Description
Check a supplied score against a top-k boundary policy.
Classification terms depend on label vocabularies, decision thresholds and denominator definitions. One class recall is not a full balanced-accuracy metric, and a row or column total is not automatically a precision or recall denominator. Empty or zero-total cases need an explicit defined flag or convention.
Check a supplied score against a top-k boundary policy.
When to use this tool
Use Top K Boundary Membership Flag when you already have candidateScore, kthScore, includeBoundaryTies, higherIsBetter and need to check a supplied score against a top-k boundary policy.
How to use the tool and how it works
- Enter candidateScore, kthScore, includeBoundaryTies, higherIsBetter. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read includedByBoundary. Inspect includedByBoundary before interpreting the associated values.
Compare candidate to kthScore using >= or > when higherIsBetter, or <= or < when lower is better, as includeBoundaryTies selects.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| candidateScore | Candidate Score | Required. Finite number. |
| kthScore | Kth Score | Required. Finite number. |
| includeBoundaryTies | Include Boundary Ties | Required. Boolean. |
| higherIsBetter | Higher Is Better | Required. Boolean. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| includedByBoundary | Compares one score to the supplied kth score; does not compute rank or k, and ties can admit more than k items. | Required. Boolean. |
{
"input": {
"candidateScore": 0.8,
"kthScore": 0.7,
"includeBoundaryTies": true,
"higherIsBetter": true
},
"output": {
"includedByBoundary": true
}
}Limitations and assumptions
- No scores are ranked and no k is supplied or validated. Ties can admit more than k items; no classification, accuracy or selection quality is inferred.
- 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.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.
Alternative or Complementary methods
Evaluate the complete prediction set, confusion structure and decision policy. Report missingness, class scope and uncertainty with the full metric; local threshold flags or one-cell fractions cannot characterize overall model performance.
References
Similar or alternative tools
- Ordinal Label Adjacent Threshold Gap
Measure a supplied upper-minus-lower ordinal-threshold gap.
- Selective Classification Accepted Count
Calculate supplied nonabstained prediction count and conditional coverage.