Recalibrate a Model Probability
court_recalibratePaid (x402: USDC on Base, USDC on Solana, XRP on XRPL, USDC on Arc, or XAH on Xahau). Map a model's raw probability to an empirically calibrated one using resolved outcomes on the ledger. Refuses with insufficient_data below 30 samples.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model": "<model>",
"prob": "<prob>"
},
"name": "court_recalibrate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prob | Yes | The model's raw predicted probability to recalibrate, between 0 and 1. | |
| model | Yes | Model identifier whose resolved ledger predictions define the calibration mapping (e.g. 'jev-1.14.0'). The model needs at least 30 resolved predictions or the call refuses with insufficient_data. | |
| task_type | No | Optional task category filter; omit to fit the mapping on all of the model's resolved predictions. |