@inproceedings{schussler-etal-2026-astronomical,
title = "From Astronomical Circulars to Auditable Follow-up Records: Schema-Constrained {LLM} Extraction with Human Verification",
author = {Sch{\"u}ssler, Fabian and
Bisero, Sofia and
Cellier, M. and
Cinosi, J. and
Ciric, A. and
Cornejo, Bernardo and
Jaroschewski, Ilja and
Alkan, Atilla Kaan and
Kiendrebeogo, R. Weizmann and
Saint-Paul, A.},
editor = "Accomazzi, Alberto and
Ghosal, Tirthankar and
Grezes, Felix and
Lockhart, Kelly and
Alkan, Atilla Kaan",
booktitle = "Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications",
month = nov,
year = "2026",
address = "Hengqin, Zhuhai, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wasp-1.3/",
pages = "17--22",
ISBN = "979-8-89176-456-9",
abstract = "GCN Circulars distribute crucial information on astronomical observations of transient phenomena, but their flexible prose mixes observations, limits, metadata, contacts, and interpretation. We present an auditable pipeline that converts these reports into event-linked, structured records. Regular expressions provide domain hints; a large language model returns strict schema-constrained JSON; deterministic stages normalize values and emit review flags. Seven domain reviewers assessed 231 outputs from 210 distinct Circulars, fully confirming 223 reports and marking eight partly correct. They confirmed 25,827 of 25,880 definite field decisions (99.80{\%}); errors concentrated in timing and facility attribution. Comparison with independent redshift datasets found semantic catalog disagreements but no values misread by our pipeline. Applied to the GCN Circular archive back to 2016, the pipeline has structured 26,811 reports into 68,393 observations, now served in real time by the Astro-COLIBRI platform. We release the extraction pipeline as an open-source package and the derived records as a continuously updated resource."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schussler-etal-2026-astronomical">
<titleInfo>
<title>From Astronomical Circulars to Auditable Follow-up Records: Schema-Constrained LLM Extraction with Human Verification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fabian</namePart>
<namePart type="family">Schüssler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="family">Bisero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="family">Cellier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="family">Cinosi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Ciric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bernardo</namePart>
<namePart type="family">Cornejo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilja</namePart>
<namePart type="family">Jaroschewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atilla</namePart>
<namePart type="given">Kaan</namePart>
<namePart type="family">Alkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">R</namePart>
<namePart type="given">Weizmann</namePart>
<namePart type="family">Kiendrebeogo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="family">Saint-Paul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Accomazzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Grezes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Lockhart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atilla</namePart>
<namePart type="given">Kaan</namePart>
<namePart type="family">Alkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, Zhuhai, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-456-9</identifier>
</relatedItem>
<abstract>GCN Circulars distribute crucial information on astronomical observations of transient phenomena, but their flexible prose mixes observations, limits, metadata, contacts, and interpretation. We present an auditable pipeline that converts these reports into event-linked, structured records. Regular expressions provide domain hints; a large language model returns strict schema-constrained JSON; deterministic stages normalize values and emit review flags. Seven domain reviewers assessed 231 outputs from 210 distinct Circulars, fully confirming 223 reports and marking eight partly correct. They confirmed 25,827 of 25,880 definite field decisions (99.80%); errors concentrated in timing and facility attribution. Comparison with independent redshift datasets found semantic catalog disagreements but no values misread by our pipeline. Applied to the GCN Circular archive back to 2016, the pipeline has structured 26,811 reports into 68,393 observations, now served in real time by the Astro-COLIBRI platform. We release the extraction pipeline as an open-source package and the derived records as a continuously updated resource.</abstract>
<identifier type="citekey">schussler-etal-2026-astronomical</identifier>
<location>
<url>https://aclanthology.org/2026.wasp-1.3/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>17</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Astronomical Circulars to Auditable Follow-up Records: Schema-Constrained LLM Extraction with Human Verification
%A Schüssler, Fabian
%A Bisero, Sofia
%A Cellier, M.
%A Cinosi, J.
%A Ciric, A.
%A Cornejo, Bernardo
%A Jaroschewski, Ilja
%A Alkan, Atilla Kaan
%A Kiendrebeogo, R. Weizmann
%A Saint-Paul, A.
%Y Accomazzi, Alberto
%Y Ghosal, Tirthankar
%Y Grezes, Felix
%Y Lockhart, Kelly
%Y Alkan, Atilla Kaan
%S Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, Zhuhai, China
%@ 979-8-89176-456-9
%F schussler-etal-2026-astronomical
%X GCN Circulars distribute crucial information on astronomical observations of transient phenomena, but their flexible prose mixes observations, limits, metadata, contacts, and interpretation. We present an auditable pipeline that converts these reports into event-linked, structured records. Regular expressions provide domain hints; a large language model returns strict schema-constrained JSON; deterministic stages normalize values and emit review flags. Seven domain reviewers assessed 231 outputs from 210 distinct Circulars, fully confirming 223 reports and marking eight partly correct. They confirmed 25,827 of 25,880 definite field decisions (99.80%); errors concentrated in timing and facility attribution. Comparison with independent redshift datasets found semantic catalog disagreements but no values misread by our pipeline. Applied to the GCN Circular archive back to 2016, the pipeline has structured 26,811 reports into 68,393 observations, now served in real time by the Astro-COLIBRI platform. We release the extraction pipeline as an open-source package and the derived records as a continuously updated resource.
%U https://aclanthology.org/2026.wasp-1.3/
%P 17-22
Markdown (Informal)
[From Astronomical Circulars to Auditable Follow-up Records: Schema-Constrained LLM Extraction with Human Verification](https://aclanthology.org/2026.wasp-1.3/) (Schüssler et al., WASP 2026)
ACL
- Fabian Schüssler, Sofia Bisero, M. Cellier, J. Cinosi, A. Ciric, Bernardo Cornejo, Ilja Jaroschewski, Atilla Kaan Alkan, R. Weizmann Kiendrebeogo, and A. Saint-Paul. 2026. From Astronomical Circulars to Auditable Follow-up Records: Schema-Constrained LLM Extraction with Human Verification. In Proceedings of the 4th Workshop on Artificial Intelligence for Scientific Publications, pages 17–22, Hengqin, Zhuhai, China. Association for Computational Linguistics.