Leaderboard / api.agent-data.workers.dev / endpoint
GET https://api.agent-data.workers.dev/api/v1/science/pubmed
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
- Public data by llm, confidence 60%
- Latest quote
- $0.02 on Base to 0x2a99…bd4e
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 6h ago
- Next probe
- 2026-11-17 17:10 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Solana | Es9vMF…wNYB | 20000 | EQuJg7…HKFA | default | yes | 3h ago |
| cdp | exact | Base | 0x8335…2913 | $0.02 | 0x2a99…bd4e | default | yes | 3h ago |
| cdp | exact | Solana | EPjFWd…Dt1v | 20000 | EQuJg7…HKFA | 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. 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 |
|---|---|---|---|---|---|
| 9h ago | Public data | 60% | llm | v1 | claude-haiku-5-5: The endpoint searches PubMed biomedical citations and returns paper metadata such as title, authors, journal, PMID and DOI. That is open scientific literature, which fits public_data best. web_search is a weaker fit because the source is a curated academic database rather than the open web. |
| 19h ago | Public data | 60% | rules | v1 | rule public_data matched "pubmed" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 6h ago | free | 402 | 39 ms | v2 | yes | $0.02 | 0x2a99…bd4e | — |
| 12h ago | free | 402 | 215 ms | v2 | yes | $0.02 | 0x2a99…bd4e | — |
| 18h ago | free | 402 | 243 ms | v2 | yes | $0.02 | 0x2a99…bd4e | — |
| 24h ago | free | 402 | 266 ms | v2 | yes | $0.02 | 0x2a99…bd4e | — |
| 31h ago | free | 402 | 14 ms | v2 | yes | $0.02 | 0x2a99…bd4e | — |
| 37h ago | free | 402 | 16 ms | v2 | yes | $0.02 | 0x2a99…bd4e | — |