{"uid":"cap_0lV5a0kYMnR2wTUcr6S4O","slug":"maha-evidence-retention-matrix-fb87e616","name":"Maha Evidence Retention Matrix","description":"Evaluate exact retention of 1-32 caller-labelled evidence spans at exactly five ascending token budgets. Returns five source-linked Context Packs, per-run retention metrics, an evidence frontier, stable hashes, and a deterministic receipt digest. Price basis: five $0.01 evaluations. Retention is not truth, accuracy, answer quality, legal compliance, or hallucination prevention. Bodies are not stored.","url":"https://www.mahastrategies.com/api/v1/context/evidence-matrix","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["clientRequestId","task","tokenBudgets","documents","requiredEvidence"],"properties":{"task":{"type":"string","maxLength":1200,"minLength":8},"scoring":{"enum":["bm25","keyword"],"type":"string"},"documents":{"type":"array","maxItems":8,"minItems":1},"budgetMode":{"enum":["guaranteed","estimated"],"type":"string"},"provenance":{"enum":["full","compact","none"],"type":"string"},"tokenBudgets":{"type":"array","maxItems":5,"minItems":1},"clientRequestId":{"type":"string","maxLength":120,"minLength":8},"requiredEvidence":{"type":"array","maxItems":32,"minItems":1}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["version","offerId","clientRequestId","inputDigest","economicBasis","runs","evidenceFrontier","boundaries","sourceTextStored","compiledContextStored","requiredEvidenceTextStored","receiptDigest"],"properties":{"runs":{"type":"array","maxItems":5,"minItems":1},"offerId":{"type":"string","const":"evidence-retention-matrix"},"version":{"type":"string","const":"0.1"},"boundaries":{"type":"array"},"inputDigest":{"type":"string"},"economicBasis":{"type":"object"},"receiptDigest":{"type":"string"},"clientRequestId":{"type":"string"},"evidenceFrontier":{"type":"array"},"sourceTextStored":{"type":"boolean","const":false},"compiledContextStored":{"type":"boolean","const":false},"requiredEvidenceTextStored":{"type":"boolean","const":false}},"additionalProperties":false}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_XKzstN1S7PvzQPKcJBO3S","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Evaluates exact retention of 1-32 caller-labelled evidence spans across five ascending token budgets, returning per-budget context packs with retention metrics, an evidence frontier, and a deterministic receipt digest.","exampleAgentPrompt":"Run an evidence retention matrix on these 3 research documents — I need to track 8 labelled evidence spans across token budgets of 500, 1000, 2000, 4000, and 8000, for the task 'summarize key clinical findings', request ID 'req-clinical-001'.","exampleUseCases":[{"title":"RAG pipeline token budget selection","prompt":"I have 5 source documents and 12 labelled evidence spans I need to preserve. Can you run a retention matrix across token budgets of 500, 1500, 3000, 6000, and 10000 tokens to find the smallest budget where all evidence survives? Task is 'answer product liability questions', request ID 'req-rag-test-42'."},{"title":"Legal brief compression audit","prompt":"Before I compress this brief, check how well my 20 labelled citations are retained at budgets of 800, 1600, 3200, 6400, and 12800 tokens — task is 'summarize case arguments for appellate review', request ID 'req-legal-brief-99'. I want to see the evidence frontier and per-run metrics."},{"title":"Research summarization quality check","prompt":"I'm summarizing 6 academic papers and I've labelled 15 key evidence spans. Run the evidence retention matrix at 1000, 2000, 4000, 8000, and 16000 tokens for the task 'extract methodology and results findings', request ID 'req-research-sum-7', and tell me which token budget is the evidence frontier."}],"resultDescription":"Returns an array of up to five run objects, each containing a source-linked context pack for that token budget, per-run retention metrics showing how many labelled evidence spans survived, an evidence frontier array identifying the threshold budget, token boundary markers, a stable input digest, and a deterministic receipt digest for verification. No body text is stored server-side.","failureModes":["Missing required fields (clientRequestId, task, tokenBudgets, documents, requiredEvidence) returns 400 validation error","More than 8 documents or more than 32 evidence spans returns schema validation failure","Token budgets array exceeding 5 entries is rejected","Payment not completed via x402 protocol returns 402 Payment Required","Documents or evidence spans that are too short/long may be rejected by schema constraints","Non-deterministic behavior is not expected but edge cases in tokenization may affect boundary placement"],"whenToPreferThis":"Choose this endpoint when you need to systematically evaluate how well specific, caller-labelled evidence spans survive document compression across a range of token budgets — particularly for RAG pipeline tuning, legal or research document auditing, or finding the minimal token budget that preserves all required citations. Prefer this over single-budget context compilation when you need a comparative matrix and an evidence frontier rather than a single compressed output.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:49:25.196Z","isFirstParty":false}