The framework uses static analysis to build a compact, deterministic representation of each repository: a dependency graph and a few contextual files.
Recovered design docs guide agents to rebuild original module structure, not test results.
A framework recovers intent, requirements and architecture from source code, and a round-trip test shows rebuilt libraries match original structure better while held-out pass rates stay similar.
Research Lab
Cezar Sas · Sandra Mitrović · Fabio Barth · Georg Rehm · Matteo Salani
IDSIA (SUPSI) · DFKI
Research Digest··3 min read
The authors present a framework that recovers aligned stakeholder intent, requirements and architecture from a compact repository representation (a static dependency graph and key contextual files), then release artefacts for 10,764 repositories in four languages.
Why this paper
From DFKI and IDSIA (SUPSI) · Released code and data
In one line
Recovered requirements and architecture preserve original module structure better during agentic rebuilds, but do not significantly improve functional correctness.
What it released
CodeData
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ✓Dataset link in the paper (huggingface.co)
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§