# Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks

arXiv: https://arxiv.org/abs/2608.18836 · HTML: https://mlsanity.com/paper/2608.18836/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Debating with More Persuasive LLMs Leads to More Truthful Answers](https://mlsanity.com/paper/2402.06782/) (2024)
- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [Overcoming Common Flaws in the Evaluation of Selective Classification Systems](https://mlsanity.com/paper/2407.01032/) (2024)
- [Realizable H-Consistent and Bayes-Consistent Loss Functions for Learning to Defer](https://mlsanity.com/paper/2407.13732/) (2024)
- [Amortized Bayesian Experimental Design for Decision-Making](https://mlsanity.com/paper/2411.02064/) (2024)
- [Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?](https://mlsanity.com/paper/2402.06160/) (2024)
- [Verifiably Robust Conformal Prediction](https://mlsanity.com/paper/2405.18942/) (2024)
- [Physics-Informed Graph Neural Networks for Water Distribution Systems](https://mlsanity.com/paper/2403.18570/) (2024)
- [Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets](https://mlsanity.com/paper/2406.06671/) (2024)
- [Graph Neural Networks for Pressure Estimation in Water Distribution Systems](https://mlsanity.com/paper/2311.10579/) (2023)

## Abstract (arXiv)

Leak localization is usually evaluated as forced-choice prediction, although sparse hydraulic observations may not justify excavation. Here, we quantify a pressure-information limit and use it to recast localization as selective, evidence-gated decision-making. A physics-grounded executor falsifies competing leak, demand, sensor and valve hypotheses in a hydraulic twin. Deterministic code computes every number and every acceptance predicate; an independent large language model auditor may add a rejection but never overturn a failed check. Forced retrieval placed only 95 of 300 leaks in the correct zone. Across 550 mixed events, the gate acted on 223 (214 correct); on a third-party 33-leak benchmark, all four accepted events were correct. In a replay of 194 audited City D repairs, the pressure tier authorized five excavation recommendations, three matching the repaired district, while the district-inflow tier returned the correct district for 85 events. Observability limits with machine-checkable abstention enable auditable utility intervention.