PerturbPFN
PerturbPFN is a transformer trained only on simulated perturbation episodes that, given observed responses to other perturbations in context, infers a latent gene graph, sparse intervention targets and strengths and rolls them through a causal decoder to predict the expression distribution under a new perturbation.
Results are recorded on linked configurations and versions of this model. Their settings and evaluations are kept separate below.
Results on linked records
This model has no results of its own in this release. 2 linked records have results. They are not assigned to the underlying model: each record keeps its own settings and evaluations, and its scores are on its own page.
- PerturbPFN step-3100 checkpoint, in-context forward pass Configuration · configuration of this model · 2 evaluations · 17 results
- PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregation Configuration · configuration of this model · 1 evaluation · 5 results
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
PerturbPFN has no ranked result on a use-case protocol in this release.
Recorded parameters: Not recorded. Licence: Not recorded.
Model Capabilities & Hardware Requirements
Deployment facts recorded for PerturbPFN. Fields the record does not carry are marked not recorded.
Evaluated Checkpoint: As described in arXiv:2607.23447v1; one checkpoint is reported, step 3100 of a 3,500-step run with seed 17
Use this model
How it works, versions and access
Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this model. Consult the linked sources and evaluation records below.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
1 source record and release history
- PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling (arXiv:2607.23447v1) · Original source · arXiv v1, submitted 2026-07-26
Technical metadata and record identifiers
Technical metadata for this record is tracked under stable ID perturbpfn-20261115-model-perturbpfn.
Source locator: Abstract; Sections 2.2 to 2.5; Appendices A and B; Tables 6 and 7
Related records
- subject: PerturbPFN: access as stated in the preprint
- subject: PerturbPFN: gene panel size
- subject: PerturbPFN: inputs and outputs
- subject: PerturbPFN: size and training compute
- subject: PerturbPFN: stated limitations
- subject: PerturbPFN: synthetic-only training
- configuration of: PerturbPFN step-3100 checkpoint, in-context forward pass
- configuration of: PerturbPFN step-3100 checkpoint, GeneRNIB panel aggregation
How to cite
PerturbPFN. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/model/perturbpfn-20261115-model-perturbpfn/
Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.
The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence