Evidence-grounded retrieval and structured extraction for extraterrestrial organic matter literature
- 1SKL Lunar and Planetary Sciences, Macau University of Science and Technology, Taipa 999078, China; CNSA Macau Center for Space Exploration and Science, Taipa 999078, Macao Special Administrative Region of China; Macau University of Science and Technology Zhuhai MUST Science and Technology Research Institute, Zhuhai 519031, China
- 2School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China
Abstract
Extraterrestrial organic matter (EOM) records early Solar System chemistry and prebiotic processes and is central to biosignature interpretation. However, relevant evidence remains dispersed across PDF articles, tables, supplements, and scanned reports, limiting systematic reuse. We developed an evidence-grounded retrieval and structured-extraction workflow that converts 670 English-language PDFs into a queryable, traceable evidence layer. The corpus spans meteorites, returned samples from Ryugu and Bennu, and lunar materials, alongside literature on analytical methods and contamination control. The workflow combines optical character recognition (OCR)-compatible ingestion, Okapi Best Matching 25 (BM25) lexical retrieval, transformer-based dense retrieval, weighted hybrid fusion, optional cross-encoder reranking, evidence-grounded question answering, and schema-guided extraction. Evaluation on 45 queries and 683 judgments showed complementary retrieval behavior: hybrid retrieval provided the highest recall, BM25 the strongest reciprocal-rank performance, and dense retrieval the highest normalized ranking quality; no method dominated all metrics. All 670 PDFs were successfully ingested. Across 20 questions and five pipelines using the same large language model (LLM), the LLM-only condition provided no corpus-linked evidence, whereas all retrieval-augmented generation pipelines returned traceable source identifiers and 90%–95% evidence-checkable answers. Extraction was more reliable for meteorite names and organic compounds than for contamination controls, revealing remaining boundary and context challenges. These results establish a reproducible computational workflow for organizing traceable evidence from EOM literature, supporting biosignature interpretation and sample-return studies. Remaining limitations include OCR-heavy documents and table/figure content.
Related
- Temporal Synchronization Determines the Accuracy of Sentinel-2 Turbidity Retrieval: Evidence from Community-Based Monitoring of the Buriganga River, Dhaka
- Radiative Transfer Modelling of Ka-band Microwave Interactions with Snow-Covered Freshwater Ice: Implications for SWOT KaRIn Property Retrieval
- Bayesian Retrieval of L-Band Absorption by Ice using SMOS Brightness Temperatures over the Antarctic Plateau
- Regime-aware retrieval of lower-tropospheric stability and a sensitivity-weighted diagnostic of cross-site transferability over heterogeneous land surfaces
- Toward fine-scale microwave monitoring of dryland vegetation: an alternative high spatial resolution vegetation optical depth retrieval algorithm from Sentinel-1 over the Sahel region
BibTeX
@article{chen2026evidencegrounded,
title = {{Evidence-grounded retrieval and structured extraction for extraterrestrial organic matter literature}},
author = {Bohan Chen and Jialong Lai and Ting Huang and Zhengyang Zou and Yong Zhao and David Carlos Fernandez-Remolar},
journal = {Applied Computing and Geosciences},
year = {2026},
month = oct,
doi = {10.1016/j.acags.2026.100420},
url = {https://doi.org/10.1016/j.acags.2026.100420},
note = {CC BY},
}
RIS
TY - JOUR
TI - Evidence-grounded retrieval and structured extraction for extraterrestrial organic matter literature
AU - Bohan Chen
AU - Jialong Lai
AU - Ting Huang
AU - Zhengyang Zou
AU - Yong Zhao
AU - David Carlos Fernandez-Remolar
PY - 2026
DA - 2026/10/30
JO - Applied Computing and Geosciences
DO - 10.1016/j.acags.2026.100420
UR - https://doi.org/10.1016/j.acags.2026.100420
AB - Extraterrestrial organic matter (EOM) records early Solar System chemistry and prebiotic processes and is central to biosignature interpretation. However, relevant evidence remains dispersed across PDF articles, tables, supplements, and scanned reports, limiting systematic reuse. We developed an evidence-grounded retrieval and structured-extraction workflow that converts 670 English-language PDFs into a queryable, traceable evidence layer. The corpus spans meteorites, returned samples from Ryugu and Bennu, and lunar materials, alongside literature on analytical methods and contamination control. The workflow combines optical character recognition (OCR)-compatible ingestion, Okapi Best Matching 25 (BM25) lexical retrieval, transformer-based dense retrieval, weighted hybrid fusion, optional cross-encoder reranking, evidence-grounded question answering, and schema-guided extraction. Evaluation on 45 queries and 683 judgments showed complementary retrieval behavior: hybrid retrieval provided the highest recall, BM25 the strongest reciprocal-rank performance, and dense retrieval the highest normalized ranking quality; no method dominated all metrics. All 670 PDFs were successfully ingested. Across 20 questions and five pipelines using the same large language model (LLM), the LLM-only condition provided no corpus-linked evidence, whereas all retrieval-augmented generation pipelines returned traceable source identifiers and 90%–95% evidence-checkable answers. Extraction was more reliable for meteorite names and organic compounds than for contamination controls, revealing remaining boundary and context challenges. These results establish a reproducible computational workflow for organizing traceable evidence from EOM literature, supporting biosignature interpretation and sample-return studies. Remaining limitations include OCR-heavy documents and table/figure content.
SN - 2590-1974
ER -