<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marina-panchenko-2026-structural">
    <titleInfo>
        <title>Structural Signatures of Correct Mathematical Reasoning Traces</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Marina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Panchenko</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>The Proceedings of the 4th Workshop on Mathematical Natural Language Processing (MathNLP 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marco</namePart>
            <namePart type="family">Valentino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Deborah</namePart>
            <namePart type="family">Ferreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mokanarangan</namePart>
            <namePart type="family">Thayaparan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leonardo</namePart>
            <namePart type="family">Ranaldi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jo-Ku</namePart>
            <namePart type="family">Cheng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Freitas</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">979-8-89176-468-2</identifier>
    </relatedItem>
    <abstract>Self-consistency improves reasoning by voting over sampled final answers, but the vote discards how those answers were reached. We ask whether the internal organization of traces provides an interpretable signal that frequency misses. For each candidate answer, we cluster recurring intermediate statements into semantic checkpoints, retain checkpoint orders that are consistent across traces, and identify relations that appear both directly and with intermediate checkpoints inserted. These relations form answer-local shortcut graphs. Our score is the number of graph edges beyond a spanning tree in the most cross-linked component, normalized by answer frequency and smoothed over nearby sampling budgets. The intuition is deliberately structural: correct traces may agree on core dependencies while varying in local decomposition, whereas a wrong majority can arise from repeated copies of one failure route. On Math500 dataset, the structural selector is mostly neutral when evidence is scarce, but after sufficient sampling it frequently repairs majority errors, reaching up to 2% increase over majority vote scores.</abstract>
    <identifier type="citekey">marina-panchenko-2026-structural</identifier>
    <location>
        <url>https://aclanthology.org/2026.mathnlp-main.15/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>194</start>
            <end>200</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Structural Signatures of Correct Mathematical Reasoning Traces
%A Marina, Maria
%A Panchenko, Alexander
%Y Valentino, Marco
%Y Ferreira, Deborah
%Y Thayaparan, Mokanarangan
%Y Ranaldi, Leonardo
%Y Cheng, Jo-Ku
%Y Freitas, Andre
%S The Proceedings of the 4th Workshop on Mathematical Natural Language Processing (MathNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-468-2
%F marina-panchenko-2026-structural
%X Self-consistency improves reasoning by voting over sampled final answers, but the vote discards how those answers were reached. We ask whether the internal organization of traces provides an interpretable signal that frequency misses. For each candidate answer, we cluster recurring intermediate statements into semantic checkpoints, retain checkpoint orders that are consistent across traces, and identify relations that appear both directly and with intermediate checkpoints inserted. These relations form answer-local shortcut graphs. Our score is the number of graph edges beyond a spanning tree in the most cross-linked component, normalized by answer frequency and smoothed over nearby sampling budgets. The intuition is deliberately structural: correct traces may agree on core dependencies while varying in local decomposition, whereas a wrong majority can arise from repeated copies of one failure route. On Math500 dataset, the structural selector is mostly neutral when evidence is scarce, but after sufficient sampling it frequently repairs majority errors, reaching up to 2% increase over majority vote scores.
%U https://aclanthology.org/2026.mathnlp-main.15/
%P 194-200

Markdown (Informal)

[Structural Signatures of Correct Mathematical Reasoning Traces](https://aclanthology.org/2026.mathnlp-main.15/) (Marina & Panchenko, MathNLP 2026)

• Structural Signatures of Correct Mathematical Reasoning Traces (Marina & Panchenko, MathNLP 2026)

ACL

• Maria Marina and Alexander Panchenko. 2026. Structural Signatures of Correct Mathematical Reasoning Traces. In The Proceedings of the 4th Workshop on Mathematical Natural Language Processing (MathNLP 2026), pages 194–200, Budapest, Hungary. Association for Computational Linguistics.