Article

Recursive Transport Topology: Diagnostics, Tunable Abstraction, and Latent Enhancement in Biological and World-Model Representations

2026-06-12

Abstract excerpt

<title>Abstract</title> <p>Recursive Indexing (RIX) proposes that useful representation geometry should be organized before manifold formation through recursive transport topology. Building on Phase I results in protein fitness landscapes, we demonstrate that recursive transport metrics generalize across seven diverse biological systems, prospectively predict regime-specific perturbation responses, maintain favor...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 955579f6-dc8c-53c5-8a30-13bed512fb47
DOI: 10.21203/rs.3.rs-9997591/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Recursive Transport Topology: Diagnostics, Tunable Abstraction, and Latent Enhancement in Biological and World-Model RepresentationsDOI 10.21203/rs.3.rs-9997591/v1Read

Do Single-Cell Models Learn Real Biology? An Empirical Analysis of Physical Interaction Signal in Pretrained scGPT Gene EmbeddingsSemantic proximity Read

∑ <sub>0</sub> –EvoCell: An AI-Native Ontology that Unifies Evolutionary and Cell Biology in Latent SpaceSemantic proximity Read

Geometric Representations of Knowledge Inside Biological Large Language Models: an Empirical AnalysisSemantic proximity Read

Performance Attribution in pLM-Based Biological Relation PredictionSemantic proximity Read

Mechanistic Interpretability of Biological Foundation Models: An Empirical Analysis of scGPT Gene-Embedding GeometrySemantic proximity Read

Virtual-cell models compress unseen intervention geometry through a target-specific generalization bottleneckSemantic proximity Read

Inhibitory Knowledge Flow from E-Communities of Practice Stabilizes Causal Gene Circuit Architectures in Single-Cell Foundation ModelsSemantic proximity Read

Detecting and quantifying overparametrization in RNA language models with REDIALSemantic proximity Read

Safeguarding open-weight genomic foundation models through weight lockingSemantic proximity Read

Overcoming Topology Bias and Cold-Start Limitations in Drug Repurposing: A Clinical-Outcome-Aligned LLM FrameworkSemantic proximity Read

Inferring transporter specificity through language model–guided graph learningSemantic proximity Read

Highly designable phenotypes and mutational buffers emerge from a systematic mapping between network topology and dynamic output.Semantic proximity Read