Does a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory Study on BIRD and a Pre-registered Confirmation on Spider

arXiv:2610.17256 · cs.AI · Submitted 2026-10-12 · Read on arXiv

cs.AI

Submitted: 2026-10-12

Updated: 2026-10-12

Comments: 23 pages, 4 figures, 9 tables. Code, frozen scorer, pre-registration and data: https://github.com/numberz-ai/numberz-ies-tdd-h-calibration

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Text-to-SQL — 1× in this paper · explained in 3 episodes

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems