Paywary

Leaderboard / lqd-verdict.onrender.com / endpoint

POST https://lqd-verdict.onrender.com/v1/verdict

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered all 11 probes in the last 7 days.
Category
Signal by llm, confidence 50%
Latest quote
$0.03 on Base to 0xc011…e4bb
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
54m ago
Next probe
2026-11-19 01:28 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
9w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactSolanaEPjFWd…Dt1v30000DPWRUL…PPmqdefaultyes3h ago
cdpexactBase0x8335…2913$0.030xc011…e4bbdefaultyes3h ago
payaiexactSolanaEPjFWd…Dt1v30000DPWRUL…PPmqdefaultyes3h 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.

WhenCategoryConfidenceMethodVersionEvidence
43h agoSignal50%llmv1claude-haiku-5-5: The endpoint returns a yes-or-no verdict with a short reason on whether to buy a men's clothing item, which is an AI-style judgment or recommendation similar to a risk verdict, but the domain is fashion rather than trading, so confidence is moderate.
47h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
54m agofree402328 msv2yes$0.030xc011…e4bb—
8h agofree402358 msv2yes$0.030xc011…e4bb—
14h agofree402420 msv2yes$0.030xc011…e4bb—
21h agofree402129 msv2yes$0.030xc011…e4bb—
27h agofree402503 msv2yes$0.030xc011…e4bb—
34h agofree402366 msv2yes$0.030xc011…e4bb—
40h agofree402190 msv2yes$0.030xc011…e4bb—
46h agofree402411 msv2yes$0.030xc011…e4bb—
2d agofree402286 msv2yes$0.030xc011…e4bb—
2d agofree402334 msv2yes$0.030xc011…e4bb—
3d agofree402330 msv2yes$0.030xc011…e4bb—