# Review Aspect Label and Prediction Audit

> Review Aspect Label and Prediction Audit is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-15).

Audits classifier labels and predictions for review aspect classification (performance, appearance, value, other) across up to 200 labelled text records, computing evaluation metrics using naive-Bayes baselines.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-sector-ml-review-aspect-label-audit?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/review-aspect-label-and-prediction-audit-65799cda
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3sUQgvshaLzoZOZ4EF2LB

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 review-aspect-label-and-prediction-audit-65799cda -d '<json body>'
```

Example prompt: I have 50 labelled product review sentences where each has an actual aspect label (performance, appearance, value, or other), a predicted label from my classifier, and four class probabilities — can you run a label and prediction audit on them to see where my model is going wrong?

## When to prefer this

Choose this endpoint when you need a fast, low-cost ($0.01) audit of a review aspect classifier's label quality and prediction accuracy on a small labelled dataset (up to 200 records) with four fixed categories (performance, appearance, value, other). Ideal for validating classifier outputs, catching labelling errors, or benchmarking against a naive-Bayes baseline without needing hosted model infrastructure or foundation model access.

## Known failure modes

- Exceeding 200 records per call returns an error or truncated results
- Malformed probability arrays (not exactly 4 values summing near 1.0) may cause computation errors
- Invalid or out-of-enum actual/predicted labels will fail schema validation
- Empty records array produces no meaningful audit output
- Missing required fields (id, text, actual, predicted, probabilities) per record causes rejection

## How this service works

Review aspect - Label and prediction audit: Label and prediction audit for Review aspect. Up to 200 supplied labelled text records. Local dataset tools, evaluation and small naive-Bayes baselines; no hosted model or foundation-model training. One of 25 profiles or calculations across 20 shared operations in this sector. 0.01 USDC includes one bounded label and prediction audit deliverable.

## Output

A bounded audit deliverable covering classification accuracy and error analysis for up to 200 review records labelled across four aspect categories (performance, appearance, value, other). Includes evaluation metrics comparing predicted vs actual labels, probability-based diagnostics, and naive-Bayes baseline comparisons computed locally without hosted model inference.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "records": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id",
     "text",
     "actual",
     "predicted",
     "probabilities"
    ],
    "properties": {
     "id": {
      "type": "string",
      "default": "",
      "maxLength": 80,
      "minLength": 1
     },
     "text": {
      "type": "string",
      "default": "",
      "maxLength": 1000
     },
     "actual": {
      "enum": [
       "performance",
       "appearance",
       "value",
       "other"
      ],
      "type": "string"
     },
     "predicted": {
      "enum": [
       "performance",
       "appearance",
       "value",
       "other"
      ],
      "type": "string"
     },
     "probabilities": {
      "type": "array",
      "items": {
       "type": "number",
       "default": 0,
       "maximum": 1,
       "minimum": 0
      },
      "default": [],
      "maxItems": 4,
      "minItems": 4
     }
    },
    "additionalProperties": false
   },
   "default": [
    {
     "id": "example-0-0",
     "text": "performance sample document number 0 for this supplied dataset.",
     "actual": "performance",
     "predicted": "performance",
     "probabilities": [
      0.8,
      0.06666666666666667,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-0-1",
     "text": "performance sample document number 1 for this supplied dataset.",
     "actual": "performance",
     "predicted": "performance",
     "probabilities": [
      0.8,
      0.06666666666666667,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-0-2",
     "text": "performance sample document number 2 for this supplied dataset.",
     "actual": "performance",
     "predicted": "performance",
     "probabilities": [
      0.8,
      0.06666666666666667,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-1-0",
     "text": "appearance sample document number 0 for this supplied dataset.",
     "actual": "appearance",
     "predicted": "appearance",
     "probabilities": [
      0.06666666666666667,
      0.8,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-1-1",
     "text": "appearance sample document number 1 for this supplied dataset.",
     "actual": "appearance",
     "predicted": "appearance",
     "probabilities": [
      0.06666666666666667,
      0.8,
      0.06666666666666667,
   
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/review-aspect-label-and-prediction-audit-65799cda/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)