Temporal reasoning over evolving semi-structured tables poses a challenge to current QA systems. We propose a SQL-based approach that involves (1) generating a 3NF schema from Wikipedia infoboxes, (2) generating SQL queries, and (3) query execution. Our central finding challenges model scaling assumptions: the quality of schema design has a greater impact on QA precision than model capacity. We establish three evidence-based principles: normalization that preserves context, semantic naming that reduces ambiguity, and consistent temporal anchoring. Our best configuration (Gemini 2.5 Flash schema + Gemini-2.0-Flash queries) achieves 80.39 EM, a 16.8\% improvement over the baseline (68.89 EM).
@article{arxiv.2512.00329,
title = {Evidence-Guided Schema Normalization for Temporal Tabular Reasoning},
author = {Ashish Thanga and Vibhu Dixit and Abhilash Shankarampeta and Vivek Gupta},
journal= {arXiv preprint arXiv:2512.00329},
year = {2025}
}