{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XL6JKUIWPGLO2JMWXNIBCDKN3P","short_pith_number":"pith:XL6JKUIW","schema_version":"1.0","canonical_sha256":"bafc9551167996ed2596bb50110d4ddbd18626f8abb621f6d49a1236f5eefd9f","source":{"kind":"arxiv","id":"2406.14783","version":2},"attestation_state":"computed","paper":{"title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Arthur C\\^amara, Jakub Zavrel, Zackary Rackauckas","submitted_at":"2024-06-20T23:20:34Z","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"},"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":"2406.14783","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-20T23:20:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2b7b2d2ab150e9e49e658b48d1cca2b7ae9c2932ef93cb5cb0e3d3ef2041022b","abstract_canon_sha256":"dcc2adcebd826a335f44328f2f694c3204a02cba088a73a3966da0b13827f879"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:58.184929Z","signature_b64":"hxpBOLF3pIXiP7etGLLaO7ajW4x3Emq4asYHicCt7omCV/ThquuEeosJ90ZQgvacTtvd3VYCzUsYBZmi144jAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bafc9551167996ed2596bb50110d4ddbd18626f8abb621f6d49a1236f5eefd9f","last_reissued_at":"2026-07-05T11:07:58.184231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:58.184231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Arthur C\\^amara, Jakub Zavrel, Zackary Rackauckas","submitted_at":"2024-06-20T23:20:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14783","kind":"arxiv","version":2},"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/2406.14783/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":"2406.14783","created_at":"2026-07-05T11:07:58.184297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14783v2","created_at":"2026-07-05T11:07:58.184297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14783","created_at":"2026-07-05T11:07:58.184297+00:00"},{"alias_kind":"pith_short_12","alias_value":"XL6JKUIWPGLO","created_at":"2026-07-05T11:07:58.184297+00:00"},{"alias_kind":"pith_short_16","alias_value":"XL6JKUIWPGLO2JMW","created_at":"2026-07-05T11:07:58.184297+00:00"},{"alias_kind":"pith_short_8","alias_value":"XL6JKUIW","created_at":"2026-07-05T11:07:58.184297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02988","citing_title":"Self-Optimizing Multi-Agent Systems for Deep Research","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18234","citing_title":"Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P","json":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P.json","graph_json":"https://pith.science/api/pith-number/XL6JKUIWPGLO2JMWXNIBCDKN3P/graph.json","events_json":"https://pith.science/api/pith-number/XL6JKUIWPGLO2JMWXNIBCDKN3P/events.json","paper":"https://pith.science/paper/XL6JKUIW"},"agent_actions":{"view_html":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P","download_json":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P.json","view_paper":"https://pith.science/paper/XL6JKUIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14783&json=true","fetch_graph":"https://pith.science/api/pith-number/XL6JKUIWPGLO2JMWXNIBCDKN3P/graph.json","fetch_events":"https://pith.science/api/pith-number/XL6JKUIWPGLO2JMWXNIBCDKN3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P/action/storage_attestation","attest_author":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P/action/author_attestation","sign_citation":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P/action/citation_signature","submit_replication":"https://pith.science/pith/XL6JKUIWPGLO2JMWXNIBCDKN3P/action/replication_record"}},"created_at":"2026-07-05T11:07:58.184297+00:00","updated_at":"2026-07-05T11:07:58.184297+00:00"}