How AI-Origin Detection Works: 47 Signal Types Explained
AI-origin detection combines stylometry, entropy, dependency context, and commit history to estimate whether code was human-written, AI-assisted, or AI-generated.
AI-origin detection is a signal model, not a magic label
Reliable AI-origin detection evaluates many weak signals together. No single variable proves authorship, but patterns across formatting, naming, control flow, dependency usage, comments, and commit timing can produce an explainable confidence score.
The 47-signal approach
ProvenanceOS groups signals into stylometric fingerprints, structural code patterns, repository history, dependency lineage, policy context, and model-family indicators. The result is a reviewable score that helps humans decide what needs attention.
How teams use the score
Security and legal teams can require review when confidence crosses a threshold, preserve evidence for audit reports, and compare AI usage across repositories without blocking every pull request by default.