{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XL6JKUIWPGLO2JMWXNIBCDKN3P","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":"dcc2adcebd826a335f44328f2f694c3204a02cba088a73a3966da0b13827f879","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-20T23:20:34Z","title_canon_sha256":"2b7b2d2ab150e9e49e658b48d1cca2b7ae9c2932ef93cb5cb0e3d3ef2041022b"},"schema_version":"1.0","source":{"id":"2406.14783","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14783","created_at":"2026-07-05T11:07:58Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14783v2","created_at":"2026-07-05T11:07:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14783","created_at":"2026-07-05T11:07:58Z"},{"alias_kind":"pith_short_12","alias_value":"XL6JKUIWPGLO","created_at":"2026-07-05T11:07:58Z"},{"alias_kind":"pith_short_16","alias_value":"XL6JKUIWPGLO2JMW","created_at":"2026-07-05T11:07:58Z"},{"alias_kind":"pith_short_8","alias_value":"XL6JKUIW","created_at":"2026-07-05T11:07:58Z"}],"graph_snapshots":[{"event_id":"sha256:8c6548b55de4be3154ff19c240fc8011c85825309f8510e6b6f59754b6870a53","target":"graph","created_at":"2026-07-05T11:07:58Z","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/2406.14783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Challenges in the automated evaluation of Retrieval-Augmented Generation (RAG) Question-Answering (QA) systems include hallucination problems in domain-specific knowledge and the lack of gold standard benchmarks for company internal tasks. This results in difficulties in evaluating RAG variations, like RAG-Fusion (RAGF), in the context of a product QA task at Infineon Technologies. To solve these problems, we propose a comprehensive evaluation framework, which leverages Large Language Models (LLMs) to generate large datasets of synthetic queries based on real user queries and in-domain documen","authors_text":"Arthur C\\^amara, Jakub Zavrel, Zackary Rackauckas","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-20T23:20:34Z","title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14783","kind":"arxiv","version":2},"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":"sha256:24774a387ce736efe76d065c9e8cd6dca7bc07e842af44399160120a47404523","target":"record","created_at":"2026-07-05T11:07:58Z","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":"dcc2adcebd826a335f44328f2f694c3204a02cba088a73a3966da0b13827f879","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-20T23:20:34Z","title_canon_sha256":"2b7b2d2ab150e9e49e658b48d1cca2b7ae9c2932ef93cb5cb0e3d3ef2041022b"},"schema_version":"1.0","source":{"id":"2406.14783","kind":"arxiv","version":2}},"canonical_sha256":"bafc9551167996ed2596bb50110d4ddbd18626f8abb621f6d49a1236f5eefd9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bafc9551167996ed2596bb50110d4ddbd18626f8abb621f6d49a1236f5eefd9f","first_computed_at":"2026-07-05T11:07:58.184231Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:58.184231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxpBOLF3pIXiP7etGLLaO7ajW4x3Emq4asYHicCt7omCV/ThquuEeosJ90ZQgvacTtvd3VYCzUsYBZmi144jAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:58.184929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14783","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24774a387ce736efe76d065c9e8cd6dca7bc07e842af44399160120a47404523","sha256:8c6548b55de4be3154ff19c240fc8011c85825309f8510e6b6f59754b6870a53"],"state_sha256":"cbf9ed5096b1715808e8fa03bba79815bfcb7142432af7d1d7c948c7ed86defe"}