The study evaluates a frozen Geneformer representation for predicting CRISPRi perturbation effects under a tightly controlled, pre‑registered protocol. While the representation shows significant predictive power within the Virtual Cell Challenge dataset, it fails to transfer to external screens, with negative zero‑shot Spearman correlations. The analysis also reveals that the VCC endpoint is heavily influenced by sampling depth, as cell count alone explains most of the variance, indicating a sampling‑depth entanglement that could mask transfer failures in less controlled settings.
arXiv:2608.00152v3 Announce Type: replace-cross Abstract: AI evaluation can support the wrong inference when an in-domain benchmark success does not survive distribution shift, or when the benchmark...
arXiv:2608. 00152v1 Announce Type: new Abstract: Predicting the magnitude of a CRISPRi perturbation's transcriptomic effect on held-out target genes is an important open problem in single-cell biology.
SCALE is a conditional transport model that treats cells as unordered sets to predict treated cell populations without requiring cell-level matching. It uses a shared set-aware encoder and a conditional DiT backbone to learn latent transport, enabling endpoint supervision that is directly delta-aligned. Across diverse perturbation types—including genetic, chemical, developmental, and immune—SCALE accurately recovers gene‑expression changes, response directions, and population structure, outperforming competing methods on CRISPR data and successfully prioritizing cytokines that elicit distinct immune responses.
The paper introduces CELLAUDIT, a method for auditing whether inputs claimed to influence predictive models actually do so. By testing if an input can enter the computation, whether predictions depend on it, and if that dependence improves observed responses, the authors evaluate agent-generated predictors on a morphology‑transcriptomics benchmark (BBBC047). Their findings show that many models claim compound contributions that are not supported by the data, and that falsification‑guided revisions can recover genuine input effects while improving performance.
The paper introduces CP‑BG‑Bench, a paired‑view evaluation framework for Cell Painting vision encoders that fixes a central cell across four matched views (raw crop, segmented, and density‑augmented variants). Using this framework on three datasets and three encoders, the authors show that standard single‑metric rankings (e.g., replicate mAP) vary systematically across protocols, revealing disagreements along axes of cell versus background, morphology versus context, and within‑study versus across‑batch performance. The study demonstrates that segmented views can outperform crops in certain tasks and that background‑driven gains are largely determined by experimental design rather than encoder choice.
The paper introduces AssayBench-Loop, a large benchmark of 1,389 CRISPR screens across five phenotype categories, and builds on it to develop AssayLoop, a sequential experimental design framework that combines a transformer-based acquisition policy (AssayFormer) trained on historical data with LLM-derived biological priors. AssayLoop achieves a 5.67‑fold enrichment over random selection, recovering 27.7% of hits after testing only about 5% of the library, and outperforms existing adaptive-design methods and standalone LLMs. The authors also present AssayLLM, extending the approach directly to an LLM via task‑specific post‑training, and show that performance improves with more historical training data and transfers to unseen phenotype categories.
arXiv:2607. 17671v1 Announce Type: new Abstract: Large-scale single-cell perturbation atlases make it possible to ask an inverse question: given an observed transcriptional response, which annotated targets and compounds in a fixed library are most consistent with that response?
Compositional analysis of frozen vision encoders should determine both what changed and where it changed. Standard factor probes score these axes separately, however, and can reward multiple operations that reuse the same predicted slot.
The study investigates whether independently trained language‑model societies share a common packet language and how inherited interface states affect learning. A comprehensive audit of 30 pairwise interactions among six restricted societies shows that only one pair is fully interoperable, another is partially compatible, and the remaining 26 pairs fail across all alignment levels. Further experiments reveal that a globally trained communication interface can act as a severe negative‑transfer prior, but inherited interfaces never outperform fresh‑interface controls by the preregistered margin.
arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.
arXiv:2607. 18553v1 Announce Type: cross Abstract: Can a language model read the quality of ongoing computation, and can an external intervention turn that readout into better outcomes?
arXiv:2607. 27651v1 Announce Type: new Abstract: Adaptive laboratories choose measurements during experiments, yet most methods begin after adaptation is permitted.