{"id":"paperContradictions","title":"Paper Contradiction Finder","description":"Takes 2 to 4 papers (DOI, arXiv id, PMID or their URLs) on a shared question and answers whether their reported numbers conflict: a verdict (CONTRADICTION_FOUND / NO_CONTRADICTION_FOUND / INCONCLUSIVE) with confidence, a one-line headline, the decisive quotes side by side and a next step, then the full evidence. Fetches the best available text (ar5iv, Europe PMC full text, else abstract), extracts quantitative claims with exact quote spans (hazard/odds/risk ratios, relative changes, differences, confidence intervals, P-values, sample sizes, units), pairs claims by shared outcome vocabulary (at most 24 pairs), and tests each pair the model confirms as the same quantity in comparable populations: opposite directions, non-overlapping intervals, the difference test from CI-derived standard errors, and a significant-versus-powered-null check, after unit normalization. Classifies each pair CONTRADICTS / CONSISTENT / DIFFERENT_POPULATIONS_OR_MEASURES / INSUFFICIENT_INFO and reports a per-paper trust summary (retraction and correction status, replication signals, sample size, preregistration, funding and conflict statements, how often the paper is contradicted) by a documented formula. Author-prestige metrics are excluded on purpose. mode \"fast\" makes no model call and tests only identical outcome phrases. If a paper cannot be found or an upstream lookup fails, the result is returned marked partial with the gaps named; abstract-only papers lower the stated confidence. A screening aid for reading, not a systematic review; CONTRADICTS does not say which paper is right.","roi":"Shows a buyer exactly which published numbers disagree across papers, with quote spans and the statistics behind each verdict, instead of an LLM's impression of consensus.","audience":"research","channels":["x402","mcp","rapidapi","apify"],"endpoint":{"method":"POST","url":"https://agents.writerslogic.com/api/v1/find-contradictions","path":"/api/v1/find-contradictions","contentType":"application/json"},"price":{"amount":"1.00","currency":"USDC","network":"base","perCall":true,"failedCallsCharged":false},"inputSchema":{"type":"object","additionalProperties":false,"required":["papers"],"properties":{"papers":{"type":"array","minItems":2,"maxItems":4,"items":{"type":"string","minLength":3,"maxLength":300},"description":"2 to 4 papers on a shared question, each a DOI (bare, doi: or doi.org URL), an arXiv id or arxiv.org URL, or a PMID (bare, PMID:n, or a pubmed.ncbi.nlm.nih.gov or europepmc.org URL)."},"claim":{"type":"string","minLength":3,"maxLength":2000,"description":"Optional claim or question to focus on; claims about it are paired first."},"mode":{"type":"string","enum":["full","fast"],"description":"full (default): one model call judges whether candidate claim pairs measure the same quantity in comparable populations. fast: no model call; only pairs with identical normalized outcome phrases are tested."}}},"resultSchema":{"type":"object","properties":{"verdict":{"type":"string","enum":["CONTRADICTION_FOUND","NO_CONTRADICTION_FOUND","INCONCLUSIVE"],"description":"Headline result across all tested pairs: CONTRADICTION_FOUND, NO_CONTRADICTION_FOUND (some pairs tested and consistent), or INCONCLUSIVE (nothing could be tested as the same quantity; not evidence of agreement)."},"confidence":{"type":"integer","description":"0-100, by the documented rule in confidenceBasis."},"headline":{"type":"string","description":"One sentence naming the papers and the kind of conflict; read this first."},"humanSummary":{"type":"string","description":"The decisive quotes side by side, the difference-test p-value, and what was not counted. (summary holds the pair counts.)"},"nextStep":{"type":"string","description":"The single most useful action for the buyer."},"topFindings":{"type":"array","items":{"type":"object","description":"pairId, kind, decidedBy, the two papers with the quote from each, and the difference test (z, p) when applicable."},"description":"Up to 3 most decisive contradictions, model-confirmed ones first."},"partial":{"type":"boolean","description":"True when a paper was not found, the model call failed, or upstream lookups were skipped or rate-limited; the result is still signed and missing says what was not seen."},"missing":{"type":"array","items":{"type":"string"}},"confidenceBasis":{"type":"string"},"mode":{"type":"string","enum":["full","fast"]},"deterministic":{"type":"boolean","description":"True when no model call was made."