# Subscription Request Low-Confidence Review Queue

> Subscription Request Low-Confidence Review Queue is a paid API for AI agents from market.datapackvibe.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Identifies low-confidence classifier predictions on subscription request text records (upgrade/downgrade/cancel/renew) for human review, using naive-Bayes baselines.

## Facts

- Endpoint: POST https://market.datapackvibe.com/x402/assistant-sector-ml-subscription-request-review-queue?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/subscription-request-low-confidence-review-queue-5f7e0e4e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_epgyPswGBYbyApEBb_Rvx

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 subscription-request-low-confidence-review-queue-5f7e0e4e -d '<json body>'
```

Example prompt: I have up to 200 labelled subscription request records with their actual labels (upgrade, downgrade, cancel, or renew), predicted labels, and class probabilities — can you run them through the low-confidence review queue to flag which predictions the model was least sure about so I can send those to a human reviewer?

## When to prefer this

Choose this endpoint when you have a local labelled dataset of subscription request text already classified by a naive-Bayes or similar lightweight model and need to surface the low-confidence predictions for human review before acting on them. It is purpose-built for subscription intent categories (upgrade, downgrade, cancel, renew) and does not require a hosted model or foundation model — ideal for small-scale, cost-sensitive ML quality assurance pipelines.

## Known failure modes

- records array exceeds 200 items — request rejected
- probabilities array does not contain exactly 4 values per record — validation error
- probability values outside [0,1] range — schema rejection
- actual or predicted labels outside allowed enum (upgrade, downgrade, cancel, renew) — validation error
- empty records array returns empty review queue with no actionable output
- malformed record IDs (empty string or over 80 characters) — schema rejection

## How this service works

Subscription request - Low-confidence review queue: Low-confidence review queue for Subscription request. 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 low-confidence review queue deliverable.

## Output

A bounded deliverable listing records where the classifier's predicted probabilities fall below the confidence threshold, identifying which upgrade/downgrade/cancel/renew predictions require human review, along with relevant evaluation metadata from the local naive-Bayes baseline analysis.

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

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/subscription-request-low-confidence-review-queue-5f7e0e4e/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)