Description
Return required labels absent from a predicted set.
Multilabel predictions can be compared as literal sets or checked against a supplied hierarchy edge. Subset inclusion, exact set equality and distance through an asserted ancestor answer different questions; a local check need not verify label meaning or the complete hierarchy.
Return required labels absent from a predicted set.
When to use this tool
Use Multilabel Subset Violation Witness when checking the stated label-set or parent/ancestor constraint.
How to use the tool and how it works
- Enter required, predicted. Follow any array-alignment requirements below. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read valid, witness. Inspect valid before interpreting the associated values.
Return required labels absent from a predicted set. Deduplicate both through set membership, witness preserves distinct required order and valid means no missing required labels.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| required | Required | Required. Array of text; maximum UTF-16 length 8192; maximum items 256. |
| predicted | Predicted | Required. Array of text; maximum UTF-16 length 8192; maximum items 256. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| valid | Whether this local input/result condition holds; inspect the limitations before treating it as full validation. | Required. Boolean. |
| witness | Witness | Required. Array of text; maximum UTF-16 length 8192; maximum items 256. |
{
"input": {
"required": [
"a",
"b"
],
"predicted": [
"a"
]
},
"output": {
"valid": false,
"witness": [
"b"
]
}
}Limitations and assumptions
- Additional predictions are allowed; this is a subset constraint, not exact-match accuracy or semantic label validation.
- Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
Alternative or Complementary methods
Validate the label vocabulary and complete hierarchy, and choose dataset-level set or hierarchical metrics appropriate to the prediction task.
References
Similar or alternative tools
- Multilabel Exact Match Single Observation
Compare one multilabel prediction with actual labels as sets.
- Classifier Logit Tie Policy Tool
Compute classifier logit tie policy from explicit bounded inputs.