TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

The Same Screening Run Disagreed on Twenty-Nine Eligible Records

Nominally identical model runs agreed 91.7 percent overall but split on 94 records in a preregistered evidence-review workflow.

Published Updated Story ID: mp-2026-08-28-018
Read the complete editionStory JSON

Summary

Nominally identical model runs agreed 91.7 percent overall but split on 94 records in a preregistered evidence-review workflow.

Twenty-nine verified eligible records appeared in only one of the paired runs. No human or model workflow recovered every eligible record, reinforcing the authors' case for validated, auditable and human-supervised use when false negatives remove evidence.

Why it matters

Nominally identical model runs agreed 91.7 percent overall but split on 94 records in a preregistered evidence-review workflow.

Limits and context

  • Twenty-nine verified eligible records appeared in only one of the paired runs.

Key claims

  1. Nominally identical model runs agreed 91.7 percent overall but split on 94 records in a preregistered evidence-review workflow.

    Qualification: Twenty-nine verified eligible records appeared in only one of the paired runs.

    Evidence: source-2026-08-28-020

Sources

  1. arXiv preprint 2608.26885arXiv · primary research

Corrections

No corrections have been recorded for this story.