Paywary

Leaderboard / agent.pocket.network / endpoint

POST https://agent.pocket.network/v1/pii-redaction

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
Data transform by llm, confidence 72%
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
2h ago
Next probe
2026-11-19 01:06 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
cdpexactBase0x8335…2913$0.0050xF732…B829defaultyes3h 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
44h agoData transform72%llmv1claude-haiku-5-5: The endpoint takes text and returns a deterministic masked version plus findings, which is a text transform rather than a model output or compliance check. The description says it is deterministic per ruleset, and the tags point to security, so confidence is moderate.
47h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
2h agofree402157 msv2yes$0.0050xF732…B829—
9h agofree402164 msv2yes$0.0050xF732…B829—
15h agofree402162 msv2yes$0.0050xF732…B829—
21h agofree402162 msv2yes$0.0050xF732…B829—
28h agofree402176 msv2yes$0.0050xF732…B829—
34h agofree402164 msv2yes$0.0050xF732…B829—
41h agofree402720 msv2yes$0.0050xF732…B829—
47h agofree402167 msv2yes$0.0050xF732…B829—
2d agofree402166 msv2yes$0.0050xF732…B829—
2d agofree402158 msv2yes$0.0050xF732…B829—
3d agofree402155 msv2yes$0.0050xF732…B829—