Direct measurement

Text labeling

openai/gpt-oss-120b · Exam revision 0.1.0

3/3Certified passes · rate not published

Exact exam

vvdex.annotation.text-labeling-1

Fingerprint: e1abe51398b2d950a3415678aaf8ec796420dfb05ea89b3b64afd33c1e345fd3
Revision status: Recorded revision

Input delivery

Text

Evidence state: Proved
Adapter: vvdex-canonical-tools · 1
Provenance: Not established

Approved quality

Task-level measurements

Classificationaccuracy: 1.0 · 3 samples
Classificationf1: 1.0 · 3 samples
Classificationprecision: 1.0 · 3 samples
Classificationrecall: 1.0 · 3 samples
Spanexactf1: 1.0 · 3 samples
Spanf1: 1.0 · 3 samples
Spanoverlapiou: 1.0 · 3 samples
Spanprecision: 1.0 · 3 samples
Spanrecall: 1.0 · 3 samples

Comparison conditions

Unproven

delivery conditions differ; delivery equivalence is unproven; delivery is not proved; lane configuration is not recorded; repository cleanliness differs; execution equivalence is unproven; runtime limits differ

Evidence path

From measurement to sealed proof

Sealed record

Evaluation ID: fr-20260907-dad35536
Record digest: d98a068bbbb888bb6215a3e1a72a7d079fc043fd8b98f52d14be0a58303da22e

Certified attempt outcomes

4072a55a-c3d4-4022-a13d-1da0420a80a3certified pass
286631d0-d089-45db-a6ce-8d8c6c0a8c00certified pass
1a3bb2c1-b140-4ff5-8252-5b7e10056541certified pass
78744a06-7809-4afb-a742-9d598907326dlane error
0d8cba8d-3afd-4eb0-9a7f-c61f3618a072lane error
ef0426f1-e4ca-44d4-8593-9a544d0de4eelane error

Open campaign summary →

Campaign fc-3377c49ce724 →Exam certification →Verify sealed evidence →

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