dmodel · Model identity and integrity report
Last updated：Aug 22, 2026, 2:22 AM · Data window: past 90 days
Measured results (90 days)
5 runs · 3 hosts · 5 anomalies
Family-fingerprint consistency
anthropic 2 ██████████░░░░░░░░░░░░░░░ 40% (suspicious) qwen 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious) openai 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious) deepseek 1 █████░░░░░░░░░░░░░░░░░░░░ 20% (suspicious)
Observed V3 sub-model mapping
→ abstain 3 (60%) — low confidence → unknown 1 (20%) ⚠ mismatch → deepseek/deepseek-v4-pro 1 (20%) ⚠ mismatch sim=0.68
Capability score distribution (auxiliary)
0-49 ████████████████████░░░░░ 4 50-69 █████░░░░░░░░░░░░░░░░░░░░ 1 70-89 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0 90-100 ░░░░░░░░░░░░░░░░░░░░░░░░░ 0
Host integrity ranking
| Host | Runs | Average score | Family match | Most common V3 match |
|---|---|---|---|---|
| https://api.makeyourlifeeasier.web.id/v1 | 3 | 0 | 0% | — |
| https://rhz4zlv.abc-tunnel.us/v1 | 1 | 0 | 0% | deepseek/deepseek-v4-pro (1) |
| https://arrives-knife-operation-carlos.trycloudflare.com/v1 | 1 | 67 | 0% | — |
Recent anomalies
https://api.makeyourlifeeasier.web.id/v1Aug 21, 2026, 11:39 PM
- Self-claimed model
- d-model
- V2 predicted family
- qwen
- V3 best match
- —
- Verdict
- Full swap
https://api.makeyourlifeeasier.web.id/v1Aug 21, 2026, 10:12 PM
- Self-claimed model
- d-model
- V2 predicted family
- openai
- V3 best match
- —
- Verdict
- Family mismatch
https://api.makeyourlifeeasier.web.id/v1Aug 21, 2026, 9:05 PM
- Self-claimed model
- d-model
- V2 predicted family
- anthropic
- V3 best match
- —
- Verdict
- V3 low confidence · Abstain
https://rhz4zlv.abc-tunnel.us/v1Aug 18, 2026, 4:38 AM
- Self-claimed model
- qd/dmodel
- V2 predicted family
- deepseek
- V3 best match
- deepseek/deepseek-v4-pro (sim 0.68)
- Verdict
- Full swap
https://arrives-knife-operation-carlos.trycloudflare.com/v1Aug 18, 2026, 3:35 AM
- Self-claimed model
- qd/dmodel
- 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 dmodel. Low family consistency, a different V3 match, or divergence from selfClaim is flagged as anomalous. BazaarLink Probe home.