How fast does a debunk arrive, and for what?

Pre-registered 2026-09-13 · readout no earlier than Tue Jun 01 2027 00:00:00 GMT+0000 (Coordinated Universal Time) · status: registered

The question

When a high-strangeness claim gets traction, how often does a documented skeptical response follow, and how quickly?

Hypothesis, stated in advance

Skeptical response is strongly predicted by a story’s corroboration count rather than by its strangeness rating — debunkers follow attention, not weirdness.

What would count as support

Publisher count at day 3 predicts the arrival of a skeptics-beat item better than the strangeness rating does.

Method

Logistic regression of "a skeptics-beat item joined within 30 days" on publisher count at day 3 and strangeness rating, with beat as a covariate. Model comparison by AIC.

Data

thestaticwire.clusters
thestaticwire.items

Known confounds

Written down before the result, so they cannot be discovered conveniently late.

Our skeptic layer is three outlets. Their coverage choices are idiosyncratic and this measures those outlets, not skepticism in general.
A debunk published under a headline our classifier does not recognise is missed entirely.

Result

Not yet. Data is still accumulating and the readout date has not been reached. Whatever it says when it arrives — including nothing at all — will be published here.

Data access

/api/v1/analyses returns this register as JSON, including every entry that found nothing.