@inproceedings{odonncha-etal-2026-evidence,
title = "Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data",
author = "O{'}Donncha, Fearghal and
Zhou, Nianjun and
Martinez, Natalia and
Rayfield, James T and
Heath III, Fenno F. and
Langbridge, Abigail and
Vaculin, Roman",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.50/",
pages = "736--748",
ISBN = "979-8-89176-394-4",
abstract = "Industrial maintenance platforms contain rich but fragmented evidence, including free-text work orders, heterogeneous operational sensors or indicators, and structured failure knowledge. These sources are often analyzed in isolation, producing alerts or forecasts that do not support conditional decision-making: given this asset history and behavior, what is happening and what action is warranted?We present Condition Insight Agent, a deployed decision-support framework that integrates maintenance language, behavioral abstractions of operational data, and engineering failure semantics to produce evidence-grounded explanations and advisory actions. The system constrains reasoning through deterministic evidence construction and structured failure knowledge, and applies a rule-based verification loop to suppress unsupported conclusions.Case studies from production CMMS deployments show that this verification-first design operates reliably under heterogeneous and incomplete data while preserving human oversight. Our results demonstrate how constrained LLM-based reasoning can function as a governed decision-support layer for industrial maintenance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="odonncha-etal-2026-evidence">
<titleInfo>
<title>Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fearghal</namePart>
<namePart type="family">O’Donncha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianjun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Rayfield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fenno</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Heath III</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abigail</namePart>
<namePart type="family">Langbridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Vaculin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Industrial maintenance platforms contain rich but fragmented evidence, including free-text work orders, heterogeneous operational sensors or indicators, and structured failure knowledge. These sources are often analyzed in isolation, producing alerts or forecasts that do not support conditional decision-making: given this asset history and behavior, what is happening and what action is warranted?We present Condition Insight Agent, a deployed decision-support framework that integrates maintenance language, behavioral abstractions of operational data, and engineering failure semantics to produce evidence-grounded explanations and advisory actions. The system constrains reasoning through deterministic evidence construction and structured failure knowledge, and applies a rule-based verification loop to suppress unsupported conclusions.Case studies from production CMMS deployments show that this verification-first design operates reliably under heterogeneous and incomplete data while preserving human oversight. Our results demonstrate how constrained LLM-based reasoning can function as a governed decision-support layer for industrial maintenance.</abstract>
<identifier type="citekey">odonncha-etal-2026-evidence</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.50/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>736</start>
<end>748</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data
%A O’Donncha, Fearghal
%A Zhou, Nianjun
%A Martinez, Natalia
%A Rayfield, James T.
%A Heath III, Fenno F.
%A Langbridge, Abigail
%A Vaculin, Roman
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F odonncha-etal-2026-evidence
%X Industrial maintenance platforms contain rich but fragmented evidence, including free-text work orders, heterogeneous operational sensors or indicators, and structured failure knowledge. These sources are often analyzed in isolation, producing alerts or forecasts that do not support conditional decision-making: given this asset history and behavior, what is happening and what action is warranted?We present Condition Insight Agent, a deployed decision-support framework that integrates maintenance language, behavioral abstractions of operational data, and engineering failure semantics to produce evidence-grounded explanations and advisory actions. The system constrains reasoning through deterministic evidence construction and structured failure knowledge, and applies a rule-based verification loop to suppress unsupported conclusions.Case studies from production CMMS deployments show that this verification-first design operates reliably under heterogeneous and incomplete data while preserving human oversight. Our results demonstrate how constrained LLM-based reasoning can function as a governed decision-support layer for industrial maintenance.
%U https://aclanthology.org/2026.acl-industry.50/
%P 736-748
Markdown (Informal)
[Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data](https://aclanthology.org/2026.acl-industry.50/) (O’Donncha et al., ACL 2026)
ACL
- Fearghal O’Donncha, Nianjun Zhou, Natalia Martinez, James T Rayfield, Fenno F. Heath III, Abigail Langbridge, and Roman Vaculin. 2026. Evidence-Driven Reasoning for Industrial Maintenance Using Heterogeneous Data. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 736–748, San Diego, California, USA. Association for Computational Linguistics.