1 citations · 3 across the 16 of their papers we have counts for
16 papers
A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts
Ihor Kendiukhov
Foundation models for astronomy are trained on survey pixels together with the catalogue products derived from those pixels. Those catalogues are incomplete at a measurable rate, a…
Ergodicity Library: A Python Toolkit for Stochastic-Process Simulation, Time-Average Diagnostics, and Agent-Based Experiments
Ihor Kendiukhov
ergodicity is an open-source Python library for computational work on stochastic dynamics, with particular emphasis on non-ergodicity, time-average behavior, heavy-tailed processes…
Exhaustive Circuit Mapping of a Single-Cell Foundation Model Reveals Massive Redundancy, Heavy-Tailed Hub Architecture, and Layer-Dependent Differentiation Control
Ihor Kendiukhov
Mechanistic interpretability of biological foundation models has relied on selective feature sampling, pairwise interaction testing, and observational trajectory analysis. Each of…
Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals
Ihor Kendiukhov
We report the discovery and extraction of a compact hematopoietic algorithm from the single-cell foundation model scGPT, to our knowledge the first biologically useful, competitive…
What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
Ihor Kendiukhov
When biological foundation models such as scGPT and Geneformer process single-cell gene expression, what geometric and topological structure forms in their internal representations…
Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence
Ihor Kendiukhov
Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain un…
Quantifying Ranking Instability Across Evaluation Protocol Axes in Gene Regulatory Network Benchmarking
Ihor Kendiukhov
Benchmark rankings are routinely used to justify scientific claims about method quality in gene regulatory network (GRN) inference, yet the stability of these rankings under plausi…
Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT
Ihor Kendiukhov
Background: Single-cell foundation models such as Geneformer and scGPT encode rich biological information, but whether this includes causal regulatory logic rather than statistical…
Multi-Dimensional Spectral Geometry of Biological Knowledge in Single-Cell Transformer Representations
Ihor Kendiukhov
Single-cell foundation models such as scGPT learn high-dimensional gene representations, but what biological knowledge these representations encode remains unclear. We systematical…
Systematic Evaluation of Single-Cell Foundation Model Interpretability Reveals Attention Captures Co-Expression Rather Than Unique Regulatory Signal
Ihor Kendiukhov
We present a systematic evaluation framework - thirty-seven analyses, 153 statistical tests, four cell types, two perturbation modalities - for assessing mechanistic interpretabili…
Scaling Laws for Masked-Reconstruction Transformers on Single-Cell Transcriptomics
Ihor Kendiukhov
Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transformers, yet their existence in s…
A Review of Developmental Interpretability in Large Language Models
Ihor Kendiukhov
This review synthesizes the nascent but critical field of developmental interpretability for Large Language Models. We chart the field's evolution from static, post-hoc analysis of…
Are LLM Belief Updates Consistent with Bayes' Theorem?
Sohaib Imran, Ihor Kendiukhov, Matthew Broerman +4
Do larger and more capable language models learn to update their "beliefs" about propositions more consistently with Bayes' theorem when presented with evidence in-context? To test…
Risk Aversion in Non-Ergodic Systems
Ihor Kendiukhov
We show in a simulation when economic agents are subject to evolution (random change and selection based on the success in the estimation of the result of the gamble) they acquire…
Present Value of the Future Consumer Goods Multiplier
Ihor Kendiukhov
In this paper, we derive a formula for the present value of future consumer goods multiplier based on the assumption that a constant share of investment in the production of consum…
A Finite-Time Technological Singularity Model With Artificial Intelligence Self-Improvement
Ihor Kendiukhov
Recent advances in the development of artificial intelligence, technological progress acceleration, long-term trends of macroeconomic dynamics increase the relevance of technologic…