mlsanityData to 14 Oct 2026

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

arXiv 2608.18836 ↗First posted 19 Aug 2026cs.AIcited by 0

Not on the map. Why?

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.

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

18 of 49 references.

References · 18

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  5. 2017Selective Classification for Deep Neural Networkscited by 852
  6. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  7. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  8. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 385
  9. 2024Debating with More Persuasive LLMs Leads to More Truthful Answerscited by 266
  10. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 63
  11. 2024Overcoming Common Flaws in the Evaluation of Selective Classification Systemscited by 37
  12. 2024Realizable H-Consistent and Bayes-Consistent Loss Functions for Learning to Defercited by 26
6 more
  1. 2024Amortized Bayesian Experimental Design for Decision-Makingcited by 21
  2. 2024Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?cited by 18
  3. 2024Verifiably Robust Conformal Predictioncited by 10
  4. 2024Physics-Informed Graph Neural Networks for Water Distribution Systemscited by 9
  5. 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Setscited by 9
  6. 2023Graph Neural Networks for Pressure Estimation in Water Distribution Systemscited by 8

Built on by

Not cited yet.