{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:256UQHJUZAAHAOCTYWU72GS55W","short_pith_number":"pith:256UQHJU","schema_version":"1.0","canonical_sha256":"d77d481d34c800703853c5a9fd1a5ded9d0b0571066cc892dbc4319448302dea","source":{"kind":"arxiv","id":"2412.12612","version":2},"attestation_state":"computed","paper":{"title":"Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Tiwari, Masoud Hashemi, Sathwik Tejaswi Madhusudhan, Shiva Krishna Reddy Malay, Vikas Yadav","submitted_at":"2024-12-17T07:21:25Z","abstract_excerpt":"Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in modeling and querying relationships. While translating natural language into SQL queries is well-researched, generating Cypher queries for Neo4j remains relatively underexplored. In this work, we present an automated, LLM-Supervised, pipeline to generate high-quality synthetic data for Text2Cypher. Our Cypher data generation pipeline introduces LLM-As-Database-Filler, a novel strategy for ensuring Cypher query correctness, thus resulting in high quality generati"},"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":"2412.12612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T07:21:25Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"a70ecf0b8437c20f514941b5f4aa31731b840bc0bb85fc6e3e9089786cd0fcbd","abstract_canon_sha256":"598a333d6cf5b670cad74ec2e28cd52dbd30c997eb3924a09cdeb792f3dd7722"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:41.250932Z","signature_b64":"AA8higJLkl1Ar59bPipXdmKODRre2znzHUxWDhrL+4e2gckoVkSccXDpTj1nTot44p6nSisJk0Awo1N5jznmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d77d481d34c800703853c5a9fd1a5ded9d0b0571066cc892dbc4319448302dea","last_reissued_at":"2026-07-05T10:04:41.250513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:41.250513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Tiwari, Masoud Hashemi, Sathwik Tejaswi Madhusudhan, Shiva Krishna Reddy Malay, Vikas Yadav","submitted_at":"2024-12-17T07:21:25Z","abstract_excerpt":"Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in modeling and querying relationships. While translating natural language into SQL queries is well-researched, generating Cypher queries for Neo4j remains relatively underexplored. In this work, we present an automated, LLM-Supervised, pipeline to generate high-quality synthetic data for Text2Cypher. Our Cypher data generation pipeline introduces LLM-As-Database-Filler, a novel strategy for ensuring Cypher query correctness, thus resulting in high quality generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12612","kind":"arxiv","version":2},"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/2412.12612/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":"2412.12612","created_at":"2026-07-05T10:04:41.250567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12612v2","created_at":"2026-07-05T10:04:41.250567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12612","created_at":"2026-07-05T10:04:41.250567+00:00"},{"alias_kind":"pith_short_12","alias_value":"256UQHJUZAAH","created_at":"2026-07-05T10:04:41.250567+00:00"},{"alias_kind":"pith_short_16","alias_value":"256UQHJUZAAHAOCT","created_at":"2026-07-05T10:04:41.250567+00:00"},{"alias_kind":"pith_short_8","alias_value":"256UQHJU","created_at":"2026-07-05T10:04:41.250567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04645","citing_title":"CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27742","citing_title":"KG2Cypher: Data-Centric Pipeline for Building Enterprise Text-to-Cypher Systems","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W","json":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W.json","graph_json":"https://pith.science/api/pith-number/256UQHJUZAAHAOCTYWU72GS55W/graph.json","events_json":"https://pith.science/api/pith-number/256UQHJUZAAHAOCTYWU72GS55W/events.json","paper":"https://pith.science/paper/256UQHJU"},"agent_actions":{"view_html":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W","download_json":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W.json","view_paper":"https://pith.science/paper/256UQHJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12612&json=true","fetch_graph":"https://pith.science/api/pith-number/256UQHJUZAAHAOCTYWU72GS55W/graph.json","fetch_events":"https://pith.science/api/pith-number/256UQHJUZAAHAOCTYWU72GS55W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W/action/storage_attestation","attest_author":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W/action/author_attestation","sign_citation":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W/action/citation_signature","submit_replication":"https://pith.science/pith/256UQHJUZAAHAOCTYWU72GS55W/action/replication_record"}},"created_at":"2026-07-05T10:04:41.250567+00:00","updated_at":"2026-07-05T10:04:41.250567+00:00"}