Paywary

Leaderboard / api.craigmbrown.com / endpoint

POST https://api.craigmbrown.com/v1/services/bundle.reputation-badge

Scores measure reliability and honesty, not output quality.

70Cautionconfidence: medium
  • Answered 6 of 8 probes in the last 7 days (75%).
  • Answered 6 of 8 probes in the last 30 days (75%).
Category
Signal by llm, confidence 45%
Latest quote
$0.018 on Base to 0x5E70…4EB9
Uptime
75% / 7d, 75% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
36m ago
Next probe
2026-11-18 18:05 UTC

Score components

Uptime, 7 days
35w 15%
Uptime, 30 days
35w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
8w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexacteip155:50420x3600…0000180000x5E70…4EB9defaultyes1h ago
cdpexactPolygon0x3c49…3359180000x5E70…4EB9defaultyes1h ago
cdpexactBase0x8335…2913$0.0180x5E70…4EB9defaultyes1h 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
23h agoSignal45%llmv1claude-haiku-5-5: The endpoint looks up an agent's track record and publishes a trust badge, which is a counterparty-risk verdict rather than a clean fit for a listed category. Signal (risk verdicts) is the closest match, though the description is partly promotional and the output is a reputation record, so confidence is moderate.
39h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
36m agofree402124 msv2yes$0.0180x5E70…4EB9—
7h agofree40293 msv2yes$0.0180x5E70…4EB9—
19h agofreetimeout15008 ms————no_responsefetch_error:timeout
26h agofree402175 msv2yes$0.0180x5E70…4EB9—
32h agofree402261 msv2yes$0.0180x5E70…4EB9—
44h agofreetimeout15000 ms————no_responsefetch_error:timeout
2d agofree402103 msv2yes$0.0180x5E70…4EB9—
2d agofree402118 msv2yes$0.0180x5E70…4EB9—