kwaipilot/kat-coder-pro-v2.5 · Model identity and integrity report

Last updated：Sep 17, 2026, 10:20 AM · Data window: past 90 days

Measured results (90 days)

2 runs · 1 hosts · 2 anomalies

Family-fingerprint consistency

  anthropic        2  █████████████████████████  100% (suspicious)

Observed V3 sub-model mapping

  → abstain                                  2 (100%) — low confidence

Capability score distribution (auxiliary)

  0-49     █████████████████████████    2
  50-69    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  70-89    ░░░░░░░░░░░░░░░░░░░░░░░░░    0
  90-100   ░░░░░░░░░░░░░░░░░░░░░░░░░    0

Host integrity ranking

Host	Runs	Average score	Family match	Most common V3 match
https://api.hcnsec.cn/v1	2	0	0%	—

Recent anomalies

https://api.hcnsec.cn/v1Aug 31, 2026, 4:26 PM

Self-claimed model: kat-coder-pro-v2.5
V2 predicted family: anthropic
V3 best match: —
Verdict: V3 low confidence · Abstain

https://api.hcnsec.cn/v1Aug 29, 2026, 1:20 PM

Self-claimed model: kat-coder-pro-v2.5
V2 predicted family: anthropic
V3 best match: —
Verdict: V3 low confidence · Abstain

Methodology

BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming kwaipilot/kat-coder-pro-v2.5. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.

Test an endpoint yourself →