DiscoveryRSI recursively improves scientific hypothesis generation
Automated scores rose from 4.86 to 5.39 after two self-improvement rounds, with larger gains in falsifiability and data resolvability.
36
AI model
DiscoveryRSI-27B
- Mentions · 7d0
- Mentions · 30d2
- All mentions2
- First seenOct 15, 2026
- Last mentioned14d ago
Timeline
2 articles · newest firstDiscoveryRSI recursively learns to generate research hypotheses
Automated scores rose from 4.86 to 5.39 after two self-improvement rounds across four life-science domains.
40
Appears with
- GPT-6ai model · 2
- Claude Opus 5ai model · 2
- GPT-6 Lunaai model · 2
- DFM-Benchproduct · 1
- Harborproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.