analyze_score_distribution
Compute summary statistics (mean, median, std, quartiles, cutoff counts) over an experiment's per-sample poisoning scores to tune the detection threshold.
Instructions
Compute summary statistics over an experiment's per-sample poisoning scores: mean, median, std, min, max, quartiles, and counts above fixed cutoffs (0.3, 0.5, 0.7) plus a chosen threshold. per_sample_scores covers only the suspect set with no clean/suspect ground-truth label, so these statistics describe the suspect score population only -- a clean-vs-suspect separation isn't computable from this data. Useful for tuning the detection threshold.
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": {
"experiment_id": "<experiment_id>"
},
"name": "analyze_score_distribution"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| threshold | No | Threshold to report the above/below split for; defaults to the experiment's stored threshold | |
| experiment_id | Yes |