@inproceedings{gui-2026-beyond,
title = "Beyond Clean Agreement: A Stability-Bounded Evaluation of Compact {AES} Distillation",
author = "Gui, Yi",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting-Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Coordinated Session Papers",
month = oct,
year = "2026",
address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2026.aimecon-sessions.5/",
pages = "39--48",
ISBN = "979-8-9983004-2-4",
abstract = "Compact distillation preserved clean essay-scoring agreement across three student models and six compressed teacher targets, but the best target differed by model and margins were small. Perturbation, distribution-shift, and subgroup-bootstrap analyses dominated those differences, indicating that resource-constrained educational scoring requires uncertainty-aware evaluation rather than clean held-out comparison alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gui-2026-beyond">
<titleInfo>
<title>Beyond Clean Agreement: A Stability-Bounded Evaluation of Compact AES Distillation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Gui</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 Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ormerod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalen</namePart>
<namePart type="family">Beiting-Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>National Council on Measurement in Education (NCME)</publisher>
<place>
<placeTerm type="text">Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-9983004-2-4</identifier>
</relatedItem>
<abstract>Compact distillation preserved clean essay-scoring agreement across three student models and six compressed teacher targets, but the best target differed by model and margins were small. Perturbation, distribution-shift, and subgroup-bootstrap analyses dominated those differences, indicating that resource-constrained educational scoring requires uncertainty-aware evaluation rather than clean held-out comparison alone.</abstract>
<identifier type="citekey">gui-2026-beyond</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-sessions.5/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>39</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Clean Agreement: A Stability-Bounded Evaluation of Compact AES Distillation
%A Gui, Yi
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-2-4
%F gui-2026-beyond
%X Compact distillation preserved clean essay-scoring agreement across three student models and six compressed teacher targets, but the best target differed by model and margins were small. Perturbation, distribution-shift, and subgroup-bootstrap analyses dominated those differences, indicating that resource-constrained educational scoring requires uncertainty-aware evaluation rather than clean held-out comparison alone.
%U https://aclanthology.org/2026.aimecon-sessions.5/
%P 39-48
Markdown (Informal)
[Beyond Clean Agreement: A Stability-Bounded Evaluation of Compact AES Distillation](https://aclanthology.org/2026.aimecon-sessions.5/) (Gui, AIME-Con 2026)
ACL