---
slug: "DistinguishingTest"
name: "DistinguishingTest"
type: "Strategy"
layer: "Mind"
ref: "DistinguishingTest#0439"
sema_id: "sema:DistinguishingTest#mh:SHA-256:0439ea3afff1b4c2272771a447e76b0a02807f40bcbb0be92fa39ff598c7ec0f"
tags: ["Mind","Strategy"]
updated: 2026-11-11
mindscape: "bootstrap"
index_url: https://mindscape.pages.dev/bootstrap/index.json
url: https://mindscape.pages.dev/bootstrap/DistinguishingTest/
related: ["EvidenceUnderdetermination","EmpiricalTest","ConfirmationBlock","Experiment","Falsification","CounterfactualAnchor","EpistemicROI"]
---

# DistinguishingTest

Find an observation that rival explanations predict differently before gathering more evidence that fits them all

Layer: Mind · Category: Strategy

## Mechanism

When the evidence in hand leaves two or more explanations standing, as in [EvidenceUnderdetermination](https://mindscape.pages.dev/bootstrap/EvidenceUnderdetermination.md), each explanation's prediction is worked out for observations not yet made, and an observation is chosen on which the predictions differ: if a failure comes from expired credentials, the request is rejected with an authentication error; if it comes from lost connectivity, the request never reaches the server. The predictions, and which outcome would favour which explanation, are recorded before the observation is made. An inconclusive result is a permitted outcome and is recorded as inconclusive, not read as favouring an explanation. Evidence that every explanation predicts equally is not sought as a test, however easy it is to obtain, and an observation is worth making only when the decision at hand depends on which explanation holds.

## Invariants

- Two or more explanations are named, each with its predicted outcome for the chosen observation.
- The predicted outcomes differ, and they are recorded, with what each would favour, before the observation is made.
- An inconclusive result is recorded as inconclusive.

## Failure modes

- Confirming test: an observation every explanation predicts is gathered and read as support for the favoured one.
- After-the-fact prediction: the predictions are stated once the result is known, so any outcome can be read as favouring the favoured explanation.
- Forced verdict: an inconclusive result is read as favouring one explanation.
- Distinction without consequence: a costly distinguishing observation is made although the decision at hand is the same under every explanation.

## Builds on

- [EvidenceUnderdetermination](https://mindscape.pages.dev/bootstrap/EvidenceUnderdetermination.md) (Mind; References)

## Used by

—

## Identity

- Sema ID: `sema:DistinguishingTest#mh:SHA-256:0439ea3afff1b4c2272771a447e76b0a02807f40bcbb0be92fa39ff598c7ec0f`
- Ref: `DistinguishingTest#0439`

## Links

- [Pattern page](https://mindscape.pages.dev/bootstrap/DistinguishingTest/)
- [View in the interactive graph](https://mindscape.pages.dev/bootstrap/#DistinguishingTest)
- [JSON](https://mindscape.pages.dev/bootstrap/DistinguishingTest.json)
- [Index of all patterns](https://mindscape.pages.dev/bootstrap/index.json)