# Document Retrieval Analytics — String Normalisation + Two-Measure Correlation

> Document Retrieval Analytics — String Normalisation + Two-Measure Correlation is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-26).

Normalises strings and computes correlation between retrieved_bytes and request_ms metrics across up to 200 document retrieval records, returning two analytical reports.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-ib26-web-09-033?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-26
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/document-retrieval-analytics-string-normalisation-two-measure-8d4092fa
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_77qYIvANpYJvtcjSpfDK9

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 document-retrieval-analytics-string-normalisation-two-measure-8d4092fa -d '<json body>'
```

Example prompt: I have document retrieval logs with site groups, dates, retrieved_bytes, and request_ms for about 150 rows — can you run string normalisation on the text fields and compute the correlation between retrieved_bytes and request_ms across all records?

## When to prefer this

Choose this endpoint when you have document retrieval log data with byte-size and latency metrics and need both text normalisation of categorical fields and a statistical correlation between the two numeric measures in a single call. It is purpose-built for retrieval telemetry datasets (up to 200 rows) and returns two bundled reports at a low flat cost, making it ideal for lightweight analytical pipelines that don't require live lookups, predictions, or external integrations.

## Known failure modes

- Fewer than 1 row submitted — request rejected
- More than 200 rows submitted — exceeds maxItems limit
- Missing required fields (row_id, site_group, date, retrieved_bytes, request_ms) on any row
- Invalid date format (must match YYYY-MM-DD pattern)
- Numeric values outside allowed range (±1,000,000,000,000)
- Insufficient numeric variance in retrieved_bytes or request_ms to compute meaningful correlation

## How this service works

Document retrieval — String normalisation + Two-measure correlation: String normalisation + Two-measure correlation for supplied document retrieval records (retrieved_bytes, request_ms). Up to 200 rows; 2 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 2 supplied-data reports for up to 200 rows.

## Output

Two analytical reports: (1) a string normalisation report cleaning and standardising text fields such as site_group and row_id, and (2) a two-measure correlation report quantifying the statistical relationship between retrieved_bytes and request_ms across the submitted rows (up to 200). No live data lookup or external action is performed; all analysis runs on the supplied rows only.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "rows": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "row_id",
     "site_group",
     "date",
     "retrieved_bytes",
     "request_ms"
    ],
    "properties": {
     "date": {
      "type": "string",
      "default": "",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "maxLength": 10
     },
     "row_id": {
      "type": "string",
      "default": "",
      "maxLength": 80,
      "minLength": 1
     },
     "request_ms": {
      "type": [
       "number",
       "null"
      ],
      "maximum": 1000000000000,
      "minimum": -1000000000000
     },
     "site_group": {
      "type": "string",
      "default": "",
      "maxLength": 80
     },
     "retrieved_bytes": {
      "type": [
       "number",
       "null"
      ],
      "maximum": 1000000000000,
      "minimum": -1000000000000
     }
    },
    "additionalProperties": false
   },
   "default": [
    {
     "date": "2026-10-01",
     "row_id": "row-1",
     "request_ms": 1,
     "site_group": "group-a",
     "retrieved_bytes": 10
    },
    {
     "date": "2026-10-02",
     "row_id": "row-2",
     "request_ms": 2,
     "site_group": "group-b",
     "retrieved_bytes": 20
    },
    {
     "date": "2026-10-03",
     "row_id": "row-3",
     "request_ms": 3,
     "site_group": "group-a",
     "retrieved_bytes": 15
    },
    {
     "date": "2026-10-04",
     "row_id": "row-4",
     "request_ms": 4,
     "site_group": "group-b",
     "retrieved_bytes": 30
    }
   ],
   "maxItems": 200,
   "minItems": 1
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/document-retrieval-analytics-string-normalisation-two-measure-8d4092fa/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from market.datapackvibe.com](https://www.zero.xyz/host/market.datapackvibe.com/llms.txt)