@inproceedings{gaikwad-maddula-2026-blocker,
title = "The Blocker Beasts and How to Tame Them: Schema-Driven Extraction in the Connective {AI} Layer of Network Operation",
author = "Gaikwad, Madhava and
Maddula, Mohan",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.47/",
pages = "785--802",
ISBN = "979-8-89176-460-6",
abstract = "In the Microsoft Azure datacenter network, a technician repairs a link and an on-call engineer, on a different shift and a different continent, decides whether the repair holds. The only channel between them is the technician{'}s free-text note. When the note omits the measurements the engineer needs, the ticket stalls: the median blocked ticket took 7.0 days to resolve, of which roughly one hour was engineering work. The rest was waiting for an account of the work that the note did not carry.\par We treat the note as the object to be repaired. A pipeline in production for ten months parses each note at write time into two lightweight schemas, STAR and ECO, using deterministic rules for measurements and a language model for prose. It reaches 0.913 F1 against a 2{,}141-note gold standard, above a stronger frontier model working alone, and across a staggered rollout of 450+ datacenters the deployed package cuts time-to-repair by 3.4 days. Resolution time falls steeply in a completeness score, at a rate that holds across five physically unrelated failure types, which is what we would expect if the constraint were in the handoff rather than in the physical work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaikwad-maddula-2026-blocker">
<titleInfo>
<title>The Blocker Beasts and How to Tame Them: Schema-Driven Extraction in the Connective AI Layer of Network Operation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Madhava</namePart>
<namePart type="family">Gaikwad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohan</namePart>
<namePart type="family">Maddula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>In the Microsoft Azure datacenter network, a technician repairs a link and an on-call engineer, on a different shift and a different continent, decides whether the repair holds. The only channel between them is the technician’s free-text note. When the note omits the measurements the engineer needs, the ticket stalls: the median blocked ticket took 7.0 days to resolve, of which roughly one hour was engineering work. The rest was waiting for an account of the work that the note did not carry.\par We treat the note as the object to be repaired. A pipeline in production for ten months parses each note at write time into two lightweight schemas, STAR and ECO, using deterministic rules for measurements and a language model for prose. It reaches 0.913 F1 against a 2,141-note gold standard, above a stronger frontier model working alone, and across a staggered rollout of 450+ datacenters the deployed package cuts time-to-repair by 3.4 days. Resolution time falls steeply in a completeness score, at a rate that holds across five physically unrelated failure types, which is what we would expect if the constraint were in the handoff rather than in the physical work.</abstract>
<identifier type="citekey">gaikwad-maddula-2026-blocker</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.47/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>785</start>
<end>802</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Blocker Beasts and How to Tame Them: Schema-Driven Extraction in the Connective AI Layer of Network Operation
%A Gaikwad, Madhava
%A Maddula, Mohan
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F gaikwad-maddula-2026-blocker
%X In the Microsoft Azure datacenter network, a technician repairs a link and an on-call engineer, on a different shift and a different continent, decides whether the repair holds. The only channel between them is the technician’s free-text note. When the note omits the measurements the engineer needs, the ticket stalls: the median blocked ticket took 7.0 days to resolve, of which roughly one hour was engineering work. The rest was waiting for an account of the work that the note did not carry.\par We treat the note as the object to be repaired. A pipeline in production for ten months parses each note at write time into two lightweight schemas, STAR and ECO, using deterministic rules for measurements and a language model for prose. It reaches 0.913 F1 against a 2,141-note gold standard, above a stronger frontier model working alone, and across a staggered rollout of 450+ datacenters the deployed package cuts time-to-repair by 3.4 days. Resolution time falls steeply in a completeness score, at a rate that holds across five physically unrelated failure types, which is what we would expect if the constraint were in the handoff rather than in the physical work.
%U https://aclanthology.org/2026.emnlp-industry.47/
%P 785-802
Markdown (Informal)
[The Blocker Beasts and How to Tame Them: Schema-Driven Extraction in the Connective AI Layer of Network Operation](https://aclanthology.org/2026.emnlp-industry.47/) (Gaikwad & Maddula, EMNLP 2026)
ACL