Leaderboard / verdict.kechlab.com / endpoint
POST https://verdict.kechlab.com/v1/canary-check
Scores measure reliability and honesty, not output quality.
- Quoted a price different from the listed price on 12 of 12 comparable probes.
- Listed only 3 days ago; new listings earn trust over 30 days.
- Category
- Signal by llm, confidence 50%
- Latest quote
- $0.0073 on Base to 0xb36c…54Eb
- 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
- 3h ago
- Next probe
- 2026-11-19 07:51 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.0091 | 0xb36c…54Eb | default | yes | 5h 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 |
|---|---|---|---|---|---|
| 45h ago | Signal | 50% | llm | v1 | claude-haiku-5-5: The endpoint returns a verdict (clean, review or leak) on whether a model reply leaked secrets, which is a risk verdict rather than LLM output. It is an AI safety check, so signal fits best, though compliance or inference are plausible alternatives since it is a guardrail rather than a trading or forecast signal. |
| 2d ago | Inference | 60% | rules | v1 | rule inference matched "paraphrase" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 3h ago | free | 402 | 606 ms | v2 | yes | $0.0073 | 0xb36c…54Eb | price_below_listingprice_mismatch |
| 9h ago | free | 402 | 684 ms | v2 | yes | $0.0073 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 16h ago | free | 402 | 923 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatch |
| 22h ago | free | 402 | 498 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatch |
| 29h ago | free | 402 | 489 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 35h ago | free | 402 | 680 ms | v2 | yes | $0.0074 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 42h ago | free | 402 | 589 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatch |
| 2d ago | free | 402 | 475 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 2d ago | free | 402 | 557 ms | v2 | yes | $0.0076 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 3d ago | free | 402 | 519 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatch |
| 3d ago | free | 402 | 586 ms | v2 | yes | $0.0075 | 0xb36c…54Eb | price_below_listingprice_mismatchprice_changed |
| 3d ago | free | 402 | 503 ms | v2 | yes | $0.0076 | 0xb36c…54Eb | price_below_listingprice_mismatch |