Research evidence comparison: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide the research question, accepted evidence and new finding. Check whether it repeats a known result, adds compatible detail or challenges a comparable finding under the supplied conditions.
Novelty depends on the research question and the current evidence set. A repost of the same run is different from an independent repeat, even when the headline sounds new.
Keep measurement conditions visible. A result from another setup may extend the known scope; it should not be presented as a contradiction unless the comparison actually supports that reading.
The linked research pipeline distinguishes repeated findings, additional information and changes to a question's answer. These fictional software measurements demonstrate the editorial classification, not a real benchmark or automatic truth assessment.
This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for research evidence comparison.

Provide the research question, accepted evidence and new finding.

Open the decision rules and keep the intended distinction between Known, Adds detail, Challenges, Review. 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 Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| A repeated observation | Known | 100% |
| Additional reported dimension | Adds detail | 100% |
| Comparable disagreement | Challenges | 100% |
| A new tested setting | Adds detail | 99.0% |
| Conditions omitted | Review | 99.0% |
| No existing evidence | Review | 97.0% |
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
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.
No. It means a comparable new observation conflicts with the stored answer. Both sources and their methods still need review.
Yes. It can extend the tested scope when the changed conditions are explicit. It should not silently replace a result measured under another setup.
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.