# Task Type Per-Label Precision and Recall

> Task Type Per-Label Precision and Recall 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).

Computes per-label precision and recall metrics for a task-type classifier (research, writing, analysis, implementation) given up to 200 labelled text records with actual and predicted labels.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-sector-ml-task-type-per-label?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/task-type-per-label-precision-and-recall-aa41ed99
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_UGSt1HDlBG0NmCpcPezpi

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 task-type-per-label-precision-and-recall-aa41ed99 -d '<json body>'
```

Example prompt: Evaluate my task-type classifier on these 50 labelled records — each has an ID, the text, and both the actual and predicted task type (research, writing, analysis, or implementation) — and give me per-label precision and recall for each category.

## When to prefer this

Choose this endpoint when you need per-label (per-class) precision and recall metrics for a task-type classifier operating over the four fixed categories: research, writing, analysis, implementation. It is ideal for lightweight, local evaluation of small to medium labelled datasets (up to 200 records) without needing a hosted model or foundation-model infrastructure. Prefer it over generic ML evaluation APIs when your labels are specifically these four task types and you need a cheap ($0.01 USDC), bounded, deterministic computation.

## Known failure modes

- More than 200 records supplied — input is capped at 200 and excess may be rejected or truncated
- Missing required fields (id, text, actual, predicted) in any record causes validation failure
- Invalid label values outside the allowed enum (research, writing, analysis, implementation) cause schema rejection
- Empty records array returns no meaningful metrics
- Highly imbalanced label distribution may yield undefined precision or recall for rare labels

## How this service works

Task type - Per-label precision and recall: Per-label precision and recall for Task type. 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 per-label precision and recall deliverable.

## Output

A per-label breakdown of precision and recall for each task type (research, writing, analysis, implementation), computed from the supplied actual versus predicted label pairs across up to 200 records. Each label receives its own precision and recall score, enabling granular diagnosis of classifier performance by category.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "records": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "id",
     "text",
     "actual",
     "predicted"
    ],
    "properties": {
     "id": {
      "type": "string",
      "default": "",
      "maxLength": 80,
      "minLength": 1
     },
     "text": {
      "type": "string",
      "default": "",
      "maxLength": 1000
     },
     "actual": {
      "enum": [
       "research",
       "writing",
       "analysis",
       "implementation"
      ],
      "type": "string"
     },
     "predicted": {
      "enum": [
       "research",
       "writing",
       "analysis",
       "implementation"
      ],
      "type": "string"
     }
    },
    "additionalProperties": false
   },
   "default": [
    {
     "id": "example-0-0",
     "text": "research sample document number 0 for this supplied dataset.",
     "actual": "research",
     "predicted": "research"
    },
    {
     "id": "example-0-1",
     "text": "research sample document number 1 for this supplied dataset.",
     "actual": "research",
     "predicted": "research"
    },
    {
     "id": "example-0-2",
     "text": "research sample document number 2 for this supplied dataset.",
     "actual": "research",
     "predicted": "research"
    },
    {
     "id": "example-1-0",
     "text": "writing sample document number 0 for this supplied dataset.",
     "actual": "writing",
     "predicted": "writing"
    },
    {
     "id": "example-1-1",
     "text": "writing sample document number 1 for this supplied dataset.",
     "actual": "writing",
     "predicted": "writing"
    },
    {
     "id": "example-1-2",
     "text": "writing sample document number 2 for this supplied dataset.",
     "actual": "writing",
     "predicted": "writing"
    },
    {
     "id": "example-2-0",
     "text": "analysis sample document number 0 for this supplied dataset.",
     "actual": "analysis",
     "predicted": "analysis"
    },
    {
     "id": "example-2-1",
     "text": "analysis sample document number 1 for this supplied dataset.",
     "actual": "analysis",
     "predicted": "analysis"
    },
    {
     "id": "example-2-2",
     "text": "analysis sample document number 2 for this supplied dataset.",
     "actual": "analysis",
     "predicted": "analysis"
    },
    {
     "id": "example-3-0",
     "text": "implementation sample document number 0 for this supplied dataset.",
     "actual": "implementation",
     "predicted": "implementat
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/task-type-per-label-precision-and-recall-aa41ed99/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)