77trust / 100

Micro Confidence Calibration Report

by Confidence Calibration Report in Other

x402 APIPassing, checked 2 h ago

Compute binary Brier score and count-weighted ECE for up to 256 declared held-out score/outcome pairs. Supports probability or percent scores, normalized to probabilities. Equal-width bins use exact rational boundaries: lower inclusive, upper exclusive, final bin includes 1. Empty bins report null means/gaps. No clinical validity claim.

POST https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report

Last 30 days

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

Uptime
100%
Response time
411 ms typical, 705 ms slowest 5%
Last check
2 h ago
Next check
any minute now

How to call it

POST https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report

Each call costs $0.047 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report
content-type: application/json

{
  "binCount": 2,
  "dataClass": "synthetic",
  "evaluationSplit": "declared-held-out-offline",
  "pairs": [
    {
      "outcome": 0,
      "score": "0"
    },
    {
      "outcome": 1,
      "score": "0.5"
    },
    {
      "outcome": 1,
      "score": "1"
    }
  ],
  "scoreUnits": "probability"
}

Parameters

ParameterTypeRequiredDescription
binCountintegerYes
dataClassstringYes One of: public, synthetic.
evaluationSplitstringYes One of: declared-held-out-offline.
pairsarrayYes
scoreUnitsstringYes One of: probability, percent.

Example response

The provider's example. We can't check it without paying.

Example response, 37 lines
{
  "amountBaseUnits": "47000",
  "boundaries": [
    "Public or synthetic inputs only. Caller labels are declarations,…"
  ],
  "inputDigest": "sha256:6b207dbfe3beaadb731bb40b19f194376e27a59b64db60bff20a0a316…",
  "offerId": "confidence-calibration-report",
  "receiptDigest": "sha256:34bf193cabf312b023b80ea60c8aae02b01f6f96133d0d6640cbdc6e1…",
  "result": {
    "binConvention": "equal-width; lower-inclusive-upper-exclusive; final-includes-one…",
    "bins": [
      {
        "absoluteGap": "0",
        "count": 1,
        "index": 0,
        "lowerBound": {
          "denominator": "1",
          "numerator": "0"
        },
        "meanScore": "0",
        "observedRate": "0",
        "upperBound": {
          "denominator": "2",
          "numerator": "1"
        },
        "upperInclusive": false
      }
    ],
    "brier": "0.083333333333",
    "clinicalValidityClaimed": false,
    "dataClass": "synthetic",
    "ece": "0.166666666667",
    "heldOutVerified": false,
    "scoreUnits": "probability"
  },
  "version": "maha-microproducts/0.1"
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.047.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report' \
  -H 'content-type: application/json' \
  --data-raw '{"binCount":2,"dataClass":"synthetic","evaluationSplit":"declared-held-out-offline","pairs":[{"outcome":0,"score":"0"},{"outcome":1,"score":"0.5"},{"outcome":1,"score":"1"}],"scoreUnits":"probability"}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report' \
  -H 'content-type: application/json' \
  --data-raw '{"binCount":2,"dataClass":"synthetic","evaluationSplit":"declared-held-out-offline","pairs":[{"outcome":0,"score":"0"},{"outcome":1,"score":"0.5"},{"outcome":1,"score":"1"}],"scoreUnits":"probability"}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.047 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.047" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.047 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fwww.mahastrategies.com%2Fapi%2Fv1%2Fmicro%2Fconfidence-calibration-report&method=POST
const res = await pay("https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "binCount": 2,
    "dataClass": "synthetic",
    "evaluationSplit": "declared-held-out-offline",
    "pairs": [
      {
        "outcome": 0,
        "score": "0"
      },
      {
        "outcome": 1,
        "score": "0.5"
      },
      {
        "outcome": 1,
        "score": "1"
      }
    ],
    "scoreUnits": "probability"
  }),
});
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.047 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.047"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://www.mahastrategies.com/api/v1/micro/confidence-calibration-report",
        json={
            "binCount": 2,
            "dataClass": "synthetic",
            "evaluationSplit": "declared-held-out-offline",
            "pairs": [
                {
                    "outcome": 0,
                    "score": "0",
                },
                {
                    "outcome": 1,
                    "score": "0.5",
                },
                {
                    "outcome": 1,
                    "score": "1",
                },
            ],
            "scoreUnits": "probability",
        },
    )
    print(res.status_code, res.text)

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
2 h agoPassed402333 ms$0.047
6 h agoPassed402705 ms$0.047
9 h agoPassed402719 ms$0.047
13 h agoPassed402313 ms$0.047
17 h agoPassed402304 ms$0.047
21 h agoPassed402411 ms$0.047
25 h agoPassed402311 ms$0.047
29 h agoPassed402332 ms$0.047
32 h agoPassed402308 ms$0.047
36 h agoPassed402463 ms$0.047
39 h agoPassed402421 ms$0.047
43 h agoPassed402486 ms$0.047
46 h agoPassed402439 ms$0.047
2 days agoPassed402584 ms$0.047
2 days agoPassed402531 ms$0.047