{"uid":"cap_f13e5Tn9ci6I77MUvEzdg","slug":"verity-suite-arbiter-5d9bd30e","name":"Verity Suite Arbiter","description":"The trust fabric for AI agents — calibrated, fail-closed services agents pay per call.","url":"https://suite.veritylayer.dev/arbiter","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"claims":{"type":"array","items":{"type":"string"},"title":"Claims","description":"Two or more mutually conflicting claims/positions to adjudicate, one per item, in stable order. Fewer than two means nothing to adjudicate."},"evidence":{"type":"array","items":{"type":"string"},"title":"Evidence","description":"Retrieved evidence excerpts/sources to judge from. If empty, weak, or off-topic, the verdict MUST reflect that (insufficient_evidence)."},"question":{"anyOf":[{"type":"string","maxLength":2000},{"type":"null"}],"title":"Question","default":null,"description":"The specific point in dispute the claims are answering, if narrower than the claims themselves. Used to scope relevance only."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.25","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.25/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.25","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_EbBU0B0RXpR-RZeIF6Qq_","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.25","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Adjudicates conflicting claims against provided evidence, returning a calibrated verdict with cited reasons and an optional cryptographic receipt","exampleAgentPrompt":"I have two conflicting claims about whether the 2008 financial crisis was primarily caused by deregulation vs. predatory lending — can you adjudicate them against these three evidence excerpts I retrieved and tell me which claim is best supported, with specific reasons citing the evidence?","exampleUseCases":[{"title":"RAG pipeline conflict resolution","prompt":"My retrieval pipeline pulled back two contradictory statements about whether mRNA vaccines alter DNA — here are the exact excerpts as evidence. Adjudicate the claims and tell me which one the evidence actually supports, citing which excerpts back which claim."},{"title":"Legal brief fact dispute","prompt":"Two legal briefs make opposing claims about whether the defendant was present at the location on March 4th — I have three witness statement excerpts as evidence. Can you arbitrate which claim the evidence supports and flag if the evidence is too weak to decide?"},{"title":"AI agent output verification","prompt":"Two AI agents gave me conflicting answers about the current EU AI Act enforcement date. Here are the source passages they each cited. Run an arbiter check to see which claim is actually supported by the evidence and give me a signed receipt I can log for audit."}],"resultDescription":"Returns a verdict enum (claim_supported, undecidable, or insufficient_evidence), a confidence score, an array of concrete reasons citing specific evidence items by content and claim index, and optionally an Ed25519-signed VerityLayer receipt for audit/verification purposes.","failureModes":["Fewer than two claims provided — nothing to adjudicate","Evidence array empty or off-topic — verdict will be insufficient_evidence","Claims are not genuinely conflicting — may return undecidable","Signing not configured — receipt field returns null","Malformed input schema — 400-level error","Payment not included or insufficient — x402 payment required error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs a calibrated, fail-closed verdict on conflicting claims backed by retrieved evidence, especially when an auditable cryptographic receipt is required. Prefer over general LLM prompting when you need structured verdicts with explicit evidence citations, consistent enum outputs, and tamper-evident receipts for compliance or multi-agent trust pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:47:01.221Z","isFirstParty":false}