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

The paper presents Tytan, a system that automatically constructs an analytic semantic schema from relational databases to improve data analysis tools. The system combines symbolic analysis and LLM-based semantic inference for entity proposal, role assignment, and naming. It was evaluated on eight databases across real-world and benchmark domains, showing 100% coverage of all important entities, attributes, and features, as well as correct retrieval instructions and high accuracy in semantic roles.

What the Document Says

  • The paper presents TYTAN, a system for constructing an analytic semantic schema from relational databases with user-provided descriptions.
  • TYTAN combines symbolic analysis of the database with LLM-based semantic inference for entity proposal, role assignment, and naming.
  • When evidence is ambiguous, TYTAN asks a targeted natural-language question to the user.
  • The evaluation of TYTAN was conducted on eight databases across real-world and benchmark domains.
  • Across seven reference domains, TYTAN achieved 100% coverage of all important entities, attributes, and features.
  • All retrieval instructions executed correctly in the evaluation (1,678 out of 1,678 claims).
  • Semantic roles agreed with the reference on 92-100% of matched attributes.
  • The small disagreement in semantic roles was found to be in the reference, not in TYTAN.
  • On a held-out blind test, TYTAN recovered the full entity structure and satisfied 100% of the satisfiable expectations of five independent blind annotators.

Key Concepts Mentioned

  • TYTAN
  • analytic semantic schema
  • relational database
  • LLM-based semantic inference
  • entity proposal
  • role assignment
  • naming
  • evaluation
  • coverage
  • retrieval correctness
  • characterization accuracy

Claims Made by the Document

  • TYTAN constructs an analytic semantic schema from relational databases.
  • TYTAN combines symbolic analysis and LLM-based semantic inference.
  • When evidence is ambiguous, TYTAN asks a targeted natural-language question to the user.
  • TYTAN achieved 100% coverage of all important entities, attributes, and features.
  • All retrieval instructions executed correctly (1,678 out of 1,678 claims).
  • Semantic roles agreed with the reference on 92-100% of matched attributes.
  • The small disagreement in semantic roles was found to be in the reference, not in TYTAN.
  • On a held-out blind test, TYTAN recovered the full entity structure and satisfied 100% of the satisfiable expectations.

Evidence Used

  • The paper describes the functionality and evaluation of TYTAN.

Methods / Approach

  • symbolic analysis of databases
  • LLM-based semantic inference
  • natural-language questions to users

Limitations Stated by the Authors

The small disagreement in semantic roles was found in the reference, not in TYTAN.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The evaluation was conducted on a limited number of databases and may not generalize to all types of relational databases.

Open Questions

  • How does TYTAN handle complex relationships between entities?
  • What is the performance of TYTAN on large-scale databases?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • The paper does not discuss how TYTAN handles complex relationships between entities.
  • The paper does not mention the performance of TYTAN on large-scale databases.

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.