{
  "abstract": "Domain-specific text-to-SQL systems ground a large language model by retrieving annotated few-shot examples, and each example needs expert-written SQL. We treat the choice of which queries to annotate as constrained experimental design on the low-dimensional manifold of query embeddings, with query-dependent annotation noise, a partition matroid constraint that spreads selections across semantic domains, and an unknown covariance structure. We propose a stratified greedy algorithm that maximizes a heteroscedastic information-gain objective. We prove that the objective is monotone and submodular under query-dependent noise, so stratified greedy selection carries a 1/2-approximation guarantee under the partition constraint. Under kernel misspecification the guarantee degrades by an additive spectral term; we compute it on both experimental pools and find it too large for the bound to be quantitatively informative. To connect the design objective to the downstream task, we give a retrieval model that bounds few-shot accuracy from below by per-domain fill distance, demonstration noise, and domain coverage, and we calibrate its locality assumption on both pools. On an enterprise supply-chain corpus and on the BIRD benchmark, the selected banks improve cross-domain retrieval and end-to-end LLM SQL over random and distance-based selection at the same annotation budget. Stratified controls and pre-specified tests show that the gain comes from the partition constraint: uniform sampling within each stratum matches the full method in the oracle-label evaluations, farthest-point selection within strata adds a little at small budgets, and the noise weighting has no measurable effect. The practical advice is to annotate one example per domain per batch from the first batch on.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.10125",
  "author_total": 1,
  "authors": [
    {
      "name": "Arash Pourhabib"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9b940hg2em0sy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.10125",
  "fulltext_url": null,
  "id": "9b940hg2em0sy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.10125",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.DB"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "stat.ML"
    ],
    [
      "openalex",
      "1702|Machine Learning and Algorithms"
    ]
  ],
  "openalex": "W7164137353",
  "pdf_url": "https://arxiv.org/pdf/2606.10125",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/9b940hg2em0sy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:26Z",
      "native_id": "2606.10125",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.10125"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ML",
      "subfield": "statistics"
    }
  ],
  "title": "Robust Active Learning for Few-Shot Example Selection in Text-to-SQL",
  "title_text": "Robust Active Learning for Few-Shot Example Selection in Text-to-SQL",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:26Z",
  "url": "https://research.draconitic.com/paper/9b940hg2em0sy",
  "venue": "arXiv",
  "versions": []
}