},"llmCalls":{"type":"integer","description":"0 in fast mode or when no candidate pairs exist; otherwise 1."},"decidedBy":{"type":"object","description":"Pairs by what decided them: code (identical outcome phrase, statistics), llm (model said not the same quantity), llm+code (model said same, code ran the tests), none (undecided)."},"degraded":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Set when the model call failed and only identical-outcome pairs were tested."},"focus":{"anyOf":[{"type":"string"},{"type":"null"}]},"summary":{"type":"object","description":"Pair counts per classification (CONTRADICTS, CONSISTENT, DIFFERENT_POPULATIONS_OR_MEASURES, INSUFFICIENT_INFO) and pairsTested."},"papers":{"type":"array","items":{"type":"object"},"description":"Per paper: resolved metadata, text level, integrity (retraction, correction), replication signals, sample size, preregistration, funding and conflict-of-interest cues with quotes, and the trust summary."},"claims":{"type":"array","items":{"type":"object"},"description":"Quantitative claims with exact quote spans (offsets into the paper text), measure, value, confidence interval, P, unit, direction word and normalized outcome phrase."},"pairs":{"type":"array","items":{"type":"object"},"description":"Candidate claim pairs with classification, contradiction kind, the statistical tests with details, who decided, and the verified model quotes."},"trustMethod":{"type":"object","description":"Trust formula, weights, and the author-prestige metrics excluded on purpose."},"coverage":{"type":"object","description":"Counts, caps, upstream call budget, elapsed time and failed sources."},"caveats":{"type":"array","items":{"type":"string"}}}},"outputSchema":{"type":"object","properties":{"data":{"type":"object","properties":{"verdict":{"type":"string","enum":["CONTRADICTION_FOUND","NO_CONTRADICTION_FOUND","INCONCLUSIVE"],"description":"Headline result across all tested pairs: CONTRADICTION_FOUND, NO_CONTRADICTION_FOUND (some pairs tested and consistent), or INCONCLUSIVE (nothing could be tested as the same quantity; not evidence of agreement)."},"confidence":{"type":"integer","description":"0-100, by the documented rule in confidenceBasis."},"headline":{"type":"string","description":"One sentence naming the papers and the kind of conflict; read this first."},"humanSummary":{"type":"string","description":"The decisive quotes side by side, the difference-test p-value, and what was not counted. (summary holds the pair counts.)"},"nextStep":{"type":"string","description":"The single most useful action for the buyer."},"topFindings":{"type":"array","items":{"type":"object","description":"pairId, kind, decidedBy, the two papers with the quote from each, and the difference test (z, p) when applicable."},"description":"Up to 3 most decisive contradictions, model-confirmed ones first."},"partial":{"type":"boolean","description":"True when a paper was not found, the model call failed, or upstream lookups were skipped or rate-limited; the result is still signed and missing says what was not seen."},"missing":{"type":"array","items":{"type":"string"}},"confidenceBasis":{"type":"string"},"mode":{"type":"string","enum":["full","fast"]},"deterministic":{"type":"boolean","description":"True when no model call was made."},"llmCalls":{"type":"integer","description":"0 in fast mode or when no candidate pairs exist; otherwise 1."},"decidedBy":{"type":"object","description":"Pairs by what decided them: code (identical outcome phrase, statistics), llm (model said not the same quantity), llm+code (model said same, code ran the tests), none (undecided)."},"degraded":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Set when the model call failed and only identical-outcome pairs were tested."},"focus":{"anyOf":[{"type":"string"},{"type":"null"}]},"summary":{"type":"object","description":"Pair counts per classification (CONTRADICTS, CONSISTENT, DIFFERENT_POPULATIONS_OR_MEASURES, INSUFFICIENT_INFO) and pairsTested."},"papers":{"type":"array","items":{"type":"object"},"description":"Per paper: resolved metadata, text level, integrity (retraction, correction), replication signals, sample size, preregistration, funding and conflict-of-interest cues with quotes, and the trust summary."},"claims":{"type":"array","items":{"type":"object"},"description":"Quantitative claims with exact quote spans (offsets into the paper text), measure, value, confidence interval, P, unit, direction word and normalized outcome phrase."},"pairs":{"type":"array","items":{"type":"object"},"description":"Candidate claim pairs with classification, contradiction kind, the statistical tests with details, who decided, and the verified model quotes."},"trustMethod":{"type":"object","description":"Trust formula, weights, and the author-prestige metrics excluded on purpose."},"coverage":{"type":"object","description":"Counts, caps, upstream call budget, elapsed time and failed sources."},"caveats":{"type":"array","items":{"type":"string"}}}},"_provenance":{"type":"object","description":"C2PA-aligned manifest and W3C VC 2.0 (eddsa-jcs-2022) issued by the hub DID; verify at POST /api/v1/verify-provenance"}},"required":["data","_provenance"]},"example":{"papers":["10.1056/NEJM199608153350701","10.1001/jama.288.3.321"],"claim":"Does postmenopausal estrogen plus progestin therapy reduce coronary heart disease risk?","mode":"full"},"openapiOperation":{"operationId":"paperContradictions","summary":"Paper Contradiction Finder","description":"Takes 2 to 4 papers (DOI, arXiv id, PMID or their URLs) on a shared question and answers whether their reported numbers conflict: a verdict (CONTRADICTION_FOUND / NO_CONTRADICTION_FOUND / INCONCLUSIVE) with confidence, a one-line headline, the decisive quotes side by side and a next step, then the full evidence. Fetches the best available text (ar5iv, Europe PMC full text, else abstract), extracts quantitative claims with exact quote spans (hazard/odds/risk ratios, relative changes, differences, confidence intervals, P-values, sample sizes, units), pairs claims by shared outcome vocabulary (at most 24 pairs), and tests each pair the model confirms as the same quantity in comparable populations: opposite directions, non-overlapping intervals, the difference test from CI-derived standard errors, and a significant-versus-powered-null check, after unit normalization. Classifies each pair CONTRADICTS / CONSISTENT / DIFFERENT_POPULATIONS_OR_MEASURES / INSUFFICIENT_INFO and reports a per-paper trust summary (retraction and correction status, replication signals, sample size, preregistration, funding and conflict statements, how often the paper is contradicted) by a documented formula. Author-prestige metrics are excluded on purpose. mode \"fast\" makes no model call and tests only identical outcome phrases. If a paper cannot be found or an upstream lookup fails, the result is returned marked partial with the gaps named; abstract-only papers lower the stated confidence. A screening aid for reading, not a systematic review; CONTRADICTS does not say which paper is right.\n\nPrice: 1.00 USDC on Base (x402).","x-x402-price-usdc":"1.00","x-x402-amount":"1000000","x-payment-info":{"protocols":["x402"],"price":{"mode":"fixed","currency":"USD","amount":"1.00"}},"x-audience":"research","x-sample-url":"https://agents.writerslogic.com/api/v1/samples/paperContradictions","security":[{"x402":[]},{"apiKey":[]}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","additionalProperties":false,"required":["papers"],"properties":{"papers":{"type":"array","minItems":2,"maxItems":4,"items":{"type":"string","minLength":3,"maxLength":300},"description":"2 to 4 papers on a shared question, each a DOI (bare, doi: or doi.org URL), an arXiv id or arxiv.org URL, or a PMID (bare, PMID:n, or a pubmed.ncbi.nlm.nih.gov or europepmc.org URL)."},"claim":{"type":"string","minLength":3,"maxLength":2000,"description":"Optional claim or question to focus on; claims about it are paired first."},"mode":{"type":"string","enum":["full","fast"],"description":"full (default): one model call judges whether candidate claim pairs measure the same quantity in comparable populations. fast: no model call; only pairs with identical normalized outcome phrases are tested."}}},"example":{"papers":["10.1056/NEJM199608153350701","10.1001/jama.288.3.321"],"claim":"Does postmenopausal estrogen plus progestin therapy reduce coronary heart disease risk?","mode":"full"}}}},"responses":{"200":{"description":"Paid result with provenance","content":{"application/json":{"schema":{"type":"object","properties":{"data":{"type":"object","properties":{"verdict":{"type":"string","enum":["CONTRADICTION_FOUND","NO_CONTRADICTION_FOUND","INCONCLUSIVE"],"description":"Headline result across all tested pairs: CONTRADICTION_FOUND, NO_CONTRADICTION_FOUND (some pairs tested and consistent), or INCONCLUSIVE (nothing could be tested as the same quantity; not evidence of agreement)."