Leaderboard / cultmath.com / endpoint
POST https://cultmath.com/run/answer-share-quick
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 11 probes in the last 7 days.
- Category
- Web audit by llm, confidence 35%
- Latest quote
- $0.74 on Base to 0x628d…5ea3
- Uptime
- 100% / 7d, 100% / 30d
- Delivery
- none not yet paid-tested
- Observed
- none reported yet (opt-in wrapper telemetry)
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 33m ago
- Next probe
- 2026-11-19 01:27 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.74 | 0x628d…5ea3 | default | yes | 3h ago |
Paid probes
No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.
Delivery checks
Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.
No delivery checks yet. They run inside the weekly paid probe.
Classification history
Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 43h ago | Web audit | 35% | llm | v1 | claude-haiku-5-5: The endpoint measures which brands or websites AI assistants cite for a category and domain, which is an AI visibility or competitive audit of a domain the caller supplies. No listed category fits cleanly; web_audit is the closest match for auditing a URL or domain, though it is really AI-answer citation analysis, so confidence is moderate-low and 'other' is a plausible alternative. |
| 46h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 33m ago | free | 402 | 123 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 8h ago | free | 402 | 142 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 14h ago | free | 402 | 125 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 20h ago | free | 402 | 245 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 27h ago | free | 402 | 299 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 33h ago | free | 402 | 132 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 39h ago | free | 402 | 2123 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 46h ago | free | 402 | 145 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 2d ago | free | 402 | 115 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 2d ago | free | 402 | 135 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |
| 3d ago | free | 402 | 177 ms | v2 | yes | $0.74 | 0x628d…5ea3 | — |