@inproceedings{kumar-etal-2026-bridging,
title = "Bridging the Data Bottleneck: A Multi-Modal Generative Extraction Pipeline for Legacy Scientific Literature",
author = "Kumar, Gaurav and
Bari, Anasse and
Nagel, David J.",
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-1.10/",
pages = "91--98",
ISBN = "979-8-89176-456-9",
abstract = "The majority of historical experimental data across the empirical sciences remains locked in unstructured legacy formats, which slows data-driven discovery. We introduce an automated multi-modal pipeline that processes large literature corpora, filters non-empirical noise, and outputs structured datasets. Layout-aware document parsing is paired with a lightweight semantic triage gatekeeper to substantially reduce the computational overhead of applying frontier multi-modal models at scale. A generative model reconstructs experimental trajectories from text and figures, while a schema-constrained prompt and a strictly typed programmatic validation layer check physical bounds before serialization. We evaluate the pipeline on a 60-document corpus of extreme-condition thermodynamic literature drawn from Low Energy Nuclear Reactions (LENR) research, reporting concrete throughput, triage, and constraint-violation statistics. We distinguish safeguards enforced in code (physical-bound validators) from those requested through the prompt, such as source grounding, and outline the evaluation needed to verify the latter. The architecture is domain-agnostic by design, and we outline how it could transfer to catalysis, energy storage, and preclinical biomedical research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2026-bridging">
<titleInfo>
<title>Bridging the Data Bottleneck: A Multi-Modal Generative Extraction Pipeline for Legacy Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anasse</namePart>
<namePart type="family">Bari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Nagel</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>The majority of historical experimental data across the empirical sciences remains locked in unstructured legacy formats, which slows data-driven discovery. We introduce an automated multi-modal pipeline that processes large literature corpora, filters non-empirical noise, and outputs structured datasets. Layout-aware document parsing is paired with a lightweight semantic triage gatekeeper to substantially reduce the computational overhead of applying frontier multi-modal models at scale. A generative model reconstructs experimental trajectories from text and figures, while a schema-constrained prompt and a strictly typed programmatic validation layer check physical bounds before serialization. We evaluate the pipeline on a 60-document corpus of extreme-condition thermodynamic literature drawn from Low Energy Nuclear Reactions (LENR) research, reporting concrete throughput, triage, and constraint-violation statistics. We distinguish safeguards enforced in code (physical-bound validators) from those requested through the prompt, such as source grounding, and outline the evaluation needed to verify the latter. The architecture is domain-agnostic by design, and we outline how it could transfer to catalysis, energy storage, and preclinical biomedical research.</abstract>
<identifier type="citekey">kumar-etal-2026-bridging</identifier>
<location>
<url>https://aclanthology.org/2026.wasp-1.10/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>91</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bridging the Data Bottleneck: A Multi-Modal Generative Extraction Pipeline for Legacy Scientific Literature
%A Kumar, Gaurav
%A Bari, Anasse
%A Nagel, David J.
%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 kumar-etal-2026-bridging
%X The majority of historical experimental data across the empirical sciences remains locked in unstructured legacy formats, which slows data-driven discovery. We introduce an automated multi-modal pipeline that processes large literature corpora, filters non-empirical noise, and outputs structured datasets. Layout-aware document parsing is paired with a lightweight semantic triage gatekeeper to substantially reduce the computational overhead of applying frontier multi-modal models at scale. A generative model reconstructs experimental trajectories from text and figures, while a schema-constrained prompt and a strictly typed programmatic validation layer check physical bounds before serialization. We evaluate the pipeline on a 60-document corpus of extreme-condition thermodynamic literature drawn from Low Energy Nuclear Reactions (LENR) research, reporting concrete throughput, triage, and constraint-violation statistics. We distinguish safeguards enforced in code (physical-bound validators) from those requested through the prompt, such as source grounding, and outline the evaluation needed to verify the latter. The architecture is domain-agnostic by design, and we outline how it could transfer to catalysis, energy storage, and preclinical biomedical research.
%U https://aclanthology.org/2026.wasp-1.10/
%P 91-98
Markdown (Informal)
[Bridging the Data Bottleneck: A Multi-Modal Generative Extraction Pipeline for Legacy Scientific Literature](https://aclanthology.org/2026.wasp-1.10/) (Kumar et al., WASP 2026)
ACL