Paywary

Leaderboard / verdict.kechlab.com / endpoint

POST https://verdict.kechlab.com/v1/moderate

Scores measure reliability and honesty, not output quality.

91Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Quoted a price different from the listed price on 4 of 11 comparable probes.
Category
Inference by llm, confidence 60%
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
44m ago
Next probe
2026-11-19 01:15 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
82w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
9w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.00750xb36c…54Ebdefaultyes3h ago

Listing changes

WhenEventFromTo
2d agoprice_changed84007500

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 agoInference60%llmv1claude-haiku-5-5: Semantic content moderation returning per-category scores and allow/review/block verdicts relies on an AI model judging text, which best fits model output; it is not a word list or a compliance, signal, or web_scrape service. Could arguably fit compliance, but inference is closer to what the caller receives.
46h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
44m agofree4021028 msv2yes$0.00730xb36c…54Ebprice_below_listingprice_mismatchprice_changed
8h agofree4021233 msv2yes$0.00750xb36c…54Eb—
14h agofree402521 msv2yes$0.00750xb36c…54Eb—
21h agofree402482 msv2yes$0.00750xb36c…54Ebprice_changed
27h agofree4021320 msv2yes$0.00740xb36c…54Ebprice_below_listingprice_mismatchprice_changed
34h agofree4021260 msv2yes$0.00750xb36c…54Eb—
40h agofree4021235 msv2yes$0.00750xb36c…54Ebprice_changed
46h agofree4021083 msv2yes$0.00760xb36c…54Ebprice_above_listingprice_mismatchprice_changed
2d agofree402641 msv2yes$0.00750xb36c…54Eb—
2d agofree402523 msv2yes$0.00750xb36c…54Ebprice_changed
3d agofree402545 msv2yes$0.00760xb36c…54Ebprice_below_listingprice_mismatch