# Evaluation Run Imports — Numeric Type Check

> Evaluation Run Imports — Numeric Type Check is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-15).

Validates that all numeric columns in an evaluation run CSV conform to expected numeric types, ranges, and category constraints, returning a type-check report.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-bx-csv-evaluations-types?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/evaluation-run-imports-numeric-type-check-70e57b5f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_IK747tdnGEAAGkliyd8bW

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 evaluation-run-imports-numeric-type-check-70e57b5f -d '<json body>'
```

Example prompt: Check the numeric types in my evaluation run CSV — it has columns evaluation_id, evaluated_on, dataset_id, correct_count, and example_count — make sure the numeric columns are valid, values are between 0 and 1000, and the allowed category values are group-a and group-b.

## When to prefer this

Choose this endpoint when you need to validate numeric column types and value ranges in an evaluation run CSV before import, particularly when your data follows the evaluation_id/evaluated_on/dataset_id/correct_count/example_count schema pattern. It is purpose-built for evaluation run import contracts, supports quoted cells, configurable delimiters, category allowlists, and min/max range bounds — making it ideal as a lightweight, low-cost data quality gate in ML evaluation pipelines.

## Known failure modes

- CSV exceeds 100,000 character limit — request rejected
- More than 1000 rows submitted — only first 1000 may be evaluated
- Invalid delimiter specified — must be comma, semicolon, or tab
- Minimum value exceeds maximum value — configuration error
- Cell length exceeds max_cell_length limit — cell flagged or rejected
- Malformed CSV structure — unparseable rows cause partial or failed report
- Empty CSV submitted — validation cannot proceed

## How this service works

Evaluation run imports — Numeric type check: Numeric type check for Evaluation run imports. Validate a declared CSV table contract, up to 1000 rows. Quoted cells supported; no external enrichment. Specialised preset in a shared 50-profile, 20-operation engine. 0.01 USDC includes one CSV numeric type check report.

## Output

A numeric type check report covering up to 1000 rows of the submitted CSV, identifying which cells or columns fail numeric type expectations, fall outside the specified min/max range, exceed cell length limits, or contain disallowed category values. The report is scoped to numeric column validation only and does not perform external data enrichment.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "csv": {
   "type": "string",
   "default": "evaluation_id,evaluated_on,dataset_id,correct_count,example_count\nrecord-a,2026-01-01,group-a,10,2\nrecord-b,2026-01-02,group-b,20,3",
   "maxLength": 100000,
   "minLength": 1
  },
  "maximum": {
   "type": "number",
   "default": 1000000000000,
   "maximum": 1000000000000,
   "minimum": -1000000000000
  },
  "minimum": {
   "type": "number",
   "default": -1000000000000,
   "maximum": 1000000000000,
   "minimum": -1000000000000
  },
  "delimiter": {
   "enum": [
    ",",
    ";",
    "\t"
   ],
   "type": "string",
   "default": ","
  },
  "max_cell_length": {
   "type": "integer",
   "default": 1000,
   "maximum": 5000,
   "minimum": 1
  },
  "allowed_categories": {
   "type": "array",
   "items": {
    "type": "string",
    "default": "",
    "maxLength": 100,
    "minLength": 1
   },
   "default": [
    "group-a",
    "group-b"
   ],
   "maxItems": 100,
   "minItems": 0
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/evaluation-run-imports-numeric-type-check-70e57b5f/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)