{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V44RUSNXR2Z3AFNQYRCN5ROF5W","short_pith_number":"pith:V44RUSNX","schema_version":"1.0","canonical_sha256":"af391a49b78eb3b015b0c444dec5c5ed94b10232c1b9edf9f18ee5f48c745b9a","source":{"kind":"arxiv","id":"2401.17461","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Dialogue Dataset Generation using LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bahadorreza Ofoghi, Diego Molla-Aliod, John Yearwood, Qingyang Li, Yelaman Abdullin","submitted_at":"2024-01-30T21:49:30Z","abstract_excerpt":"Linear programming (LP) problems are pervasive in real-life applications. However, despite their apparent simplicity, an untrained user may find it difficult to determine the linear model of their specific problem. We envisage the creation of a goal-oriented conversational agent that will engage in conversation with the user to elicit all information required so that a subsequent agent can generate the linear model. In this paper, we present an approach for the generation of sample dialogues that can be used to develop and train such a conversational agent. Using prompt engineering, we develop"},"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":"2401.17461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T21:49:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3b97dffc1e85b131dd3710937ae30eb55595958ba978f1b792a818f9bea9bf5f","abstract_canon_sha256":"56bc9b3211bd3909135d4a3116220a55057771727a958e3493b442165c48a27e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:37.157383Z","signature_b64":"wZ34dOiCaWC2WCoqOHrD0Renpe5/4SAAbng+IP57vpg3gy2ouEiRlqbITkxmxp5dyPI1WymKaPyGM3FCEFBGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af391a49b78eb3b015b0c444dec5c5ed94b10232c1b9edf9f18ee5f48c745b9a","last_reissued_at":"2026-07-05T07:39:37.156955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:37.156955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Dialogue Dataset Generation using LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bahadorreza Ofoghi, Diego Molla-Aliod, John Yearwood, Qingyang Li, Yelaman Abdullin","submitted_at":"2024-01-30T21:49:30Z","abstract_excerpt":"Linear programming (LP) problems are pervasive in real-life applications. However, despite their apparent simplicity, an untrained user may find it difficult to determine the linear model of their specific problem. We envisage the creation of a goal-oriented conversational agent that will engage in conversation with the user to elicit all information required so that a subsequent agent can generate the linear model. In this paper, we present an approach for the generation of sample dialogues that can be used to develop and train such a conversational agent. Using prompt engineering, we develop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17461","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/2401.17461/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":"2401.17461","created_at":"2026-07-05T07:39:37.157013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17461v1","created_at":"2026-07-05T07:39:37.157013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17461","created_at":"2026-07-05T07:39:37.157013+00:00"},{"alias_kind":"pith_short_12","alias_value":"V44RUSNXR2Z3","created_at":"2026-07-05T07:39:37.157013+00:00"},{"alias_kind":"pith_short_16","alias_value":"V44RUSNXR2Z3AFNQ","created_at":"2026-07-05T07:39:37.157013+00:00"},{"alias_kind":"pith_short_8","alias_value":"V44RUSNX","created_at":"2026-07-05T07:39:37.157013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01394","citing_title":"UniD$^3$: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18167","citing_title":"DiscussLLM: Teaching Large Language Models When to Speak","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W","json":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W.json","graph_json":"https://pith.science/api/pith-number/V44RUSNXR2Z3AFNQYRCN5ROF5W/graph.json","events_json":"https://pith.science/api/pith-number/V44RUSNXR2Z3AFNQYRCN5ROF5W/events.json","paper":"https://pith.science/paper/V44RUSNX"},"agent_actions":{"view_html":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W","download_json":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W.json","view_paper":"https://pith.science/paper/V44RUSNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17461&json=true","fetch_graph":"https://pith.science/api/pith-number/V44RUSNXR2Z3AFNQYRCN5ROF5W/graph.json","fetch_events":"https://pith.science/api/pith-number/V44RUSNXR2Z3AFNQYRCN5ROF5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W/action/storage_attestation","attest_author":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W/action/author_attestation","sign_citation":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W/action/citation_signature","submit_replication":"https://pith.science/pith/V44RUSNXR2Z3AFNQYRCN5ROF5W/action/replication_record"}},"created_at":"2026-07-05T07:39:37.157013+00:00","updated_at":"2026-07-05T07:39:37.157013+00:00"}