Arc Institute unveils PIE, a perturbation model that generalizes to unseen cell lines and perturbations
yusufroohani · x · 2026-10-06
The Arc Institute team has released its first preprint, PIE (Perturbation is Everything), targeting a key challenge in therapeutics discovery: generalizing across unseen cellular and experimental conditions.
- Method: simplifies the learning objective and leverages curated biological knowledge from public databases.
- Capability: generalizes across a combinatorial space of perturbation studies, unseen cell lines and unseen perturbations.
- Context: the authors frame the field's two bottlenecks—system representation and signal identification—as data problems, and use PIE to build intuition about what's learnable and guide future experiments.
The preprint is public; the project was led by @imrive with multiple Arc Institute contributors.
More from Research
- NeurIPS paper: self-model measurements predict emergent misalignment intervention success — jiaxinwen22 · 2026-10-06
- BRIE: a living benchmark for evaluating LLM information retrieval from electronic health records — BraydonDymm · 2026-10-06
- New paper probes Olmo 3 puzzle: near-identical short-context models diverge after long-context extension — kylelostat · 2026-10-06
- Researcher heads to COLM 2026 with two Ai2 papers on hybrid models and long context — kylelostat · 2026-10-06
- Verifier Agents and Placebo Tests: Catching an AI Causal Analysis That Reasons Itself Wrong — hugobowne · 2026-10-06
- Stanford's DITTO-X does forward and reverse teleoperation for dexterous robot hands — chris_j_paxton · 2026-10-06