MétaCan
Menu
← Back to cohort
Record W7082440795 · doi:10.5281/zenodo.17170899

Applying Large Language Models to Space Engineering Documentation

2025· report· en· W7082440795 on OpenAlexaffabout

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2025
Typereport
Languageen
FieldComputer Science
TopicGeochemistry and Geologic Mapping
Canadian institutionsCanadian Space Agency
Fundersnot available
KeywordsDocumentationSpace (punctuation)Model-driven architectureChatbotValue (mathematics)Technical documentation

Abstract

fetched live from OpenAlex

Space programs produce large volumes of engineering documentation which is increasingly challenging for engineers to digest. In addition, the complexity of space systems is increasing, and a new generation of space engineers are taking on challenging roles which require rapid assimilation of vast quantities of engineering documents. Project management practices have evolved to provide rigor and documentation around the programs including documents such as lessons learned, risks, mitigations etc. The ability to combine these documents rapidly and access distilled content that has been processed by a Large Language Model (LLM) has great value on large space engineering programs and projects. This paper outlines the approach and findings undertaken by the Canadian Space Agency, Space Exploration Development group in a prototype LLM AI chatbot that allows users to interact with engineering documents, citing the sources of the provided answers.

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.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.005
metaresearch head score (Gemma)0.026
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.012
Threshold uncertainty score0.027

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0050.026
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0050.007
Open science0.0020.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0060.002

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 head0.033
GPT teacher head0.262
Teacher spread0.229 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)→Same topicGeochemistry and Geologic Mapping→French-language works237,207→