claude4sonnet · Model identity and integrity report
Last updated:Jul 30, 2026, 8:50 AM · Data window: past 90 days
Measured results (90 days)
7 runs · 1 hosts · 7 anomalies
Family-fingerprint consistency
anthropic 7 █████████████████████████ 100% (suspicious)
Observed V3 sub-model mapping
→ anthropic/claude-haiku-4.5 7 (100%) ⚠ mismatch sim=0.73
Capability score distribution (auxiliary)
0-49 ███████░░░░░░░░░░░░░░░░░░ 2 50-69 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 70-89 ██████████████████░░░░░░░ 5 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://ai-api.burgeon.cn/v1 | 7 | 61 | 0% | anthropic/claude-haiku-4.5 (7) |
Recent anomalies
https://ai-api.burgeon.cn/v1May 26, 2026, 9:09 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.75)
- Verdict
- Full swap
https://ai-api.burgeon.cn/v1May 26, 2026, 8:20 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.75)
- Verdict
- Full swap
https://ai-api.burgeon.cn/v1May 26, 2026, 8:16 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.70)
- Verdict
- Full swap
https://ai-api.burgeon.cn/v1May 26, 2026, 8:15 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.75)
- Verdict
- Full swap
https://ai-api.burgeon.cn/v1May 26, 2026, 8:01 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.70)
- Verdict
- Full swap
https://ai-api.burgeon.cn/v1May 26, 2026, 7:00 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.75)
- Verdict
- Full swap
https://ai-api.burgeon.cn/v1May 26, 2026, 6:56 AM
- Self-claimed model
- claude-4-sonnet
- V2 predicted family
- anthropic
- V3 best match
- anthropic/claude-haiku-4.5 (sim 0.73)
- Verdict
- Full swap
Methodology
BazaarLink Probe combines a Bayesian V2 family classifier across nine fingerprint categories with V3 sub-model references to verify endpoints claiming claude4sonnet. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.