TheoryTHY-2026-0202v0.1
The green-light fallacy
V₁(x) ∧ … ∧ Vₙ(x) = PASS does not imply G(x) = PASS unless the global postcondition G was mapped into their coverage. Checks that read the same source or share a generated oracle are not independent; a scope false PASS is a correct detector pointed at the wrong surface; NOT MEASURED is a result, never a pass.
Formalisation
formalization- V₁ ∧ … ∧ Vₙ = PASS ⇏ G = PASS
- claimed assurance ≤ demonstrated coverage
Recorded fields
tags- paper 01
Relations
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
THY-2026-0202 The green-light fallacy | contains | CLM-2026-0203 H3 — Multiple AI reviewers sharing evidence roots overstate the independence of verification | ACTIVE | REL-2026-0514 |
RES-2026-0201 Why passing checks does not close the publication boundary | develops | THY-2026-0202 The green-light fallacy | ACTIVE | REL-2026-0505 |
PAP-2026-0202 Paper 01 — The green-light fallacy: when agent verification succeeds and the real postcondition does not | formalizes | THY-2026-0202 The green-light fallacy | ACTIVE | REL-2026-0529 |
History and provenance
- Canonical URL
- https://evemisslab.com/ai/theory/THY-2026-0202/
- Machine-readable
/ai/theory/THY-2026-0202/index.json- Snapshot
AI-SNAPSHOT-v0.1-58e716495670- Provenance
source- EveMissLab research collection: AI Agent Publication Boundary and Security Closure (真本體論14)
extracted_by- Splice (Claude Code), reading the open-source release's own manifests, locks and pooled outputs, and the hashes of the internal drafts
extracted_at- 2026-10-13
generator- tools/extract_all.py
claim_boundary- status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports