{"uid":"cap_ylTlonLFuaglz4KrZsFhy","slug":"shelf-thirdmade-net-hallucination-check-09f2fb06","name":"shelf.thirdmade.net Hallucination Check","description":"Entailment scoring: does the provided context support this claim? Research agents use this to self-check outputs.","url":"https://shelf.thirdmade.net/probe/hallucination-check","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["context","claim"],"properties":{"claim":{"type":"string","description":"Claim to check"},"context":{"type":"string","description":"Evidence/context text"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_rG7mBH-RaO2s88CygYvSH","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Scores whether a provided context passage entails or supports a given claim, helping research agents self-verify their outputs.","exampleAgentPrompt":"Check whether this passage — 'Aspirin was first synthesized in 1897 by Felix Hoffmann at Bayer' — actually supports the claim 'Aspirin was invented in the 19th century by a German chemist.'","exampleUseCases":[{"title":"Research agent output self-check","prompt":"Before I send this research report, check whether the source paragraph I pulled actually supports the claim I'm making: context is 'The Amazon rainforest absorbs approximately 2 billion tons of CO2 per year', and the claim is 'The Amazon is the world's largest carbon sink.'"},{"title":"RAG pipeline grounding verification","prompt":"I generated an answer from my retrieved documents — can you check if the context 'Elon Musk founded SpaceX in 2002' actually entails the claim 'SpaceX was founded by Elon Musk in the early 2000s'? I want a hallucination score before I return it to the user."},{"title":"Fact-check AI-written summary","prompt":"My AI just summarized an article and wrote 'The study found that coffee reduces Alzheimer's risk by 30%'. The original text says 'A new study suggests moderate coffee consumption may be associated with a lower risk of cognitive decline.' Does the context actually support that claim?"}],"resultDescription":"Returns an entailment score indicating how strongly the provided context passage supports the given claim, allowing agents to quantify whether their outputs are grounded in evidence or potentially hallucinated.","failureModes":["Missing 'context' or 'claim' query parameter returns a 400 error","Very long context or claim strings may be truncated or rejected","Ambiguous or semantically empty claims may produce low-confidence mid-range scores","Payment failure (x402) if USDC balance is insufficient","Service unavailability returns 5xx if GPU/model backend is down"],"whenToPreferThis":"Choose this endpoint when you need a lightweight, per-claim entailment check to verify that agent-generated text is grounded in retrieved context — especially in RAG pipelines, research automation, or any workflow where hallucination risk must be bounded before output is surfaced to users. Prefer this over general-purpose LLM self-critique when you need a deterministic, scoreable signal rather than a free-text explanation.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:33:08.506Z","isFirstParty":false}