paper-with-me

홈 › Papers

Locked Evaluation Surfaces: Transfer Failure and Sampling-Depth Entanglement in CRISPRi Perturbation-Effect Prediction

2026-07-31 · Mehrdad Shoeibi, Niloofar Yousefi arxiv

Predicting how held-out target genes respond to CRISPRi perturbation, and whether such predictions transfer across biological screens, is hard to evaluate: a representation can be informative within one screen yet fail across screens, while endpoint definitions and design factors such as sampling depth differ between datasets. We evaluate a frozen Geneformer representation under a locked, pre-registered protocol, with heads and model selection frozen before test evaluation, external outcome labels withheld until final unblinding, and analysis-governing decisions fixed before the evaluations they govern. In-distribution on the Virtual Cell Challenge (VCC), the frozen representation carries measurable predictive information beyond a dimension-matched random-feature control (Delta R^2 = +0.1645, 95% CI [+0.1375, +0.1920]), satisfying the pre-registered informativeness gate required before interpreting transfer. It then fails zero-shot transfer on both external screens (Spearman rho = -0.139 and -0.267), lying below that control on each. Adding a predefined magnitude block improves the representation externally (Delta rho = +0.032 and +0.143) but does not rescue transfer: both remain negative. A pre-registered, count-adjusted max-response secondary is positively associated with the outcome on both screens; we report it as correlational and secondary, not as a recovered magnitude signal. Finally, the VCC endpoint is strongly sample-size associated: a count-only linear model reaches R^2 = +0.4325, versus +0.2589 for the four magnitude scalars; adding those scalars to cell count improves R^2 by only +0.0017, so much of the aggregate-magnitude signal overlaps with cell count. A locked evaluation thus surfaces a transfer failure and a sampling-depth entanglement that a less controlled evaluation could obscure.

📄 PDF Abstract BibTeX arXiv:2608.00152

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reliability analysis of discrete-state performance functions via adaptive sequential sampling with detection of failure surfaces

2022-08-04 · Miroslav Vořechovský

The paper presents a new efficient and robust method for rare event probability estimation for computational models of an engineering product or a process returning categorical information only, for example, either succe…

Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines

2026-08-18 · Kaiji Sekimoto, Muneki Yasuda arxiv

Learning restricted Boltzmann machines (RBMs) is computationally challenging because it requires expectations whose exact evaluation is generally intractable. The expectations are typically evaluated using a sampling app…

Counterpoint by Convolution

2019-03-18 · Cheng-Zhi Anna Huang, Tim Cooijmans, Adam Roberts, Aaron Courville 외

Machine learning models of music typically break up the task of composition into a chronological process, composing a piece of music in a single pass from beginning to end. On the contrary, human composers write music in…

Music GenerationMusic Modeling

SLAP: Slapband-based Autonomous Perching Drone with Failure Recovery for Vertical Tree Trunks

2026-01-01 · Julia Di, Kenneth A. W. Hoffmann, Tony G. Chen, Tian-Ao Ren 외 arxiv

Perching allows unmanned aerial vehicles (UAVs) to reduce energy consumption, remain anchored for surface sampling operations, or stably survey their surroundings. Previous efforts for perching on vertical surfaces have …

LiT: Zero-Shot Transfer with Locked-image text Tuning

2021-11-15 · CVPR 2022 1 · Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner 외

This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training. In our empirical study we find that locked pre-tra…

image-classificationImage ClassificationRetrievalZero-Shot Image Classification+1