# Paper Cluster Retrieval Comparison

> Paper Cluster Retrieval Comparison is a paid API for AI agents from www.mahastrategies.com, paid per call via x402, $0.144/call, status unknown (last checked 2026-10-20).

Compares paired frozen-cohort recovery vs. seeded whole-paper cluster resampling across 100–2000 bootstrap replicates to report a descriptive percentile interval for question-weighted complete-recovery delta.

## Facts

- Endpoint: POST https://www.mahastrategies.com/api/v1/micro/paper-cluster-retrieval-comparison?utm_source=zero.xyz
- Price: $0.144/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/paper-cluster-retrieval-comparison-c7a7a4d0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_eHZif9_Czxpo0sw1swGgg

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 paper-cluster-retrieval-comparison-c7a7a4d0 -d '<json body>'
```

Example prompt: Compare my baseline and candidate retrieval configs on papers [paper-001, paper-002, paper-003] with 500 resamples using seed 42, against a corpus hash of sha256-abc123, treating the data as synthetic — give me the percentile interval for the question-weighted complete-recovery delta across my 10 questions.

## When to prefer this

Choose this endpoint when you need a reproducible, non-parametric descriptive interval comparing two retrieval strategies on a fixed paper cohort — especially when you want cluster-level resampling (whole-paper, not question-level) and no significance testing or population guarantees. Prefer it over parametric tests when you want a purely descriptive bootstrap interval, and over question-level bootstraps when you want variance estimates that respect paper-level clustering.

## Known failure modes

- Invalid or missing required fields (e.g. missing paperIds, questions, or seed) returns a validation error
- resamples value outside 100–2000 range is rejected
- paperIds or evidence arrays exceeding 64 items are rejected
- corpusHash exceeding 71 characters is rejected
- dataClass not set to 'public' or 'synthetic' is rejected
- Mismatched evidence and paperIds counts may produce unexpected results
- Network or payment failure may prevent the call from completing

## How this service works

Compare paired frozen-cohort recovery with seeded whole-paper cluster resampling (100–2000 replicates, 2–64 papers, 64 questions). Report a descriptive percentile interval for question-weighted complete-recovery delta. No question-level bootstrap, significance test, or population guarantee.

## Output

Returns a structured result object with a version identifier, offer ID, input digest, receipt digest, a boundaries array (up to 128 percentile boundary values), and a result object containing the descriptive percentile interval for the question-weighted complete-recovery delta between the baseline and candidate retrieval configurations. No significance test or population-level guarantee is provided.

## Request schema (JSON Schema)

```json
{
 "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": [
      "dataClass",
      "corpusHash",
      "paperIds",
      "evidence",
      "questions",
      "baseline",
      "candidate",
      "seed",
      "resamples"
     ],
     "properties": {
      "seed": {
       "type": "integer",
       "maximum": 4294967295,
       "minimum": 0
      },
      "baseline": {
       "type": "object"
      },
      "evidence": {
       "type": "array",
       "maxItems": 64,
       "minItems": 1
      },
      "paperIds": {
       "type": "array",
       "maxItems": 64,
       "minItems": 1
      },
      "candidate": {
       "type": "object"
      },
      "dataClass": {
       "enum": [
        "public",
        "synthetic"
       ],
       "type": "string"
      },
      "questions": {
       "type": "array",
       "maxItems": 64,
       "minItems": 1
      },
      "resamples": {
       "type": "integer",
       "maximum": 2000,
       "minimum": 100
      },
      "corpusHash": {
       "type": "string",
       "maxLength": 71
      }
     },
     "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",
      "amountBaseUnits",
      "inputDigest",
      "result",
      "boundaries",
      "receiptDigest"
     ],
     "properties": {
      "result": {
       "type": "object"
      },
      "offerId": {
       "enum": [
        "paper-cluster-retrieval-comparison"
       ],
       "type": "string"
      },
      "version": {
       "enum": [
        "maha-microproducts/0.1"
       ],
       "type": "string"
      },
      "boundaries": {
       "type": "array",
       "maxItems": 128,
       "minItems": 0
      },
      "inputDigest": {
       "type": "string",
       "maxLength": 71
      },
      "receiptDige
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/paper-cluster-retrieval-comparison-c7a7a4d0/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)