BinComp: A stratified approach to compiler provenance Attribution
Bibliographic record
Abstract
Compiler provenance encompasses numerous pieces of information, such as the compiler family, compiler version, optimization level, and compiler-related functions. The extraction of such information is imperative for various binary analysis applications, such as function fingerprinting, clone detection, and authorship attribution. It is thus important to develop an efficient and automated approach for extracting compiler provenance. In this study, we present B i n C o m p , a practical approach which, analyzes the syntax, structure, and semantics of disassembled functions to extract compiler provenance. B i n C o m p has a stratified architecture with three layers. The first layer applies a supervised compilation process to a set of known programs to model the default code transformation of compilers. The second layer employs an intersection process that disassembles functions across compiled binaries to extract statistical features (e.g., numerical values) from common compiler/linker-inserted functions. This layer labels the compiler-related functions. The third layer extracts semantic features from the labeled compiler-related functions to identify the compiler version and the optimization level. Our experimental results demonstrate that B i n C o m p is efficient in terms of both computational resources and time.
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 | 0.004 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.003 | 0.006 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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.
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".