Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

Key points

The authors propose a contrast set, a bundle of mutually exclusive and collectively exhaustive competing explanations for one scientific question, as the unit of discovery.
89% of the top pointwise candidates were rejections, and re-evaluating the same evidence with contrast sets resolved 73% of these candidates to a specific alternative.
Guiding search with contrast sets resolved 67% more questions than pointwise surprisal under the same experiment budget, averaging 161.9 versus 97.2 at K=200.
In a blinded study, 38 human experts chose the same explanation as the system on 78% of resolved questions.
Most of the gain came from corrective resolutions, where evidence shifted support away from the prior-leading explanation to another one.
The authors note the experiments use tabular, observational datasets and a gpt-4o backbone, and on such data a resolution is a statistical rather than a causal finding.

External research summaries. These are not HDATF publications or measured product results.