openai/gpt-5.4-mini · Model identity and integrity report

Family

openai

V3 sub-model reference

Available ✓

Checks

知識截止 · 能力探針 · 拒絕模板 · 拒絕溫度參數

Family-fingerprint coverage

52 weighted rules · 8 feature categories

Concrete reference answers, refusal templates, and individual signal weights are not published because disclosure would help spoofing endpoints evade detection.

79 runs · 54 hosts · 72 anomalies

Family-fingerprint consistency

  openai          77  ████████████████████████░   97% (expected)
  unknown          2  █░░░░░░░░░░░░░░░░░░░░░░░░    3% (suspicious)

Observed V3 sub-model mapping

  → abstain                                 45 (57%) — low confidence
  → openai/gpt-5.4                          25 (32%) ⚠ mismatch sim=0.92
  → unknown                                  4 ( 5%) ⚠ mismatch
  → openai/gpt-5.4-mini                      3 ( 4%) ✓ correct sim=0.94
  → openai/gpt-4.1-mini                      1 ( 1%) ⚠ mismatch sim=0.70
  → openai/gpt-5.5                           1 ( 1%) ⚠ mismatch sim=0.94

Capability score distribution (auxiliary)

  0-49     ██████████░░░░░░░░░░░░░░░   31
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ██████████░░░░░░░░░░░░░░░   31
  90-100   ██████░░░░░░░░░░░░░░░░░░░   17

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming openai/gpt-5.4-mini. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.