Metraipolis › archive › dc_ef9ff0a359da

Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses — arXiv:2608.07946

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.07946
License (as archived): CC0-1.0
Archived: 2026-10-19T09:14:22.388Z
SHA-256 of the archived text: 3d663dad29aef67362d55a5796b2167d31f5553e31ce52b8052354dd60c28301
Stable URL of this page: https://metraipolis.com/documento/dc_ef9ff0a359da

How to cite

Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses — arXiv:2608.07946 — arXiv (en), https://arxiv.org/abs/2608.07946 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef9ff0a359da (Metraipolis archive dc_ef9ff0a359da, sha256 3d663dad29aef67362d55a5796b2167d31f5553e31ce52b8052354dd60c28301)

BibTeX

@misc{dcef9ff0a359da,
  title = {Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses — arXiv:2608.07946},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07946},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef9ff0a359da; sha256 3d663dad29aef67362d55a5796b2167d31f5553e31ce52b8052354dd60c28301},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07946. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.DB).
Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.07946 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:12:27.034Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).