# Classification Model Audit

> Classification Model Audit is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-10).

Computes confusion matrix, per-label precision/recall/F1, macro F1, and accuracy from up to 300 supplied expected/predicted label pairs

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-classification-audit?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/classification-model-audit-ef52af42
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RNRhbrnsl-LUqdwJTmqE9

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 classification-model-audit-ef52af42 -d '<json body>'
```

Example prompt: Can you audit these 200 classifier predictions for me? I have a list of expected vs predicted labels — I need the confusion matrix, per-label precision, recall, and F1, plus the overall macro F1 and accuracy.

## When to prefer this

Choose this endpoint when you have a fixed set of up to 300 ground-truth and predicted label pairs and need standard classification metrics (confusion matrix, per-label precision/recall/F1, macro F1, accuracy) computed quickly and cheaply without spinning up any model infrastructure. It is ideal for post-hoc model auditing, CI/CD quality gates, or reporting workflows where you already have predictions in hand.

## Known failure modes

- Empty or missing examples array returns a validation error
- More than 300 label pairs submitted exceeds the limit and is rejected
- Labels with empty strings or exceeding 40 characters fail schema validation
- Mismatched or malformed JSON body returns a 400 error
- Network or payment (x402) failure prevents the call from completing

## How this service works

Classification Model Audit: Compute a confusion matrix, per-label precision/recall/F1, macro F1 and accuracy from up to 300 supplied expected/predicted labels. No model calls or claims about unseen data. 0.01 USDC includes up to 300 labelled predictions.

## Output

Returns a confusion matrix showing true/false positives and negatives per class, per-label precision, recall, and F1 scores, as well as overall macro F1 and accuracy — all computed from the supplied expected/predicted label pairs without making any model calls.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "examples": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "expected",
     "predicted"
    ],
    "properties": {
     "expected": {
      "type": "string",
      "maxLength": 40,
      "minLength": 1
     },
     "predicted": {
      "type": "string",
      "maxLength": 40,
      "minLength": 1
     }
    },
    "additionalProperties": false
   },
   "default": [
    {
     "expected": "positive",
     "predicted": "positive"
    },
    {
     "expected": "negative",
     "predicted": "positive"
    }
   ],
   "maxItems": 300,
   "minItems": 1
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/classification-model-audit-ef52af42/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)