VVDex ForgeAI exams. Evidence. Independent grading.

Direct measurement

Robot video annotation

cli/codex-gpt-5.5 · Exam revision 0.1.0

0/9Certified passes · rate not published

Exact exam

vvdex.annotation.robot-video-1

Fingerprint
c3b4773c375c10ad989357bb179cffd62151eccd2a58b52254609a54d434be33
Revision status
Recorded revision

Input delivery

Video — sampled frames

Evidence state
Proved
Adapter
Not recorded
Provenance
Not established

Approved quality

Task-level measurements

Boxf1
0.75 · 4 samples
Boxiou
0.5597967422313328 · 4 samples
Boxprecision
0.75 · 4 samples
Boxrecall
0.75 · 4 samples
Classificationaccuracy
1.0 · 4 samples
Classificationf1
1.0 · 4 samples
Classificationprecision
1.0 · 4 samples
Classificationrecall
1.0 · 4 samples
Eventf1
0.0 · 4 samples
Eventprecision
0.0 · 4 samples
Eventrecall
0.0 · 4 samples
Eventtemporaliou
0.13928571428571446 · 4 samples
Segmentf1
0.8333333333333333 · 4 samples
Segmentprecision
0.75 · 4 samples
Segmentrecall
1.0 · 4 samples
Segmenttemporaliou
0.6044722497522305 · 4 samples
Trackingconsistency
1.0 · 4 samples

Comparison conditions

Unproven

delivery adapter identity, version or configuration is not recorded; delivery conditions differ; delivery equivalence is unproven; delivery is not proved; different exam fingerprint; lane configuration is not recorded; repository cleanliness differs; execution equivalence is unproven; runtime limits differ

Evidence path

From measurement to sealed proof

Public evidence exposes commitments and approved report sections. Canonical task bodies, hidden tests, answers and private traces remain withheld.