Leaderboard / medien.halowerk.com / endpoint
POST https://medien.halowerk.com/v1/baumarkt/media/subtitle-review-flags/snapshot-compare
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
- Data transform by llm, confidence 45%
- Latest quote
- $0.031 on Base to 0x2880…4E5E
- Uptime
- 100% / 7d, 100% / 30d
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 54m ago
- Next probe
- 2026-11-17 23:23 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.031 | 0x2880…4E5E | eip3009 | yes | 4h 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 |
|---|---|---|---|---|---|
| 11h ago | Data transform | 45% | llm | v1 | claude-haiku-5-5: Endpoint compares caller-supplied snapshots of subtitle cues and returns change witnesses after timing and source-quote validation, which is a deterministic transform of supplied data rather than media processing or a model-generated review. The 'editorial review flags' wording and provider call suggest some AI involvement, so confidence is moderate; 'other' or 'signal' are plausible alternatives. |
| 20h ago | Document | 50% | rules | v1 | rule document matched "subtitle" in metadata |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 54m ago | free | 402 | 2498 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |
| 7h ago | free | 402 | 167 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |
| 14h ago | free | 402 | 584 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |
| 20h ago | free | 402 | 466 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |
| 26h ago | free | 402 | 156 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |
| 32h ago | free | 402 | 159 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |
| 38h ago | free | 402 | 157 ms | v2 | yes | $0.031 | 0x2880…4E5E | — |