@inproceedings{battaner-moro-etal-2026-pressmint,
title = "{P}ress{M}int {Q}uick{C}heck: Operationalising Readiness Diagnostics for Interoperable Historical Newspaper Corpora",
author = "Battaner Moro, Elena and
Caballos Villar, Almudena and
Cuevas Ria{\~n}o, Mar{\'i}a and
Miguez Lamanuzzi, Marina and
Romero L{\'o}pez, Dolores",
editor = "Ogrodniczuk, Maciej and
Osenova, Petya and
Wissik, Tanja",
booktitle = "Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.pressmint-1.3/",
doi = "10.63317/2pgz3sxyv56b",
pages = "11--15",
abstract = "PressMint QuickCheck is a lightweight, reproducible readiness diagnostic for historical newspaper collections. Given a candidate dataset (ZIP export or IIIF manifests), it detects which components are present, identifies interoperability-critical metadata gaps, and applies lightweight OCR sanity checks. It produces three standardised artefacts: a human-readable readiness report, a minimal normalised manifest (CSV), and a tentative v1 scorecard (suitability{\_}score 0-4) for prioritisation across collections. The workflow is delivered as a Colab-first notebook (no installation required). A key design decision treats content{\_}language and metadata{\_}language declarations as first-class interoperability signals, reflecting the multilingual scope of PressMint and ParlaMint corpora projects."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="battaner-moro-etal-2026-pressmint">
<titleInfo>
<title>PressMint QuickCheck: Operationalising Readiness Diagnostics for Interoperable Historical Newspaper Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner Moro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Almudena</namePart>
<namePart type="family">Caballos Villar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">María</namePart>
<namePart type="family">Cuevas Riaño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Miguez Lamanuzzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dolores</namePart>
<namePart type="family">Romero López</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Wissik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>PressMint QuickCheck is a lightweight, reproducible readiness diagnostic for historical newspaper collections. Given a candidate dataset (ZIP export or IIIF manifests), it detects which components are present, identifies interoperability-critical metadata gaps, and applies lightweight OCR sanity checks. It produces three standardised artefacts: a human-readable readiness report, a minimal normalised manifest (CSV), and a tentative v1 scorecard (suitability_score 0-4) for prioritisation across collections. The workflow is delivered as a Colab-first notebook (no installation required). A key design decision treats content_language and metadata_language declarations as first-class interoperability signals, reflecting the multilingual scope of PressMint and ParlaMint corpora projects.</abstract>
<identifier type="citekey">battaner-moro-etal-2026-pressmint</identifier>
<identifier type="doi">10.63317/2pgz3sxyv56b</identifier>
<location>
<url>https://aclanthology.org/2026.pressmint-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PressMint QuickCheck: Operationalising Readiness Diagnostics for Interoperable Historical Newspaper Corpora
%A Battaner Moro, Elena
%A Caballos Villar, Almudena
%A Cuevas Riaño, María
%A Miguez Lamanuzzi, Marina
%A Romero López, Dolores
%Y Ogrodniczuk, Maciej
%Y Osenova, Petya
%Y Wissik, Tanja
%S Proceedings of the First Workshop on Creating Interoperable Corpora of Historical Newspapers
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma de Mallorca, Spain
%F battaner-moro-etal-2026-pressmint
%X PressMint QuickCheck is a lightweight, reproducible readiness diagnostic for historical newspaper collections. Given a candidate dataset (ZIP export or IIIF manifests), it detects which components are present, identifies interoperability-critical metadata gaps, and applies lightweight OCR sanity checks. It produces three standardised artefacts: a human-readable readiness report, a minimal normalised manifest (CSV), and a tentative v1 scorecard (suitability_score 0-4) for prioritisation across collections. The workflow is delivered as a Colab-first notebook (no installation required). A key design decision treats content_language and metadata_language declarations as first-class interoperability signals, reflecting the multilingual scope of PressMint and ParlaMint corpora projects.
%R 10.63317/2pgz3sxyv56b
%U https://aclanthology.org/2026.pressmint-1.3/
%U https://doi.org/10.63317/2pgz3sxyv56b
%P 11-15
Markdown (Informal)
[PressMint QuickCheck: Operationalising Readiness Diagnostics for Interoperable Historical Newspaper Corpora](https://aclanthology.org/2026.pressmint-1.3/) (Battaner Moro et al., PressMint 2026)
ACL