{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C2FAEWAENPZS6FAGSDAYIL3FCV","short_pith_number":"pith:C2FAEWAE","schema_version":"1.0","canonical_sha256":"168a0258046bf32f140690c1842f651544db44abe5ee1e959cdf7511d24d72c8","source":{"kind":"arxiv","id":"2409.11500","version":1},"attestation_state":"computed","paper":{"title":"Multi-Document Grounded Multi-Turn Synthetic Dialog Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chulaka Gunasekara, Danish Contractor, Radu Florian, Ram\\'on Fernandez Astudillo, Young-Suk Lee","submitted_at":"2024-09-17T19:02:39Z","abstract_excerpt":"We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with Chain-of-Thought (CoT) prompting. Second, we support the generation of multi-document grounded dialogs by mimicking real-world use of retrievers to update the grounding documents after every user-turn in the dialog. Third, we apply LLM-as-a-Judge to filter out queries with incorrect answers. Human evaluation of the synthetic dialog data suggests that the data is divers"},"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":"2409.11500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T19:02:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a154b074347478e7a91b27f6405470593bb01f891162ecc8442ea56c43c74d6","abstract_canon_sha256":"ef5f474d38e7c22f8426439e92d2d16671a40881cb90e9008cab113317b5a689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:32.509464Z","signature_b64":"Gmttl+7ANKBqNqTKRXyW+66RFLl9Fcj1RZUECRpH3VxOIE3tEOs4Uw93UeoOk9du7UbJekXb0chB35l6OIA2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"168a0258046bf32f140690c1842f651544db44abe5ee1e959cdf7511d24d72c8","last_reissued_at":"2026-07-05T09:08:32.508873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:32.508873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Document Grounded Multi-Turn Synthetic Dialog Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chulaka Gunasekara, Danish Contractor, Radu Florian, Ram\\'on Fernandez Astudillo, Young-Suk Lee","submitted_at":"2024-09-17T19:02:39Z","abstract_excerpt":"We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with Chain-of-Thought (CoT) prompting. Second, we support the generation of multi-document grounded dialogs by mimicking real-world use of retrievers to update the grounding documents after every user-turn in the dialog. Third, we apply LLM-as-a-Judge to filter out queries with incorrect answers. Human evaluation of the synthetic dialog data suggests that the data is divers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11500","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/2409.11500/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":"2409.11500","created_at":"2026-07-05T09:08:32.508969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11500v1","created_at":"2026-07-05T09:08:32.508969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11500","created_at":"2026-07-05T09:08:32.508969+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2FAEWAENPZS","created_at":"2026-07-05T09:08:32.508969+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2FAEWAENPZS6FAG","created_at":"2026-07-05T09:08:32.508969+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2FAEWAE","created_at":"2026-07-05T09:08:32.508969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29523","citing_title":"K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20729","citing_title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","ref_index":3,"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":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV","json":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV.json","graph_json":"https://pith.science/api/pith-number/C2FAEWAENPZS6FAGSDAYIL3FCV/graph.json","events_json":"https://pith.science/api/pith-number/C2FAEWAENPZS6FAGSDAYIL3FCV/events.json","paper":"https://pith.science/paper/C2FAEWAE"},"agent_actions":{"view_html":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV","download_json":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV.json","view_paper":"https://pith.science/paper/C2FAEWAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11500&json=true","fetch_graph":"https://pith.science/api/pith-number/C2FAEWAENPZS6FAGSDAYIL3FCV/graph.json","fetch_events":"https://pith.science/api/pith-number/C2FAEWAENPZS6FAGSDAYIL3FCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV/action/storage_attestation","attest_author":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV/action/author_attestation","sign_citation":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV/action/citation_signature","submit_replication":"https://pith.science/pith/C2FAEWAENPZS6FAGSDAYIL3FCV/action/replication_record"}},"created_at":"2026-07-05T09:08:32.508969+00:00","updated_at":"2026-07-05T09:08:32.508969+00:00"}