MétaCan
Menu
Back to cohort
Record W4407066124 · doi:10.1190/tle44020108.1

Advancing geologic document digitalization and information retrieval with generative AI

2025· article· en· W4407066124 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueThe Leading Edge · 2025
Typearticle
Languageen
FieldComputer Science
TopicImage Processing and 3D Reconstruction
Canadian institutionsVirtual Materials Group (Canada)
Fundersnot available
KeywordsGenerative grammarInformation retrievalComputer scienceArtificial intelligence

Abstract

fetched live from OpenAlex

Abstract This paper demonstrates how generative artificial intelligence (AI) enhances geoscientific document processing by improving text analysis, table extraction, and figure classification. Traditional workflows struggle with domain-specific terminology, poor-quality inputs, and rare formats. To address these challenges, we employ domain fine-tuned bidirectional encoder representations from transformers (BERT) models to enhance text processing. Additionally, we utilize multimodal large language models for precise table recognition and context-aware image classification. Finally, a domain-optimized retrieval system, GeoRAG, improves the relevance and accuracy of information retrieval. These AI-driven advancements streamline digitalization, enhance data extraction, and enable efficient handling of complex geoscientific documents. While challenges such as hallucinations, interpretability, and output consistency remain, this study highlights the transformative potential of generative AI for geoscience workflows and decision-making processes.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.960
Threshold uncertainty score0.341

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.002
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.004
GPT teacher head0.231
Teacher spread0.227 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it