CancelDeath

Methodology

Version v1. Every score snapshot records the version that produced it, so historical charts stay interpretable when the methodology changes.

A language model reads each study and extracts what it says: design, sample, endpoint quality, risk of bias, replication status, and how the result sits against prior evidence. It never returns a score.

Deterministic code turns those extracted values into a score movement. The same inputs always produce the same number, which is what makes an evidence history auditable rather than a matter of opinion.

Humans handle ambiguity: disputed interpretations, low-confidence classifications, and every change large enough to matter.

Maximum weight by study design
Study designWeight
Meta analysis1.00
Systematic review0.90
Rct0.85
Cohort0.50
Case control0.35
Observational0.30
Animal0.15
Preclinical0.12
In vitro0.08
Case report0.05
Other0.05

Weight is then adjusted for sample size, follow-up duration, endpoint quality, risk of bias, replication, consistency with prior evidence, and effect magnitude. Preprints are discounted by half. No single event can move a score by more than 8 points.

Strong human evidence85+
Good human evidence70+
Moderate human evidence55+
Early human evidence40+
Preclinical evidence25+
Preliminary signal10+
Insufficient evidence0+

The headline score is a weighted composite: human evidence 60%, animal 20%, mechanistic 20%. Safety acts as a ceiling rather than a bonus, so an intervention with a poor safety profile cannot score highly on the strength of its mechanism.

  • Any proposed change of more than 5 points
  • Landmark and major findings
  • Anything that weakens the evidence base
  • Safety signals, regulatory decisions, retractions, replication failures
  • Any change to a high-profile intervention scoring above 80
  • Any extraction below 97% model confidence

An experimental composite of five pillars, weighted as below. It is not a probability, a forecast, or a peer-reviewed instrument, and it should not be cited as one.

Human trial
30%
Regulatory
15%
Translation
20%
Biomarker
15%
Healthspan
20%

Every evidence page carries a correction link. Corrections go to a moderator queue rather than editing the record directly. An accepted correction earns its reporter reputation, triggers a re-analysis where one is warranted, and appears in the public change history for that entity.