{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HDV6G4VJXGAWFCU7IEMOTOPYIY","short_pith_number":"pith:HDV6G4VJ","schema_version":"1.0","canonical_sha256":"38ebe372a9b981628a9f4118e9b9f8462559129cf869595042df3a6b16409161","source":{"kind":"arxiv","id":"2504.14375","version":1},"attestation_state":"computed","paper":{"title":"Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arpit Sharma, Kun Qian, Maximillian Chen, Siyan Li, Zhou Yu","submitted_at":"2025-04-19T18:25:53Z","abstract_excerpt":"Training conversational question-answering (QA) systems requires a substantial amount of in-domain data, which is often scarce in practice. A common solution to this challenge is to generate synthetic data. Traditional methods typically follow a top-down approach, where a large language model (LLM) generates multi-turn dialogues from a broad prompt. Although this method produces coherent conversations, it offers limited fine-grained control over the content and is susceptible to hallucinations. We introduce a bottom-up conversation synthesis approach, where QA pairs are generated first and the"},"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":"2504.14375","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-19T18:25:53Z","cross_cats_sorted":[],"title_canon_sha256":"0ea93f937a2e8e57d1cecaf741bb747c7dcd79f06c9ae5e991761b9c02343833","abstract_canon_sha256":"6f4538b97d98f6b931e5bbebf42f2f45e167811fce46307efe9c25ba50797457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:42.427715Z","signature_b64":"V0zRMDje7a8QY6pRktY9LRCUf+n2MOpauRti/5P3QoU/g2gXYpKZVC78zq5H9Oqn0gH8/g0XX7pgRWbErVPNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ebe372a9b981628a9f4118e9b9f8462559129cf869595042df3a6b16409161","last_reissued_at":"2026-07-05T10:51:42.427195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:42.427195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arpit Sharma, Kun Qian, Maximillian Chen, Siyan Li, Zhou Yu","submitted_at":"2025-04-19T18:25:53Z","abstract_excerpt":"Training conversational question-answering (QA) systems requires a substantial amount of in-domain data, which is often scarce in practice. A common solution to this challenge is to generate synthetic data. Traditional methods typically follow a top-down approach, where a large language model (LLM) generates multi-turn dialogues from a broad prompt. Although this method produces coherent conversations, it offers limited fine-grained control over the content and is susceptible to hallucinations. We introduce a bottom-up conversation synthesis approach, where QA pairs are generated first and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14375","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/2504.14375/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":"2504.14375","created_at":"2026-07-05T10:51:42.427258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14375v1","created_at":"2026-07-05T10:51:42.427258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14375","created_at":"2026-07-05T10:51:42.427258+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDV6G4VJXGAW","created_at":"2026-07-05T10:51:42.427258+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDV6G4VJXGAWFCU7","created_at":"2026-07-05T10:51:42.427258+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDV6G4VJ","created_at":"2026-07-05T10:51:42.427258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY","json":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY.json","graph_json":"https://pith.science/api/pith-number/HDV6G4VJXGAWFCU7IEMOTOPYIY/graph.json","events_json":"https://pith.science/api/pith-number/HDV6G4VJXGAWFCU7IEMOTOPYIY/events.json","paper":"https://pith.science/paper/HDV6G4VJ"},"agent_actions":{"view_html":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY","download_json":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY.json","view_paper":"https://pith.science/paper/HDV6G4VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14375&json=true","fetch_graph":"https://pith.science/api/pith-number/HDV6G4VJXGAWFCU7IEMOTOPYIY/graph.json","fetch_events":"https://pith.science/api/pith-number/HDV6G4VJXGAWFCU7IEMOTOPYIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY/action/storage_attestation","attest_author":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY/action/author_attestation","sign_citation":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY/action/citation_signature","submit_replication":"https://pith.science/pith/HDV6G4VJXGAWFCU7IEMOTOPYIY/action/replication_record"}},"created_at":"2026-07-05T10:51:42.427258+00:00","updated_at":"2026-07-05T10:51:42.427258+00:00"}