{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UOYOVN5TTQMZSWHECXRXYTHIKN","short_pith_number":"pith:UOYOVN5T","schema_version":"1.0","canonical_sha256":"a3b0eab7b39c199958e415e37c4ce853554e49bf0c9a05a9fc9678d1c3593a9d","source":{"kind":"arxiv","id":"2606.27742","version":1},"attestation_state":"computed","paper":{"title":"KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyemin Lee, Junghyuk Seo, Minjun Choi, Sujin Mo, Yerin Kim, Youngjoong Ko","submitted_at":"2026-06-26T05:41:33Z","abstract_excerpt":"Enterprise Knowledge Graphs (KGs) are increasingly used for internal search, analytics, and question answering, but building natural-language interfaces for private enterprise graphs remains costly. We present KG2Cypher, a data-centric pipeline for building enterprise text-to-Cypher systems from existing KGs. KG2Cypher first constructs an executable Cypher query from observed graph facts and then uses LLMs to generate its associated natural-language question. The resulting Text-Cypher pairs are validated with an LLM judge and human validation, and are converted into candidate-aware SFT data. T"},"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":"2606.27742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-26T05:41:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93075f89f1012e91c26222b2c194263cbf08f0afb09d3ecad1da9b313317d3e8","abstract_canon_sha256":"e4c2840a5fa69cc1263aff0a8064277fd9fb283c5cb5a0165e915c98efa87ad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:47.189864Z","signature_b64":"Vf9n+FX6FWVtTmh2vBRyNJSqK4rFO7REbwEbojX32A0DiZvtDkOKKXgcOqkVJu+ZSCt4AqRTI2yvBW8F/U7PAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3b0eab7b39c199958e415e37c4ce853554e49bf0c9a05a9fc9678d1c3593a9d","last_reissued_at":"2026-06-29T01:14:47.189452Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:47.189452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyemin Lee, Junghyuk Seo, Minjun Choi, Sujin Mo, Yerin Kim, Youngjoong Ko","submitted_at":"2026-06-26T05:41:33Z","abstract_excerpt":"Enterprise Knowledge Graphs (KGs) are increasingly used for internal search, analytics, and question answering, but building natural-language interfaces for private enterprise graphs remains costly. We present KG2Cypher, a data-centric pipeline for building enterprise text-to-Cypher systems from existing KGs. KG2Cypher first constructs an executable Cypher query from observed graph facts and then uses LLMs to generate its associated natural-language question. The resulting Text-Cypher pairs are validated with an LLM judge and human validation, and are converted into candidate-aware SFT data. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27742","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/2606.27742/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":"2606.27742","created_at":"2026-06-29T01:14:47.189515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27742v1","created_at":"2026-06-29T01:14:47.189515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27742","created_at":"2026-06-29T01:14:47.189515+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOYOVN5TTQMZ","created_at":"2026-06-29T01:14:47.189515+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOYOVN5TTQMZSWHE","created_at":"2026-06-29T01:14:47.189515+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOYOVN5T","created_at":"2026-06-29T01:14:47.189515+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/UOYOVN5TTQMZSWHECXRXYTHIKN","json":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN.json","graph_json":"https://pith.science/api/pith-number/UOYOVN5TTQMZSWHECXRXYTHIKN/graph.json","events_json":"https://pith.science/api/pith-number/UOYOVN5TTQMZSWHECXRXYTHIKN/events.json","paper":"https://pith.science/paper/UOYOVN5T"},"agent_actions":{"view_html":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN","download_json":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN.json","view_paper":"https://pith.science/paper/UOYOVN5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27742&json=true","fetch_graph":"https://pith.science/api/pith-number/UOYOVN5TTQMZSWHECXRXYTHIKN/graph.json","fetch_events":"https://pith.science/api/pith-number/UOYOVN5TTQMZSWHECXRXYTHIKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN/action/storage_attestation","attest_author":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN/action/author_attestation","sign_citation":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN/action/citation_signature","submit_replication":"https://pith.science/pith/UOYOVN5TTQMZSWHECXRXYTHIKN/action/replication_record"}},"created_at":"2026-06-29T01:14:47.189515+00:00","updated_at":"2026-06-29T01:14:47.189515+00:00"}