# Data Reconciliation — Record Quality Audit + String Normalisation + IQR Outlier Flags

> Data Reconciliation — Record Quality Audit + String Normalisation + IQR Outlier Flags is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-19).

Runs three analytical reports on supplied reconciliation data (source_total vs target_total): a record quality audit, string normalisation, and IQR-based outlier flagging — all locally, without external lookups.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-ib26-analytics-11-203?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/data-reconciliation-record-quality-audit-string-normalisation-iqr-296e7f6b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FNo1I12U2LWv5D7xqoqHF

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 data-reconciliation-record-quality-audit-string-normalisation-iqr-296e7f6b -d '<json body>'
```

Example prompt: Can you audit this batch of reconciliation records for quality issues, normalise the string fields, and flag any IQR outliers in the source_total column? I have up to 150 rows with row IDs, dates, dataset groups, and source/target totals.

## When to prefer this

Choose this endpoint when you need a bundled, low-cost ($0.01 USDC) trio of data quality reports — quality audit, string normalisation, and IQR outlier detection — applied to reconciliation data in a single call, without needing external data sources, live lookups, or ML predictions. Ideal for ETL validation, financial reconciliation checks, and batch data cleaning where up to 200 rows must be assessed quickly and cheaply. Prefer alternatives if you need keyed dataset comparison (a sibling endpoint exists for that), live data enrichment, or more than 200 rows per batch.

## Known failure modes

- Rows array is empty or missing — returns validation error
- More than 200 rows submitted — rejected with max-items error
- date field does not match YYYY-MM-DD pattern — schema validation failure
- source_total or target_total outside ±1,000,000,000,000 range — rejected
- Invalid field enum value (not 'source_total' or 'target_total') — schema error
- Too few rows to compute meaningful IQR — outlier report may be trivial or empty

## How this service works

Data reconciliation — Record quality audit + String normalisation + IQR outlier flags: Record quality audit + String normalisation + IQR outlier flags for supplied data reconciliation records (source_total, target_total). Up to 200 rows; 3 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 3 supplied-data reports for up to 200 rows.

## Output

Three independent analytical reports covering: (1) a record quality audit identifying missing, malformed, or inconsistent fields; (2) string normalisation output for text fields like dataset_group; and (3) IQR-based outlier flags identifying statistically anomalous rows in the selected numeric field (source_total or target_total). All analysis is performed locally on the supplied data with no external lookups.

## Request schema (JSON Schema)

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/data-reconciliation-record-quality-audit-string-normalisation-iqr-296e7f6b/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)