Leaderboard / doc.lonestaroracle.xyz / endpoint
POST https://doc.lonestaroracle.xyz/convert
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 6 probes in the last 7 days.
- Category
- Document by llm, confidence 85%
- Latest quote
- $0.05 on Base to 0x52Ab…6C06
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 4h ago
- Next probe
- 2026-11-17 16:28 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | eip155:5042 | 0x3600…0000 | 50000 | 0xeF2a…42ab | eip3009 | yes | 36m ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 50000 | 3nmeVj…rSgw | default | yes | 36m ago |
| payai | exact | Base | 0x8335…2913 | $0.05 | 0x52Ab…6C06 | default | yes | 3m ago |
| cdp | exact | Base | 0x8335…2913 | $0.05 | 0x52Ab…6C06 | default | yes | 36m 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. Delivery results do not affect scores yet.
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 |
|---|---|---|---|---|---|
| 13h ago | Document | 85% | llm | v1 | claude-haiku-5-5: The endpoint converts PDFs, webpages and docs into Markdown, which is file conversion, so document fits best. The optional AI summary is secondary. It could be read as web_scrape since it fetches URLs, but the core output is format conversion of documents. |
| 16h ago | Document | 60% | rules | v1 | rule document matched "pdf" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 4h ago | free | 402 | 234 ms | v2 | yes | $0.05 | 0x52Ab…6C06 | — |
| 10h ago | free | 402 | 284 ms | v2 | yes | $0.05 | 0x52Ab…6C06 | — |
| 16h ago | free | 402 | 230 ms | v2 | yes | $0.05 | 0x52Ab…6C06 | — |
| 22h ago | free | 402 | 228 ms | v2 | yes | $0.05 | 0x52Ab…6C06 | — |
| 28h ago | free | 402 | 229 ms | v2 | yes | $0.05 | 0x52Ab…6C06 | — |
| 35h ago | free | 402 | 236 ms | v2 | yes | $0.05 | 0x52Ab…6C06 | — |