← Back to all news
arXiv Machine Learning By Arjun Bhupatiraju, Abhiram Bhupatiraju

Predictive Multiplicity in Cell-Fate Assignment: Label-Free Rashomon Sets and the Limits of Per-Cell Certification

Read the original on arXiv Machine Learning →

The paper introduces FateMultiplicity, a label‑free framework that builds a Rashomon set of statistically admissible models for single‑cell trajectory inference by cross‑fitting held‑out genes and non‑inferiority testing. It shows that model multiplicity is large and depends more on the diversity of the model space than its size, and that per‑cell certified fate margins do not improve assignment reliability compared to baseline models. The study also identifies two robust constructions— a margin‑erosion ratio for branch‑point detection and a certification filter that reduces disagreement with clonal outcomes— that merit further investigation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 21

When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders

The paper investigates when post‑training quantization (PTQ) calibration helps or hurts text embedders, focusing on the amount of calibration (dose) and whether to calibrate at all. Across three models and 161 calibration runs at 4‑bit weight quantization, the effect ranges from significant gains to catastrophic degradation, driven mainly by the functional displacement of the quantized model. A validation‑gated abstention rule is proposed that avoids harmful calibrations while capturing most benefits, highlighting the trade‑off between safety and opportunity.

By Hyojung Han, Ryangkyung Kang, Youngeun Kim, Seung-Hun Jeon
efficiencysafety
More like this →
arXiv Machine Learning
Aug 31

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

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.

By Mehrdad Shoeibi, Niloofar Yousefi
More like this →
arXiv Computer Vision
6d ago

PRISM: Pathology Reliability In Scarce-label Medicine. A Tile-level Benchmark of Pathology Foundation Models

PRISM is a tile‑level benchmark for pathology foundation models that evaluates reliability across four dimensions: model choice, label fraction, calibration, and out‑of‑distribution transfer. It tests eight models on six datasets at six label fractions (1%–100%) with 864 linear probe runs, plus a five‑hospital Camelyon17 transfer study. The benchmark reveals four key phenomena, including the changing relationship between AUROC and calibration at low labels, collapse of linear probes on harder datasets, the impact of source‑domain labels on target calibration, and limitations of temperature scaling.

By Alicem Koyun
benchmarks
More like this →