- Who it helps
- Researchers assessing scientific prediction beyond question answering
- Availability
- The November 11 preprint is public. Its abstract describes one hundred public experiments and sixteen private unpublished wet-lab experiments.
Compare predictions with experimental results
The authors evaluate thirteen agent configurations. This tests a narrower capability than conducting an experiment: the agent must predict the relative results of candidate conditions.
Private experiments help, but do not settle generalization
Reported correlations remain author results on a bounded set. The abstract does not establish broad discovery ability or dependable predictions for a new laboratory.
What you can do
- Read the primary description and its stated limits before planning an evaluation. Open reference ↗
Where the evidence stops
Abstract checked. No experiment, model run or independent validation performed.
Sources read. Public source text checked November 14, 2026 UTC. No installation, model inference or complete workflow executed.
Sources & further reading
Paper · paper
Science Prediction Universe ↗
November 11 abstract describes outcome prediction using public and private experiments. No prediction run reproduced.
Science Prediction Universe authors · page checked 2026-11-14 · Published 2026-11-11
Coverage note: Abstract checked. No experiment, model run or independent validation performed.
The record over time (1)
Dated source checks and published explanations. An observation date can differ from the original release date.
- · Added to Current
Science Prediction Universe evaluates whether agents can rank experimental outcomes before seeing the measurements.