Leaderboard / agent.pocket.network / endpoint
POST https://agent.pocket.network/v1/sentiment-classification
Scores measure reliability and honesty, not output quality.
- Listed only 2 days ago; new listings earn trust over 30 days.
- Answered all 11 probes in the last 7 days.
- Category
- Inference by llm, confidence 60%
- Latest quote
- $0.005 on Base to 0xF732…B829
- 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
- 1h ago
- Next probe
- 2026-11-19 01:04 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.005 | 0xF732…B829 | 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. 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 |
|---|---|---|---|---|---|
| 43h ago | Inference | 60% | llm | v1 | claude-haiku-5-5: Sentiment classification of text is model-style output (labels and scores) that fits inference, though it is lexicon-based rather than an LLM, and the tag 'documents' hints at a document category; inference is the closest fit for returned label and score output. |
| 47h ago | Inference | 50% | rules | v1 | rule inference matched "sentiment classif" in metadata |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 1h ago | free | 402 | 584 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 8h ago | free | 402 | 158 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 15h ago | free | 402 | 155 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 21h ago | free | 402 | 154 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 27h ago | free | 402 | 279 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 34h ago | free | 402 | 214 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 40h ago | free | 402 | 854 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 46h ago | free | 402 | 619 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 2d ago | free | 402 | 154 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 2d ago | free | 402 | 165 ms | v2 | yes | $0.005 | 0xF732…B829 | — |
| 3d ago | free | 402 | 154 ms | v2 | yes | $0.005 | 0xF732…B829 | — |