{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LTHZPGCA2KAUZPD3YLDQOWIZAL","short_pith_number":"pith:LTHZPGCA","schema_version":"1.0","canonical_sha256":"5ccf979840d2814cbc7bc2c707591902fc282ce2f657968a88f0a8623f894fa3","source":{"kind":"arxiv","id":"2504.07803","version":1},"attestation_state":"computed","paper":{"title":"A System for Comprehensive Assessment of RAG Frameworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Domenico Alfano, Mattia Rengo, Roberto Abbruzzese, Senad Beadini","submitted_at":"2025-04-10T14:41:34Z","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"},"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":"2504.07803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-10T14:41:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7d59f0db75de84a9a1505a7bde4e6864d9f1c42bd426cf13421b235cec71734b","abstract_canon_sha256":"072669d13d24fc9f5f667c82e31120e2dc608185743c923731e508a5dd83c5c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:15.021907Z","signature_b64":"U96SITpEdqT/7ng8dfPIfm4VVwttNW7pHuiocG6Q/ZBJExC2M06XfIAgc6v4dSHKjZdFomprYC0mTVQt0Y/LBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ccf979840d2814cbc7bc2c707591902fc282ce2f657968a88f0a8623f894fa3","last_reissued_at":"2026-07-05T10:47:15.021438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:15.021438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A System for Comprehensive Assessment of RAG Frameworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Domenico Alfano, Mattia Rengo, Roberto Abbruzzese, Senad Beadini","submitted_at":"2025-04-10T14:41:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07803","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/2504.07803/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":"2504.07803","created_at":"2026-07-05T10:47:15.021495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07803v1","created_at":"2026-07-05T10:47:15.021495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07803","created_at":"2026-07-05T10:47:15.021495+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTHZPGCA2KAU","created_at":"2026-07-05T10:47:15.021495+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTHZPGCA2KAUZPD3","created_at":"2026-07-05T10:47:15.021495+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTHZPGCA","created_at":"2026-07-05T10:47:15.021495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.14891","citing_title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL","json":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL.json","graph_json":"https://pith.science/api/pith-number/LTHZPGCA2KAUZPD3YLDQOWIZAL/graph.json","events_json":"https://pith.science/api/pith-number/LTHZPGCA2KAUZPD3YLDQOWIZAL/events.json","paper":"https://pith.science/paper/LTHZPGCA"},"agent_actions":{"view_html":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL","download_json":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL.json","view_paper":"https://pith.science/paper/LTHZPGCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07803&json=true","fetch_graph":"https://pith.science/api/pith-number/LTHZPGCA2KAUZPD3YLDQOWIZAL/graph.json","fetch_events":"https://pith.science/api/pith-number/LTHZPGCA2KAUZPD3YLDQOWIZAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL/action/storage_attestation","attest_author":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL/action/author_attestation","sign_citation":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL/action/citation_signature","submit_replication":"https://pith.science/pith/LTHZPGCA2KAUZPD3YLDQOWIZAL/action/replication_record"}},"created_at":"2026-07-05T10:47:15.021495+00:00","updated_at":"2026-07-05T10:47:15.021495+00:00"}