# Maha Evidence Retention Matrix

> Maha Evidence Retention Matrix is a paid API for AI agents from www.mahastrategies.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-14).

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.

## Facts

- Endpoint: POST https://www.mahastrategies.com/api/v1/context/evidence-matrix
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/maha-evidence-retention-matrix-fb87e616
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0lV5a0kYMnR2wTUcr6S4O

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability maha-evidence-retention-matrix-fb87e616 -d '<json body>'
```

Example prompt: 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'.

## When to prefer this

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.

## Known failure modes

- 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

## How this service works

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.

## Output

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.

## Request schema (JSON Schema)

```json
{
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "type": "string",
     "enum": [
      "POST"
     ]
    },
    "bodyType": {
     "type": "string",
     "enum": [
      "json",
      "form-data",
      "text"
     ]
    },
    "body": {
     "type": "object",
     "additionalProperties": false,
     "properties": {
      "clientRequestId": {
       "type": "string",
       "minLength": 8,
       "maxLength": 120
      },
      "task": {
       "type": "string",
       "minLength": 8,
       "maxLength": 1200
      },
      "documents": {
       "type": "array",
       "minItems": 1,
       "maxItems": 8
      },
      "provenance": {
       "type": "string",
       "enum": [
        "full",
        "compact",
        "none"
       ]
      },
      "scoring": {
       "type": "string",
       "enum": [
        "bm25",
        "keyword"
       ]
      },
      "budgetMode": {
       "type": "string",
       "enum": [
        "guaranteed",
        "estimated"
       ]
      },
      "tokenBudgets": {
       "type": "array",
       "minItems": 1,
       "maxItems": 5
      },
      "requiredEvidence": {
       "type": "array",
       "minItems": 1,
       "maxItems": 32
      }
     },
     "required": [
      "clientRequestId",
      "task",
      "tokenBudgets",
      "documents",
      "requiredEvidence"
     ]
    }
   },
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "additionalProperties": false,
     "properties": {
      "version": {
       "type": "string",
       "const": "0.1"
      },
      "offerId": {
       "type": "string",
       "const": "evidence-retention-matrix"
      },
      "clientRequestId": {
       "type": "string"
      },
      "inputDigest": {
       "type": "string"
      },
      "economicBasis": {
       "type": "object"
      },
      "runs": {
       "type": "array",
       "minItems": 1,
       "maxItems": 5
      },
      "evidenceFrontier": {
       "type": "array"
      },
      "boundaries": {
       "type": "array"
      },
      "sourceTextStored": {
       "type": "boolean",
       "const": false
      },
      "compiledContex
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/maha-evidence-retention-matrix-fb87e616/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from www.mahastrategies.com](https://www.zero.xyz/host/www.mahastrategies.com/llms.txt)