{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6UBCEMOPIFBMMOX7EED7IKVMJG","short_pith_number":"pith:6UBCEMOP","schema_version":"1.0","canonical_sha256":"f5022231cf4142c63aff2107f42aac49ad525321686728f4dd3ce4f59fd67e9b","source":{"kind":"arxiv","id":"2410.23090","version":1},"attestation_state":"computed","paper":{"title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guanting Dong, Hongjin Qian, Ji-Rong Wen, Kelong Mao, Tetsuya Sakai, Yiruo Cheng, Yongkang Wu, Zhicheng Dou, Ziliang Zhao","submitted_at":"2024-10-30T15:06:32Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introduce CORAL, a large-scale benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from W"},"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":"2410.23090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-30T15:06:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ef8ea8cae8efa221deac48a130d674e8d5e2da3569c7b5f32065c9830d130b17","abstract_canon_sha256":"504a23dbded2356f1ba26ec53fb6664a5b07fa58c94266def1003931bcf970d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:40.938972Z","signature_b64":"BGgEbkrAa3GWRPCGrkJRHnXg12k87G8P94SuYokGS3231+ZFl+bn/oA7uXxPN4bEy8rMVqM+tWGbVIddwQJ7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5022231cf4142c63aff2107f42aac49ad525321686728f4dd3ce4f59fd67e9b","last_reissued_at":"2026-07-05T09:28:40.938490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:40.938490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guanting Dong, Hongjin Qian, Ji-Rong Wen, Kelong Mao, Tetsuya Sakai, Yiruo Cheng, Yongkang Wu, Zhicheng Dou, Ziliang Zhao","submitted_at":"2024-10-30T15:06:32Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a powerful paradigm for enhancing large language models (LLMs) through external knowledge retrieval. Despite its widespread attention, existing academic research predominantly focuses on single-turn RAG, leaving a significant gap in addressing the complexities of multi-turn conversations found in real-world applications. To bridge this gap, we introduce CORAL, a large-scale benchmark designed to assess RAG systems in realistic multi-turn conversational settings. CORAL includes diverse information-seeking conversations automatically derived from W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23090","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/2410.23090/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":"2410.23090","created_at":"2026-07-05T09:28:40.938549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23090v1","created_at":"2026-07-05T09:28:40.938549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23090","created_at":"2026-07-05T09:28:40.938549+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UBCEMOPIFBM","created_at":"2026-07-05T09:28:40.938549+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UBCEMOPIFBMMOX7","created_at":"2026-07-05T09:28:40.938549+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UBCEMOP","created_at":"2026-07-05T09:28:40.938549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20729","citing_title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16310","citing_title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG","json":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG.json","graph_json":"https://pith.science/api/pith-number/6UBCEMOPIFBMMOX7EED7IKVMJG/graph.json","events_json":"https://pith.science/api/pith-number/6UBCEMOPIFBMMOX7EED7IKVMJG/events.json","paper":"https://pith.science/paper/6UBCEMOP"},"agent_actions":{"view_html":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG","download_json":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG.json","view_paper":"https://pith.science/paper/6UBCEMOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23090&json=true","fetch_graph":"https://pith.science/api/pith-number/6UBCEMOPIFBMMOX7EED7IKVMJG/graph.json","fetch_events":"https://pith.science/api/pith-number/6UBCEMOPIFBMMOX7EED7IKVMJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG/action/storage_attestation","attest_author":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG/action/author_attestation","sign_citation":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG/action/citation_signature","submit_replication":"https://pith.science/pith/6UBCEMOPIFBMMOX7EED7IKVMJG/action/replication_record"}},"created_at":"2026-07-05T09:28:40.938549+00:00","updated_at":"2026-07-05T09:28:40.938549+00:00"}