{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LTHZPGCA2KAUZPD3YLDQOWIZAL","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":"072669d13d24fc9f5f667c82e31120e2dc608185743c923731e508a5dd83c5c1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T14:41:34Z","title_canon_sha256":"7d59f0db75de84a9a1505a7bde4e6864d9f1c42bd426cf13421b235cec71734b"},"schema_version":"1.0","source":{"id":"2504.07803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07803","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07803v1","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07803","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"LTHZPGCA2KAU","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_16","alias_value":"LTHZPGCA2KAUZPD3","created_at":"2026-07-05T10:47:15Z"},{"alias_kind":"pith_short_8","alias_value":"LTHZPGCA","created_at":"2026-07-05T10:47:15Z"}],"graph_snapshots":[{"event_id":"sha256:44fc711b0c427c19a8bc4e80925499dba092b2d6dec1b5334eeb82771f1ac098","target":"graph","created_at":"2026-07-05T10:47:15Z","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/2504.07803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval Augmented Generation (RAG) has emerged as a standard paradigm for enhancing the factual accuracy and contextual relevance of Large Language Models (LLMs) by integrating retrieval mechanisms. However, existing evaluation frameworks fail to provide a holistic black-box approach to assessing RAG systems, especially in real-world deployment scenarios. To address this gap, we introduce SCARF (System for Comprehensive Assessment of RAG Frameworks), a modular and flexible evaluation framework designed to benchmark deployed RAG applications systematically. SCARF provides an end-to-end, black","authors_text":"Domenico Alfano, Mattia Rengo, Roberto Abbruzzese, Senad Beadini","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T14:41:34Z","title":"A System for Comprehensive Assessment of RAG Frameworks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07803","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":"sha256:8f79eab2f2882b4f9e6994a10faf9d867e12434d4c5bfa7f8769e52c820df2b0","target":"record","created_at":"2026-07-05T10:47:15Z","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":"072669d13d24fc9f5f667c82e31120e2dc608185743c923731e508a5dd83c5c1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T14:41:34Z","title_canon_sha256":"7d59f0db75de84a9a1505a7bde4e6864d9f1c42bd426cf13421b235cec71734b"},"schema_version":"1.0","source":{"id":"2504.07803","kind":"arxiv","version":1}},"canonical_sha256":"5ccf979840d2814cbc7bc2c707591902fc282ce2f657968a88f0a8623f894fa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ccf979840d2814cbc7bc2c707591902fc282ce2f657968a88f0a8623f894fa3","first_computed_at":"2026-07-05T10:47:15.021438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:15.021438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U96SITpEdqT/7ng8dfPIfm4VVwttNW7pHuiocG6Q/ZBJExC2M06XfIAgc6v4dSHKjZdFomprYC0mTVQt0Y/LBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:15.021907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f79eab2f2882b4f9e6994a10faf9d867e12434d4c5bfa7f8769e52c820df2b0","sha256:44fc711b0c427c19a8bc4e80925499dba092b2d6dec1b5334eeb82771f1ac098"],"state_sha256":"36916c5cb282db4cb98125280df75742fc8468b502bbcba72e58f2e439266fd5"}