# Lead Stage Confidence Calibration Bins

> Lead Stage Confidence Calibration Bins is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-18).

Computes confidence calibration bins for a multi-class lead stage classifier (enquiry, qualified, negotiation, closed) from up to 200 labelled records with predicted probabilities.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-sector-ml-lead-stage-calibration?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/lead-stage-confidence-calibration-bins-304eba95
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_l3xxysu4MlVc3pnHWQPmm

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 lead-stage-confidence-calibration-bins-304eba95 -d '<json body>'
```

Example prompt: Run confidence calibration binning on these 50 lead stage records — each has the actual stage (enquiry, qualified, negotiation, or closed), the predicted stage, and four class probabilities. I want to see how well-calibrated the model's confidence scores are across each bin.

## When to prefer this

Choose this endpoint when you have a trained multi-class lead stage classifier producing probability outputs and need to evaluate how well-calibrated those probabilities are across the four pipeline stages, without requiring a hosted model or cloud training infrastructure. Ideal for lightweight, local-style calibration analysis at very low cost ($0.01 per call) on datasets up to 200 records.

## Known failure modes

- Records array empty or missing — validation error returned
- Probabilities array does not have exactly 4 elements per record — schema rejection
- Probability values outside [0,1] range — validation failure
- More than 200 records supplied — request rejected or truncated
- Actual or predicted labels outside allowed enum values — schema error
- Malformed JSON body — HTTP 400 response

## How this service works

Lead stage - Confidence calibration bins: Confidence calibration bins for Lead stage. 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 confidence calibration bins deliverable.

## Output

Returns binned confidence calibration statistics for the supplied lead stage records, including accuracy and average confidence per bin across the four classes (enquiry, qualified, negotiation, closed), enabling reliability diagram construction and ECE/calibration error assessment.

## 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": [
       "enquiry",
       "qualified",
       "negotiation",
       "closed"
      ],
      "type": "string"
     },
     "predicted": {
      "enum": [
       "enquiry",
       "qualified",
       "negotiation",
       "closed"
      ],
      "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": "enquiry sample document number 0 for this supplied dataset.",
     "actual": "enquiry",
     "predicted": "enquiry",
     "probabilities": [
      0.8,
      0.06666666666666667,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-0-1",
     "text": "enquiry sample document number 1 for this supplied dataset.",
     "actual": "enquiry",
     "predicted": "enquiry",
     "probabilities": [
      0.8,
      0.06666666666666667,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-0-2",
     "text": "enquiry sample document number 2 for this supplied dataset.",
     "actual": "enquiry",
     "predicted": "enquiry",
     "probabilities": [
      0.8,
      0.06666666666666667,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-1-0",
     "text": "qualified sample document number 0 for this supplied dataset.",
     "actual": "qualified",
     "predicted": "qualified",
     "probabilities": [
      0.06666666666666667,
      0.8,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
    {
     "id": "example-1-1",
     "text": "qualified sample document number 1 for this supplied dataset.",
     "actual": "qualified",
     "predicted": "qualified",
     "probabilities": [
      0.06666666666666667,
      0.8,
      0.06666666666666667,
      0.06666666666666667
     ]
    },
 
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/lead-stage-confidence-calibration-bins-304eba95/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)