},"confidence":{"type":"integer","description":"0-100, by the documented rule in confidenceBasis."},"headline":{"type":"string","description":"One sentence naming the papers and the kind of conflict; read this first."},"humanSummary":{"type":"string","description":"The decisive quotes side by side, the difference-test p-value, and what was not counted. (summary holds the pair counts.)"},"nextStep":{"type":"string","description":"The single most useful action for the buyer."},"topFindings":{"type":"array","items":{"type":"object","description":"pairId, kind, decidedBy, the two papers with the quote from each, and the difference test (z, p) when applicable."},"description":"Up to 3 most decisive contradictions, model-confirmed ones first."},"partial":{"type":"boolean","description":"True when a paper was not found, the model call failed, or upstream lookups were skipped or rate-limited; the result is still signed and missing says what was not seen."},"missing":{"type":"array","items":{"type":"string"}},"confidenceBasis":{"type":"string"},"mode":{"type":"string","enum":["full","fast"]},"deterministic":{"type":"boolean","description":"True when no model call was made."},"llmCalls":{"type":"integer","description":"0 in fast mode or when no candidate pairs exist; otherwise 1."},"decidedBy":{"type":"object","description":"Pairs by what decided them: code (identical outcome phrase, statistics), llm (model said not the same quantity), llm+code (model said same, code ran the tests), none (undecided)."},"degraded":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"Set when the model call failed and only identical-outcome pairs were tested."},"focus":{"anyOf":[{"type":"string"},{"type":"null"}]},"summary":{"type":"object","description":"Pair counts per classification (CONTRADICTS, CONSISTENT, DIFFERENT_POPULATIONS_OR_MEASURES, INSUFFICIENT_INFO) and pairsTested."},"papers":{"type":"array","items":{"type":"object"},"description":"Per paper: resolved metadata, text level, integrity (retraction, correction), replication signals, sample size, preregistration, funding and conflict-of-interest cues with quotes, and the trust summary."},"claims":{"type":"array","items":{"type":"object"},"description":"Quantitative claims with exact quote spans (offsets into the paper text), measure, value, confidence interval, P, unit, direction word and normalized outcome phrase."},"pairs":{"type":"array","items":{"type":"object"},"description":"Candidate claim pairs with classification, contradiction kind, the statistical tests with details, who decided, and the verified model quotes."},"trustMethod":{"type":"object","description":"Trust formula, weights, and the author-prestige metrics excluded on purpose."},"coverage":{"type":"object","description":"Counts, caps, upstream call budget, elapsed time and failed sources."},"caveats":{"type":"array","items":{"type":"string"}}}},"_provenance":{"type":"object","description":"C2PA-aligned manifest and W3C VC 2.0 (eddsa-jcs-2022) issued by the hub DID; verify at POST /api/v1/verify-provenance"}},"required":["data","_provenance"]}}}},"400":{"description":"Invalid request (no payment consumed)","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"string"},"code":{"type":"string"}}}}}},"401":{"description":"Invalid X-API-KEY","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"string"},"code":{"type":"string"}}}}}},"402":{"description":"Payment required or invalid","content":{"application/json":{"schema":{"type":"object","description":"x402 v2 PaymentRequired (also base64 in the PAYMENT-REQUIRED header)","properties":{"x402Version":{"type":"integer"},"error":{"type":"string"},"code":{"type":"string"},"resource":{"type":"object"},"accepts":{"type":"array","items":{"type":"object"}},"extensions":{"type":"object"}}}}}},"502":{"description":"Upstream failure; the payment is released or not settled","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"string"},"code":{"type":"string"}}}}}}}},"links":{"docs":"https://agents.writerslogic.com/docs/paperContradictions/","docsJson":"https://agents.writerslogic.com/docs/paperContradictions.json","sample":"https://agents.writerslogic.com/api/v1/samples/paperContradictions","openapi":"https://agents.writerslogic.com/openapi.json","catalog":"https://agents.writerslogic.com/api/v1/catalog","verifyProvenance":"https://agents.writerslogic.com/api/v1/verify-provenance","index":"https://agents.writerslogic.com/docs/index.json"}}