{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7K7YO3JQY6AUMNAUMTW5LY6ZKT","short_pith_number":"pith:7K7YO3JQ","schema_version":"1.0","canonical_sha256":"fabf876d30c78146341464edd5e3d954c02073c5b3cb841c2fb3f07e801b5516","source":{"kind":"arxiv","id":"2508.17693","version":2},"attestation_state":"computed","paper":{"title":"Database Normalization via Dual-LLM Self-Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Eunjae Jo, Gyuyeong Kim, Nakyung Lee","submitted_at":"2025-08-25T06:02:17Z","abstract_excerpt":"Database normalization is crucial to preserving data integrity. However, it is time-consuming and error-prone, as it is typically performed manually by data engineers. To this end, we present Miffie, a database normalization framework that leverages the capability of large language models. Miffie enables automated data normalization without human effort while preserving high accuracy. The core of Miffie is a dual-model self-refinement architecture that combines the best-performing models for normalized schema generation and verification, respectively. The generation module eliminates anomalies"},"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":"2508.17693","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-08-25T06:02:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"194805ba9f2b0398336796f20cbc6716e6f447018139c188391b49482aa905f0","abstract_canon_sha256":"838e414c03e54e1b33004599c51780af456f8f4d275a5beee75c7025d973e4ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:03:47.625050Z","signature_b64":"Hs1UImc6yOw+C7oDZYplgjLoJ9ZEc6P8Zqo6yIHdC4ltjz0gXrM2ynJybrnqvGUw0hOhypOT4kqmKzfooTORDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fabf876d30c78146341464edd5e3d954c02073c5b3cb841c2fb3f07e801b5516","last_reissued_at":"2026-06-08T01:03:47.623972Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:03:47.623972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Database Normalization via Dual-LLM Self-Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Eunjae Jo, Gyuyeong Kim, Nakyung Lee","submitted_at":"2025-08-25T06:02:17Z","abstract_excerpt":"Database normalization is crucial to preserving data integrity. However, it is time-consuming and error-prone, as it is typically performed manually by data engineers. To this end, we present Miffie, a database normalization framework that leverages the capability of large language models. Miffie enables automated data normalization without human effort while preserving high accuracy. The core of Miffie is a dual-model self-refinement architecture that combines the best-performing models for normalized schema generation and verification, respectively. The generation module eliminates anomalies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17693","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/2508.17693/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":"2508.17693","created_at":"2026-06-08T01:03:47.624197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17693v2","created_at":"2026-06-08T01:03:47.624197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17693","created_at":"2026-06-08T01:03:47.624197+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K7YO3JQY6AU","created_at":"2026-06-08T01:03:47.624197+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K7YO3JQY6AUMNAU","created_at":"2026-06-08T01:03:47.624197+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K7YO3JQ","created_at":"2026-06-08T01:03:47.624197+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/7K7YO3JQY6AUMNAUMTW5LY6ZKT","json":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT.json","graph_json":"https://pith.science/api/pith-number/7K7YO3JQY6AUMNAUMTW5LY6ZKT/graph.json","events_json":"https://pith.science/api/pith-number/7K7YO3JQY6AUMNAUMTW5LY6ZKT/events.json","paper":"https://pith.science/paper/7K7YO3JQ"},"agent_actions":{"view_html":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT","download_json":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT.json","view_paper":"https://pith.science/paper/7K7YO3JQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17693&json=true","fetch_graph":"https://pith.science/api/pith-number/7K7YO3JQY6AUMNAUMTW5LY6ZKT/graph.json","fetch_events":"https://pith.science/api/pith-number/7K7YO3JQY6AUMNAUMTW5LY6ZKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT/action/storage_attestation","attest_author":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT/action/author_attestation","sign_citation":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT/action/citation_signature","submit_replication":"https://pith.science/pith/7K7YO3JQY6AUMNAUMTW5LY6ZKT/action/replication_record"}},"created_at":"2026-06-08T01:03:47.624197+00:00","updated_at":"2026-06-08T01:03:47.624197+00:00"}