Leaderboard / research.halowerk.com / endpoint
POST https://research.halowerk.com/v1/grounding-score
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 7 probes in the last 7 days.
- Category
- Inference by llm, confidence 42%
- Latest quote
- $0.002 on Base to 0x2880…4E5E
- 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
- 2h ago
- Next probe
- 2026-11-18 03:15 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.002 | 0x2880…4E5E | eip3009 | yes | 56m 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 |
|---|---|---|---|---|---|
| 3h ago | Inference | 42% | llm | v1 | claude-haiku-5-5: The endpoint scores how well an answer's sentences are supported by supplied sources, a grounding or fact-checking analysis of model output. It has no service name or tags and the description is somewhat abstract, but it is not a plain web search or scrape; the closest fit among the categories is inference (model output evaluation), though signal or other could plausibly apply. |
| 26h ago | Other | 40% | rules | v1 | rule none matched "" in none |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 2h ago | free | 402 | 537 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |
| 8h ago | free | 402 | 575 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |
| 15h ago | free | 402 | 567 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |
| 21h ago | free | 402 | 159 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |
| 28h ago | free | 402 | 152 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |
| 35h ago | free | 402 | 463 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |
| 41h ago | free | 402 | 154 ms | v2 | yes | $0.002 | 0x2880…4E5E | — |