Evidence · DiggingBeagle record
Small decision models used for memory safety vulnerability triage at scale
Research on rule-based candidate mining and 4B typed decision ranking across C/C++ repositories followed by execution and human validation.
- Published
- Nov 12, 2026
- Source role
- primary disclosure
Evidence record
Research on rule-based candidate mining and 4B typed decision ranking across C/C++ repositories followed by execution and human validation.
Claim-level citations (2)
- supportsA 4B typed decision model prioritized low-cost memory-safety research, while execution and human review supplied the actual proof: A software security harness mined fixed rules, patch clues and static signals across 4,245 C/C++ repositories. A small typed-decision model ranked bounded candidates instead of generating full exploit narratives; later reproducibility and human validation established which candidates were genuine. The researchers report 187 confirmed findings, with impact categories and follow-up disclosure status. The model classifier itself had modest discrimination and weak pairwise vulnerable-versus-patched ranking; the pipeline required deterministic checks and substantial follow-through.
Decision-model paper, Method, Classification, campaign results and limitations
- supportsA 4B typed decision model prioritized low-cost memory-safety research, while execution and human review supplied the actual proof: The 187 reports are not independently confirmed internet exploitation or 187 new CVEs with public patches. Reported throughput and cost omit parts of the original engineering effort; effectiveness depends on the candidate miner and validation budget. The AI mechanism is constrained decision-based triage, not giving an untrusted model authority to declare a flaw, assign a final severity or execute live exploits.
Primary disclosure: results, scope and limitations