Galápagos: Automated N-Version Programming with LLMs
Bibliographic record
Abstract
N-Version Programming is a well-known methodology for developing fault-tolerant systems. It achieves fault detection and correction at runtime by adding diverse redundancy into programs, minimizing fault mode overlap between redundant program variants. In this work, we propose the automated generation of program variants using large language models. We design, develop, and evaluate Galápagos : a tool for generating program variants using LLMs, validating their correctness and equivalence, and using them to assemble N-Version binaries. We evaluate Galápagos by creating N-Version components of real-world C code. Our original results show that Galápagos can produce program variants that are proven to be functionally equivalent, even when the variants are written in a different programming language. Our systematic diversity measurement indicates that functionally equivalent variants produced by Galápagos are statically different after compilation and present diverging internal behavior at runtime. We demonstrate that the variants produced by Galápagos can protect C code against real miscompilation bugs which affect the Clang compiler. Overall, our article shows that producing N-Version software can be drastically automated by advanced usage of practical formal verification and generative language models.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".