Leaderboard / api.craigmbrown.com / endpoint
POST https://api.craigmbrown.com/v1/services/content.youtube-research
Scores measure reliability and honesty, not output quality.
- Answered 7 of 8 probes in the last 7 days (88%).
- Answered 7 of 8 probes in the last 30 days (88%).
- Category
- Web scrape by llm, confidence 60%
- Latest quote
- $0.03 on Base to 0x5E70…4EB9
- Uptime
- 88% / 7d, 88% / 30d
- Delivery
- none not yet paid-tested
- Observed
- none reported yet (opt-in wrapper telemetry)
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 6h ago
- Next probe
- 2026-11-18 12:17 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.03 | 0x5E70…4EB9 | default | yes | 37m 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 |
|---|---|---|---|---|---|
| 22h ago | Web scrape | 60% | llm | v1 | claude-haiku-5-5: The endpoint researches YouTube videos by fetching their transcripts and returning per-video theses, claims and quotes, which is closest to reading and returning page content. It could also be seen as inference or web_search given the topic-discovery and summarisation aspects, but transcript retrieval is the core output. |
| 38h ago | Inference | 60% | rules | v1 | rule inference matched "transcripts" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 6h ago | free | 402 | 114 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |
| 18h ago | free | timeout | 15001 ms | — | — | — | — | no_responsefetch_error:timeout |
| 24h ago | free | 402 | 181 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |
| 31h ago | free | 402 | 113 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |
| 37h ago | free | 402 | 109 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |
| 43h ago | free | 402 | 334 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |
| 2d ago | free | 402 | 120 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |
| 2d ago | free | 402 | 95 ms | v2 | yes | $0.03 | 0x5E70…4EB9 | — |