Paywary

Leaderboard / agents.writerslogic.com / endpoint

POST https://agents.writerslogic.com/api/v1/llm-watermark-detector

Scores measure reliability and honesty, not output quality.

85Payconfidence: medium
  • Listed only 3 days ago; new listings earn trust over 30 days.
  • Answered 10 of 11 probes in the last 7 days (91%).
Category
Inference by llm, confidence 35%
Latest quote
$0.005 on Base to 0x34C2…6522
Uptime
91% / 7d, 91% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
16m ago
Next probe
2026-11-19 16:55 UTC

Score components

Uptime, 7 days
74w 15%
Uptime, 30 days
74w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
11w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
payaiexactBase0x8335…2913$0.0050x34C2…6522eip3009yes5h 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
36h agoInference35%llmv1claude-haiku-5-5: Detects watermark evidence in text via statistical z-test and invisible-character scan; closest fit is analysis, but it is not model output or a signal.
3d agoInference60%rulesv1rule inference matched "paraphrase" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
16m agofree40241 msv2yes$0.0050x34C2…6522—
7h agofree40253 msv2yes$0.0050x34C2…6522—
19h agofreetimeout15001 ms————no_responsefetch_error:timeout
25h agofree40229 msv2yes$0.0050x34C2…6522—
31h agofree40236 msv2yes$0.0050x34C2…6522—
37h agofree4023068 msv2yes$0.0050x34C2…6522—
43h agofree40223 msv2yes$0.0050x34C2…6522—
2d agofree40224 msv2yes$0.0050x34C2…6522—
2d agofree402112 msv2yes$0.0050x34C2…6522—
3d agofree402176 msv2yes$0.0050x34C2…6522—
3d agofree40212 msv2yes$0.0050x34C2…6522—
3d agofree40230 msv2yes$0.0050x34C2…6522—