Source and example scope
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
Provide the passage's expectation and ending. Check whether the ending reverses or fulfills that expectation, or remains unresolved, using only the story facts you supply.
The village arrival is a reversal because the setup says the keeper was expected alone. A description of a strange object without an established expectation would not provide the same comparison.
An open ending leaves the expectation unresolved. The model is not asked to invent what happened next, judge literary quality or measure a reader’s emotional reaction.
The source discussion notes uncertainty around surprise and humour. These fictional passages expose one narrow comparison; they are not an evaluation of the novels or model results mentioned there.
These fictional inputs and decision rules were written for this page. The linked X discussion provides background; the technical implementation follows TypeSafe's Choice contract.

Use the sample to understand the rule, then test your own input for narrative expectation check.

Provide the passage's expectation and ending.

Open the decision rules and keep the intended distinction between Reversal, Expected ending, No expectation, Unresolved ending, Need evidence. 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 Need evidence before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Unexpected visitor | Reversal | 100% |
| Promise fulfilled | Expected ending | 100% |
| Description without setup | No expectation | 96.0% |
| Open ending | Unresolved ending | 100% |
| Negative reversal | Reversal | 100% |
| No passage | Need evidence | 99.0% |
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
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
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.
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.jsonThe rubric explains the decision; the application owns the next step.
A reader may find it surprising, but this rubric deliberately requires an expectation in the supplied passage. That keeps the judgment tied to inspectable evidence.
No. The text may be present and deliberately open. Need evidence is reserved for an absent essential input; Unresolved ending describes the passage itself.
No. It is the model distribution for this one request. The six examples are functional checks with authored expectations, not a representative benchmark. Inspect disagreements and evaluate your own examples before using the label.
The window shows an error and supplies no fresh judgment. The downloadable runner sends one request without retries. Need evidence is a valid outcome about incomplete input; it does not stand in for a network or provider failure.
Edit the evidence above or use the Playground to test another bounded question.