Leaderboard / agent-data.centorprat.workers.dev / endpoint
POST https://agent-data.centorprat.workers.dev/tools/app-review-problem-scanner
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 8 probes in the last 7 days.
- Category
- Web scrape by llm, confidence 45%
- Latest quote
- $0.05 on Base to 0x8d38…B120
- 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
- 39m ago
- Next probe
- 2026-11-18 05:45 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.05 | 0x8d38…B120 | default | yes | 2h ago |
| cdp | exact | Polygon | 0x3c49…3359 | 50000 | 0x8d38…B120 | default | yes | 2h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 50000 | 3644Dr…RHQh | default | yes | 2h 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 |
|---|---|---|---|---|---|
| 23h ago | Web scrape | 45% | llm | v1 | claude-haiku-5-5: The endpoint pulls recent app store reviews for given apps and returns a problem brief with themes, spike versions, ratings and sample complaints. No listed category fits exactly; it is closest to web_scrape since it fetches public review content from store pages, though it is really an analysis of review data, so confidence is moderate. |
| 27h ago | Public data | 60% | rules | v1 | rule public_data matched "app store" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 39m ago | free | 402 | 220 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 7h ago | free | 402 | 387 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 13h ago | free | 402 | 632 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 20h ago | free | 402 | 252 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 26h ago | free | 402 | 245 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 32h ago | free | 402 | 209 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 39h ago | free | 402 | 204 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |
| 45h ago | free | 402 | 248 ms | v2 | yes | $0.05 | 0x8d38…B120 | — |