Methodology

How predictions are found

We pull the automatic subtitles from each lecture on the Predictive History channel, clean them into readable text with timestamps, and use a language model to surface candidate claims. Nothing the model produces is published automatically.

The falsifiability bar

A claim only qualifies if a neutral third party could, at some future date, judge it true or false against public evidence. Vague directional statements, opinions, and commentary about the past do not qualify. Conditional claims (“if X, then Y”) are marked as such.

The human review gate

Every candidate is reviewed by a person before it appears here. The reviewer checks the paraphrase against the source, trims the quote, confirms the timestamp, and either approves, rejects, or merges it into an existing prediction. Nothing is published without that review. The gate is permanent.

How scoring works

A prediction stays pending until there is public evidence to resolve it. It is then marked confirmed, partial, wrong, or unverifiable. Every resolved verdict carries at least one public evidence link, and the reasoning is stated plainly. The headline accuracy figure is computed from the resolved calls only; it is never adjusted by hand.

Honest caveats

• The resolved denominator is small and will stay small for a long time, so early accuracy numbers carry wide uncertainty. We state the denominator openly rather than hiding it.
• Predictions often cluster around the same underlying event, so a single correct or incorrect call can move several verdicts at once. Treat the count as a record, not an independent sample.
• Extraction depends on subtitle quality and on judgement about what counts as a claim. We show the exact quote and a link to the source so you can check every call yourself.