Description
Count covered importance only when predicted and observed, unexplained importance when observed but not predicted, and normalize covered weight.
Evidence weights and credences are numerical representations under a chosen model. Likelihood ratios, probabilities, logarithmic weights and confidence bounds have different meanings; one local calculation does not establish the truth of a claim.
Count covered importance only when predicted and observed, unexplained importance when observed but not predicted, and normalize covered weight.
When to use this tool
Use Explanation Coverage One Observation Term when you need an explicit evidence-weight or probability-consistency term.
How to use the tool and how it works
- Enter predicted, observed, importance, totalImportance. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read coveredWeight, unexplainedWeight, coverageContribution. Use the output convention below.
Require positive totalImportance and importance within it. Count covered importance only when predicted and observed, unexplained importance when observed but not predicted, and normalize covered weight.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| predicted | Predicted | Required. Boolean. |
| observed | Observed | Required. Boolean. |
| importance | Importance | Required. Finite number; minimum 0. |
| totalImportance | Total Importance | Required. Finite number; strictly above 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| coveredWeight | Covered Weight | Required. Finite number. |
| unexplainedWeight | Unexplained Weight | Required. Finite number. |
| coverageContribution | Coverage Contribution | Required. Finite number. |
{
"input": {
"predicted": true,
"observed": true,
"importance": 3,
"totalImportance": 10
},
"output": {
"coveredWeight": 3,
"unexplainedWeight": 0,
"coverageContribution": 0.3
}
}Limitations and assumptions
- Unobserved items contribute zero under this definition. It is one observation term, not a complete explanation score, causal test or truth assessment.
- 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 source quality and the complete inference model. Check likelihood meaning, dependence, prior assumptions, normalization and uncertainty rather than substituting counts or weights for justified evidence.
References
Similar or alternative tools
- Assertion Support Path Count
Count distinct selected-assertion paths and any-valid paths; subtract for invalidOnlyPaths.
- Claim Source Support Count
For the requested claim, count distinct source IDs with true and false support separately.