SciConHarness blocks ground-truth sources to force models to synthesize, not look up
manoelribeiro · x · 2026-10-07
The authors describe their evaluation methodology: SciConHarness blocks the target ground-truth Cochrane review and other answer-revealing sources, so frontier models must actually synthesize evidence across studies rather than retrieve the answer when tackling scientific synthesis questions in health research.
Related event: SciConHarness Blocks Answer Sources to Force Genuine Evidence Synthesis(2 posts)→
More from Research
- COLM paper: latent reasoning traces decodable 65-93% of the time in LRMs — sarahwiegreffe · 2026-10-07
- Apple ML Research is hiring a PhD intern to make foundation models know what they know — sineadwilliamso · 2026-10-07
- CAVEAT testbed exposes how merchants can steer your shopping AI agent — ZacharyHuang12 · 2026-10-07
- GEA treats agent groups as the evolution unit, hitting 71% SWE-bench Verified with zero human help — xwang_lk · 2026-10-07
- 9B model fine-tuned with ~$25 of compute hits 79% of Jev's Decision Index score — sophiamyang · 2026-10-07
- Recovery skills lift real-robot task success from 77.5% to 87.5% in Recova — qinzytech · 2026-10-07