<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T00:56:09Z</responseDate><request verb="GetRecord" identifier="oai:digital.lib.washington.edu:1773/57748" metadataPrefix="dim">https://digital.lib.washington.edu/server/oai/request</request><GetRecord><record><header><identifier>oai:digital.lib.washington.edu:1773/57748</identifier><datestamp>2026-09-17T10:05:35Z</datestamp><setSpec>com_1773_4888</setSpec><setSpec>col_1773_4909</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Suciu, Dan</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Kayali, Moe</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-09-16T18:24:53Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026-09-16</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2026</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="other">Kayali_washington_0250E_30182.pdf</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/1773/57748</dim:field>
   <dim:field mdschema="dc" element="description">Thesis (Ph.D.)--University of Washington, 2026</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Semantic heterogeneity—the fact that the same real-world concept is represented differently across databases—is the principal obstacle to integrating, querying, and analyzing data across organizational boundaries. Its cost is concrete: analysts spend 40% of their working hours loading and cleaning data, and 60–70% of enterprise data is never used for analytics. The difficulty scales with the schema: enterprise systems routinely expose more than 10^5 attributes under opaque, proprietary vocabularies that no analyst—and no publicly trained model—can resolve by lookup. This dissertation asks how foundation models change the treatment of semantic heterogeneity: which data-management tasks they help solve, and how they compare against four decades of schema-matching and data-integration techniques. It answers through three systems, each closing a distinct gap. CHORUS brings foundation models to data discovery, unifying table-class detection, column-type annotation, and join-column prediction in a single prompt-based architecture with an anchoring mitigation against hallucination; it matches or exceeds task-specific deep models trained on 10^5-10^6 labelled examples, reaching 0.93, 0.89, and 0.90 F1 on the three tasks with no per-task training. Goby confronts the enterprise gap that public benchmarks conceal: it releases the first data-integration benchmark drawn from real, semi-private enterprise data, quantifies the performance drop that both LLM- and ML-based methods suffer on it, and closes that drop by learning a working ontology from data samples and serializing its full hierarchy into the model. Query Blueprints attacks the entanglement of structure and vocabulary in natural-language-to-query translation: by letting the user specify query structure exactly and grounding only the unknown vocabulary in data, it answers queries over opaque schemas where end-to-end LLM agents collapse—34% accuracy versus under 10% for four state-of-the-art agents on a scrambled-schema benchmark, at $0.40 versus $13.03 in cost. Together the three systems trace the contemporary heterogeneity stack: foundation models can replace task-specific training on public schemas, but enterprise data demands that structure be factored from vocabulary, and that vocabulary be grounded in data rather than recalled from training.</dim:field>
   <dim:field mdschema="dc" element="format" qualifier="mimetype">application/pdf</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en_US</dim:field>
   <dim:field mdschema="dc" element="rights">none</dim:field>
   <dim:field mdschema="dc" element="subject">Computer science</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="other">Computer science and engineering</dim:field>
   <dim:field mdschema="dc" element="title">Semantic Heterogeneity in the Age of Foundation Models: Benchmarks and Systems for Opaque Enterprise Schemas</dim:field>
   <dim:field mdschema="dc" element="type">Thesis</dim:field>
   <dim:field mdschema="dc" element="embargo" qualifier="terms">Open Access</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>