58f6464ca2e83ebf8d0bc4d80aba7498c"}