Run-to-run consistency (pass^k)

Share of tasks that pass on every repeated run.

Who judgesAutomatable
EvidenceGrade E2
Product typeCross-cuttingID X17

What run-to-run consistency (pass^k) means

Share of tasks that pass on every repeated run.

Why it matters. Models vary between runs. Pass-on-every-repeat is closer to what users experience than average accuracy.

Example, illustrative

A task passes 4 of 5 runs and counts as a failure under this measure.

How to measure it

01

Define the unit

Decide whether you count per sentence, per note, per patient or per call.

02

Sample on purpose

Pick cases that cover specialties, languages and rare events, not only easy ones.

03

Judge with clinicians

Clinicians label a sample. Graders are then checked against those labels.

04

Report the margin

Show an interval, and the grader's own error rate beside the score.

Watch out for

A single average hides rare, serious errors and weaker subgroups.

What a good report shows

A number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.

Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.

Reviewed by the Precision research team.

How strong is the evidence

E2 · Preprint, benchmark page or vendor-run result. Backed by numbers from a preprint, a benchmark page or a vendor-run test. Treat as strong but not settled.

What the sources say

Cekura counts a workflow as passing only if all runs pass (Cekura).

  • Automatable. Can be scored by software, including an AI grader that is spot-checked against clinicians.
  1. Cekurabenchmarks.cekura.ai

Found something out of date? Write to hello@precision.example.

Quick answers

What is run-to-run consistency (pass^k) in healthcare AI?

Share of tasks that pass on every repeated run. It sits in the every product type group.

Why does run-to-run consistency (pass^k) matter?

Models vary between runs. Pass-on-every-repeat is closer to what users experience than average accuracy. A task passes 4 of 5 runs and counts as a failure under this measure.

How is run-to-run consistency (pass^k) measured?

Define the unit, then Sample on purpose, then Judge with clinicians, then Report the margin. Report the unit (per sentence, per note, per patient), the sampling method, the severity scale, and how often the automated grader agreed with clinicians compared with how often clinicians agreed with each other.

What should I watch out for with run-to-run consistency (pass^k)?

A single average hides rare, serious errors and weaker subgroups. A good report gives: a number with a clear unit, a stated sample, a margin and the grader's agreement with clinicians.

Can run-to-run consistency (pass^k) be automated?

Largely yes, including AI graders that are spot-checked against clinicians. Report the grader's error rate beside every score.

Measure run-to-run consistency (pass^k) on your own data