@inproceedings{jeong-zhu-2026-answers,
title = "Same Answers, Different Active-Store States: An Identification Audit of {F}act{C}onsolidation Single-Hop",
author = "Jeong, Daeun and
Zhu, Yongjun",
editor = "Kamalloo, Ehsan and
Gontier, Nicolas and
Rozanov, Nikolai and
Hashemzadeh, Maryam and
Arora, Akhil",
booktitle = "Proceedings of the Second Workshop for {RE}search on Agent Language Models ({REALM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.realm-1.29/",
pages = "443--450",
ISBN = "979-8-89176-485-9",
abstract = "After a factual conflict, the same credited answer can arise from different record-choice rules and different active-store states. We audit this ambiguity in MemoryAgentBench{'}s 400-question FactConsolidation Single-Hop (FC-SH) task. A fixed exact-template parser identifies 282 questions with two target arrivals and distinct values, plus 118 singletons. In every two-arrival case, the larger serial also arrives last, so last-arrival and maximum-serial selection coincide. We cross these selectors with stores that expose either one active record or all versions. Given this alignment and the policy contracts, all four policies produce the same 400 prediction strings and receive 393/400, although the exact earlier fact ID is visible on 0/282 targets under one-record stores and 282/282 under all-version stores. Swapping the two arrivals while preserving their serials separates the selectors on all 282 targets. Under this primary parser, seven gold items are credited only to the earlier value; joining both candidates yields 400/400 under substring exact match. Thus, within this controlled grid, released FC-SH answers identify neither record choice nor active-store visibility. This release-level measurement audit pairs an order contrast for choice with direct store observation for visibility."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jeong-zhu-2026-answers">
<titleInfo>
<title>Same Answers, Different Active-Store States: An Identification Audit of FactConsolidation Single-Hop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daeun</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjun</namePart>
<namePart type="family">Zhu</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Kamalloo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Gontier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Rozanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Hashemzadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akhil</namePart>
<namePart type="family">Arora</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">979-8-89176-485-9</identifier>
</relatedItem>
<abstract>After a factual conflict, the same credited answer can arise from different record-choice rules and different active-store states. We audit this ambiguity in MemoryAgentBench’s 400-question FactConsolidation Single-Hop (FC-SH) task. A fixed exact-template parser identifies 282 questions with two target arrivals and distinct values, plus 118 singletons. In every two-arrival case, the larger serial also arrives last, so last-arrival and maximum-serial selection coincide. We cross these selectors with stores that expose either one active record or all versions. Given this alignment and the policy contracts, all four policies produce the same 400 prediction strings and receive 393/400, although the exact earlier fact ID is visible on 0/282 targets under one-record stores and 282/282 under all-version stores. Swapping the two arrivals while preserving their serials separates the selectors on all 282 targets. Under this primary parser, seven gold items are credited only to the earlier value; joining both candidates yields 400/400 under substring exact match. Thus, within this controlled grid, released FC-SH answers identify neither record choice nor active-store visibility. This release-level measurement audit pairs an order contrast for choice with direct store observation for visibility.</abstract>
<identifier type="citekey">jeong-zhu-2026-answers</identifier>
<location>
<url>https://aclanthology.org/2026.realm-1.29/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>443</start>
<end>450</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Same Answers, Different Active-Store States: An Identification Audit of FactConsolidation Single-Hop
%A Jeong, Daeun
%A Zhu, Yongjun
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F jeong-zhu-2026-answers
%X After a factual conflict, the same credited answer can arise from different record-choice rules and different active-store states. We audit this ambiguity in MemoryAgentBench’s 400-question FactConsolidation Single-Hop (FC-SH) task. A fixed exact-template parser identifies 282 questions with two target arrivals and distinct values, plus 118 singletons. In every two-arrival case, the larger serial also arrives last, so last-arrival and maximum-serial selection coincide. We cross these selectors with stores that expose either one active record or all versions. Given this alignment and the policy contracts, all four policies produce the same 400 prediction strings and receive 393/400, although the exact earlier fact ID is visible on 0/282 targets under one-record stores and 282/282 under all-version stores. Swapping the two arrivals while preserving their serials separates the selectors on all 282 targets. Under this primary parser, seven gold items are credited only to the earlier value; joining both candidates yields 400/400 under substring exact match. Thus, within this controlled grid, released FC-SH answers identify neither record choice nor active-store visibility. This release-level measurement audit pairs an order contrast for choice with direct store observation for visibility.
%U https://aclanthology.org/2026.realm-1.29/
%P 443-450
Markdown (Informal)
[Same Answers, Different Active-Store States: An Identification Audit of FactConsolidation Single-Hop](https://aclanthology.org/2026.realm-1.29/) (Jeong & Zhu, REALM 2026)
ACL