Score anchor clarity: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Show one score anchor with its instructions and glossary. Check whether it defines a concrete condition, depends on an unavailable neighbor or only names an undefined degree.
Jev Score compares state with individual anchor descriptions. A useful anchor needs enough meaning in its own text and the shared instructions; a missing previous level cannot supply that meaning.
This demonstration uses Choice to review anchor wording. Standalone does not mean the full scale is complete, non-overlapping or calibrated. Those are separate properties that require the other anchors and representative inputs.
This original wording-review exercise applies guidance in the repository explicitly named by the cited post. The inputs and review labels are ours. The repository teaches Jev integration; it does not implement this page's analyzer or establish its accuracy.

Use the sample to understand the rule, then test your own input for score anchor clarity.

Show one score anchor with its instructions and glossary.

Open the decision rules and keep the intended distinction between Standalone, Neighbor, Degreeonly, Unclear. Edit the choices only when testing your own rule.

Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

Review Unclear before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Concrete coverage | Standalone | 96.0% |
| Missing previous level | Neighbor | 98.0% |
| An undefined adjective | Degreeonly | 100% |
| A supplied term | Standalone | 48.0% |
| Missing definition | Unclear | 84.0% |
| An empty anchor | Unclear | 100% |
These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 6 of 6 results matched the authored fixture expectations.Verified
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
Yes. The evaluator receives the instructions. A term defined there can make a short anchor concrete without repeating the definition.
One anchor can be understandable but overlap another or leave gaps. This page only checks whether this one anchor can be interpreted from its supplied context.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.