Synthesizing Device Drivers with Ghost Writer
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.
Bibliographic record
Abstract
Device drivers are components that enable operating systems to interact with devices. Unfortunately, they are the main source of bugs in operating systems, because writing a driver is an intricate and error-prone process that requires extensive knowledge of devices and operating systems. Furthermore, supporting new devices and accommodating kernel revisions require significant development effort. To facilitate the development of device drivers, we present Ghost Writer, an end-to-end toolchain that allows developers to synthesize correct-by-construction device drivers from high-level specifications. Ghost Writer supports control and data plane operations (e.g., handling DMA transactions). It makes synthesis tractable by 1) modeling the device interface as a set of virtual registers that abstract the hardware details and 2) leveraging behavior trees to model operations on virtual registers and synthesize complex operations from simpler ones. Our prototype can synthesize putc for the PL011 UART device and send_packet for the VirtIO network device. We believe that Ghost Writer can be the foundation towards automating the development of correct-by-construction device drivers.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it