Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data

Source

arXiv

arxiv.org/abs/2608.06331v1

Read the source

Source

Plain-Language Brief

TYTAN is a system that automatically constructs an analytic semantic schema from a relational database, with user-provided descriptions when available. It uses symbolic analysis and LLM-based semantic inference for entity proposal, role assignment, and naming. If the evidence leaves a decision ambiguous, TYTAN asks targeted natural-language questions to the user.

What the Document Says

  • TYTAN is a system for automatically constructing an analytic semantic schema from a relational database.
  • The system combines symbolic analysis of the database with LLM-based semantic inference for entity proposal, role assignment, and naming.
  • When evidence leaves a decision ambiguous, TYTAN asks targeted natural-language questions to the user.
  • The evaluation was done on eight databases spanning real-world and benchmark domains.
  • Across seven reference domains, TYTAN reaches every entity, attribute, and aggregable feature of the expert-corrected reference schemas (100% coverage).
  • 100% of its retrieval instructions execute correctly (1,678 of 1,678 self-generated claims).
  • Semantic roles agree with the reference on 92-100% of matched attributes.
  • On a held-out blind test, TYTAN recovers the full entity structure with verified keys and satisfies 100% of the satisfiable expectations of five independent blind annotators.

Key Concepts Mentioned

  • TYTAN
  • analytic semantic schema
  • relational database
  • LLM-based semantic inference
  • natural-language question

Claims Made by the Document

  • TYTAN constructs an analytic semantic schema from a relational database.
  • The system achieves 100% coverage of entities, attributes, and aggregable features.
  • All retrieval instructions execute correctly.
  • Semantic roles agree with the reference on 92-100% of matched attributes.
  • TYTAN recovers the full entity structure and satisfies 100% of the satisfiable expectations in a blind test.

Evidence Used

  • The text explains that TYTAN is designed to construct an analytic semantic schema from a relational database, with evaluation results provided.
  • The evaluation results show that TYTAN achieves 100% coverage and correct retrieval of instructions, as well as high agreement in semantic roles.

Methods / Approach

  • Symbolic analysis
  • LLM-based semantic inference
  • Natural-language question asking

Limitations Stated by the Authors

The small disagreement between TYTAN's results and the reference schema is due to an error in the reference, not in TYTAN.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The text does not mention any limitations of TYTAN beyond those pointed out by the authors.

Open Questions

  • What kind of relational databases were used for evaluation?
  • What is the exact nature of the LLM used in semantic inference?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The text mentions eight databases, but does not specify their origin or characteristics.

Raw Abstract / Excerpt

From natural-language query interfaces to automated report generation, data analysis tools need a description of the data: the real-world entities it contains, which columns function as measures or identifiers, and how tables connect into units of analysis. Today, this semantic layer is usually written by hand. This is a knowledge-acquisition bottleneck that limits the scalability of analytic systems, keeps non-technical users dependent on experts, and is itself error-prone. We present TYTAN, a system for automatically constructing an analytic semantic schema from a relational database and, when available, a short user-provided description. TYTAN combines symbolic analysis of the database with LLM-based semantic inference for entity proposal, role assignment, and naming. When the evidence leaves a decision ambiguous, TYTAN asks the user a targeted natural-language question. We evaluate TYTAN on eight databases spanning real-world and benchmark domains along the three axes that define a schema's functional utility: (i) coverage, are all important entities and features captured?; (ii) retrieval correctness, do the schema's instructions actually reach the data; and (iii) characterization accuracy, are semantic types correct? Across the seven reference domains, TYTAN reaches every entity, attribute, and aggregable feature of the expert-corrected reference schemas (100% coverage). Additionally, 100% of its retrieval instructions execute correctly (1,678 of 1,678 self-generated claims), and semantic roles agree with the reference on 92-100% of matched attributes. Checking the underlying data showed the small disagreement is in the reference, not in TYTAN. On a held-out blind test (a live, ten-table database with no declared keys), TYTAN recovers the full entity structure with verified keys and satisfies 100% of the satisfiable expectations of five independent blind annotators.