{"ID":3084673,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-06T20:20:29.47808685Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05415","arxiv_id":"2606.05415","title":"Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval","abstract":"Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identity keys, foreign keys, and source hierarchy; and the resulting schema drives extraction, deduplication, and cross-source linking into a provenance-aware knowledge graph. At query time the schema -- optionally extended via a monotonic protocol -- conditions a multi-tool agent routing retrieval across structured lookup, graph traversal, and vector search, returning grounded answers with traceable citations. In controlled zero-shot comparisons using the same LLM, data, and evaluation harness, the system improves over retrieval-only and decomposition-based baselines across four QA benchmarks, with ablations showing that schema-conditioned routing, structural intelligence, and schema-guided construction each contribute to the gains.","short_abstract":"Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically disco...","url_abs":"https://arxiv.org/abs/2606.05415","url_pdf":"https://arxiv.org/pdf/2606.05415v1","authors":"[\"Padmaja Jonnalagedda\",\"Yuguang Yao\",\"Xiang Gao\",\"Hilaf Hasson\",\"Kamalika Das\"]","published":"2026-06-03T20:28:36Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}