Add it to a GitHub README or profile β the card updates as the ranking changes:
Benchmark contamination forensics: exact n-gram containment scanning in pure Python plus a C++17 MinHash engine (bloomdex) for corpus-scale leakage checks.
AI failure causality explorer: ingest execution events and their dependencies, forge a causal graph, rank the events most likely to have started an incident, and export timelines plus Markdown/JSON investigations.