Compiling Distributed System Models with PGo [evaluation]
Bibliographic record
Abstract
Distributed systems are difficult to design and implement<br> correctly. In response, both research and industry are exploring<br> applications of formal methods to distributed systems. A key challenge<br> in this domain is the missing link between the formal design of a<br> system and its implementation. Today, practitioners bridge this link through<br> manual effort. We present a language called Modular PlusCal that extends PlusCal by<br> cleanly separating the model of a system from a model of its<br> environment. We then present a compiler tool-chain called PGo that<br> automatically translates MPCal models to TLA+ for model checking,<br> and that also compiles MPCal models to runnable Go code.<br> PGo provides system designers with a new ability to model and check<br> their designs, and then re-use their modeling efforts to<br> mechanically extract runnable implementations of their designs. Our evaluation shows that the PGo approach works for complex models:<br> we model check, compile, and evaluate the performance of MPCal systems<br> based on Raft, CRDTs, and primary-backup.<br> Compared to previous work, PGo requires less time to develop a<br> checked model and derive a fully working implementation. With PGo we<br> created a formally checked Raft model and its corresponding<br> implementation in under 1 person-month, which is 3x less time than<br> Ivy. Our evaluation shows that a PGo-based<br> Raft KV store with three nodes has 41% higher throughput than a Raft<br> KV store based on Ivy, the highest performing verified Raft-based KV<br> store from related work. A PGo-based CRDT set has a latency within 2x of a CRDT set implementation from SoundCloud called<br> Roshi.
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 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.097 | 0.006 |
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; both teacher heads agree on what is shown here.
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".