用可验证的拒绝机制，让AI漏水诊断更可信且可审计。
Verifiable abstention makes AI leak diagnosis accountable in urban water distribution networks
- 将漏水定位转为带证据门槛的选择性决策，避免无依据开挖。
- 在550次混合事件中，223次触发判断，其中214次正确；第三方测试全部通过。
- 适用于城市供水系统运维，提升诊断结果的可解释性和问责性。
漏水定位通常以强制选择方式评估，但稀疏的水力观测数据可能不足以支持开挖。本文量化了压力信息的极限，并将其用于将定位重构为选择性、证据驱动的决策过程。一个基于物理的执行器在水力孪生模型中验证漏水、需求、传感器和阀门等假设。确定性代码计算每项数值与接受条件；独立的大语言模型审计员可提出拒绝，但无法推翻已失败的检查。强制检索仅将300个漏水中的95个定位到正确区域。在550次混合事件中，系统触发223次判断，其中214次正确；在第三方33个漏水基准测试中，所有4个被接受事件均正确。对194次已审计的城市D修复事件回放显示，压力层级授权了5次开挖建议，其中3次匹配实际修复区；而区流量层级则在85次事件中返回了正确区域。可观测性边界结合机器可验证的拒绝机制，实现了可审计的实用干预。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。