Apodex launches TRACES, the first benchmark for measuring 'discoverative AI' in science
Div_pradeep · x · 2026-08-20
Apodex AI aims to tackle scientific discovery by turning research problems into executable environments for AI solvers. They released TRACES, the world's first benchmark for measuring 'discoverative AI'—testing AI's ability to work through evidence and reach verifiable conclusions without answer keys. Apodex reports its system can train specialized scientific models to human-expert levels.
Related event: Apodex Launches TRACES, First Benchmark for Discoverative AI(8 posts)→
More from Research
- Programmable Cellular Automata: CA rules as readable code for explainability — Amidos2006 · 2026-09-11
- GEVIBench launches as a comprehensive benchmark for comparing voltage indicators — drmichaellevin · 2026-09-11
- Gaussian Light Transport: 13D Gaussian Mixtures Speed Up Global Illumination — ssh4net · 2026-09-11
- Llama Loves Pirates — Goodfire's Tom McGrath on teaching math without the pirate style — Machine Learning Street Talk · 2026-09-11
- Fortnow: P vs NP beyond AI's reach, but NP vs L separations could fall — fortnow · 2026-09-11
- MaP-WAM tackles non-Markovian robot manipulation with memory-grounded planning — Sizhe Zhao · 2026-09-11