@inproceedings{crossley-etal-2026-automated,
title = "Automated Approaches for Scoring Math Misunderstandings in Student Self-Explanations",
author = "Crossley, Scott and
Rittle-Johnson, Bethany and
Adler, Rebecca and
Burleigh, L and
King, Jules and
Benner, Meg",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting-Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Full 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-main.33/",
pages = "297--302",
ISBN = "979-8-9983004-0-0",
abstract = "This study reports on an open data science competition based on a benchmark dataset of mathematics misunderstandings, comprising over 52,000 mathematics explanations written to justify answer choices from 15 multiple-choice questions that were labeled by expert human annotators. Competitors were tasked with correctly classifying the explanations and any misunderstandings. By combining stable validation methods with efficient inference and enriched training data, top teams achieved high accuracy scores that correctly classified the explanations as correct, a misunderstanding, or neither and, if it did have a misunderstanding, what type of misunderstanding it was."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="crossley-etal-2026-automated">
<titleInfo>
<title>Automated Approaches for Scoring Math Misunderstandings in Student Self-Explanations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Crossley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bethany</namePart>
<namePart type="family">Rittle-Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Adler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">L</namePart>
<namePart type="family">Burleigh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jules</namePart>
<namePart type="family">King</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meg</namePart>
<namePart type="family">Benner</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): Full 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">979-8-9983004-0-0</identifier>
</relatedItem>
<abstract>This study reports on an open data science competition based on a benchmark dataset of mathematics misunderstandings, comprising over 52,000 mathematics explanations written to justify answer choices from 15 multiple-choice questions that were labeled by expert human annotators. Competitors were tasked with correctly classifying the explanations and any misunderstandings. By combining stable validation methods with efficient inference and enriched training data, top teams achieved high accuracy scores that correctly classified the explanations as correct, a misunderstanding, or neither and, if it did have a misunderstanding, what type of misunderstanding it was.</abstract>
<identifier type="citekey">crossley-etal-2026-automated</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-main.33/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>297</start>
<end>302</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Approaches for Scoring Math Misunderstandings in Student Self-Explanations
%A Crossley, Scott
%A Rittle-Johnson, Bethany
%A Adler, Rebecca
%A Burleigh, L.
%A King, Jules
%A Benner, Meg
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting-Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-0-0
%F crossley-etal-2026-automated
%X This study reports on an open data science competition based on a benchmark dataset of mathematics misunderstandings, comprising over 52,000 mathematics explanations written to justify answer choices from 15 multiple-choice questions that were labeled by expert human annotators. Competitors were tasked with correctly classifying the explanations and any misunderstandings. By combining stable validation methods with efficient inference and enriched training data, top teams achieved high accuracy scores that correctly classified the explanations as correct, a misunderstanding, or neither and, if it did have a misunderstanding, what type of misunderstanding it was.
%U https://aclanthology.org/2026.aimecon-main.33/
%P 297-302
Markdown (Informal)
[Automated Approaches for Scoring Math Misunderstandings in Student Self-Explanations](https://aclanthology.org/2026.aimecon-main.33/) (Crossley et al., AIME-Con 2026)
ACL
- Scott Crossley, Bethany Rittle-Johnson, Rebecca Adler, L Burleigh, Jules King, and Meg Benner. 2026. Automated Approaches for Scoring Math Misunderstandings in Student Self-Explanations. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 297–302, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).