# Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses

arXiv: https://arxiv.org/abs/2608.07946 · HTML: https://mlsanity.com/paper/2608.07946/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 32 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [SelectiveNet: A Deep Neural Network with an Integrated Reject Option](https://mlsanity.com/paper/1901.09192/) (2019)
- [SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning](https://mlsanity.com/paper/1711.04436/) (2017)
- [Sherlock: A Deep Learning Approach to Semantic Data Type Detection](https://mlsanity.com/paper/1905.10688/) (2019)
- [Reliable Text-to-SQL with Adaptive Abstention](https://mlsanity.com/paper/2501.10858/) (2025)
- [Calibrating LLMs for Text-to-SQL Parsing by Leveraging Sub-clause Frequencies](https://mlsanity.com/paper/2505.23804/) (2025)

## Built on by (most cited first, 1 of 1)

- [Memory as Infrastructure: Reliability Engineering for Persistent Agent Memory in Months-Long LLM-Assisted Development](https://mlsanity.com/paper/2609.05510/) (2026)

## Abstract (arXiv)

Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean. Production warehouses are the inverse: cryptic identifiers, partial or absent documentation. We address the problem they pose first: recovering what columns and values mean from the data itself. Rosetta places a language model inside a verification harness: a deterministic profiler extracts structural evidence (value fingerprints, a 26-pattern library, checksum verdicts), the model proposes semantics conditioned on that evidence, and every fact carries provenance and a confidence bounded by its evidence class. Against human documentation on 680 paired columns across eleven BIRD databases, identifiers destroyed, the harness delivers metadata that is 0.475 accurate on the 42% of columns it commits to, against 0.223 on 94% for the same model used directly. Restricted to the 283 columns where both arms speak, the harness writes no better prose than the model alone; the gain is selection: deterministic evidence governs whether the system speaks (coverage +0.257 [0.128, 0.378]), not how well. The deterministic layer is a competence detector, not a competence amplifier. A backbone swap bounds the claim: the prose finding reproduces, but prompt-requested abstention does not transfer; a code-enforced commit gate (predictions registered first; measured on a third backbone and held-out databases) makes no-evidence coverage 0.000 on every backbone. On a blind i2b2 clinical warehouse Rosetta decodes 95.5% of 134 real ICD-9 codes from values alone and abstains on all 44 NDC drug codes. The catalog supports calibrated abstention at query time: under full schema opacity a naive translator falls from 0.92 to 0.42 execution accuracy while our gate answers at 86% accuracy over 59% coverage. Negative results are reported plainly, including that our own authority ladder is not the mechanism behind the headline.