SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.11998 · 2024

Learning Useful Representations of Recurrent Neural Network Weight Matrices

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2403.11998.json · badge: /api/ran/2403.11998.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
vincentherrmann/rnn-weights-representation-learning canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
conditional_args Ran
ran; our contract draft was wrong, not the code
vincentherrmann/rnn-weights-representation-learning/rnn_weights_representation_learning/training_script.py
pointer only (licence: NONE) · get_code("d6bf9b1d6db6bedd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vincentherrmann/rnn-weights-representation-learning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

mlp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vincentherrmann/rnn-weights-representation-learning/rnn_weights_representation_learning/modules_rnn_encoders.py
pointer only (licence: NONE) · get_code("173e195e1fe036cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vincentherrmann/rnn-weights-representation-learning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

task_entropy_criterion Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vincentherrmann/rnn-weights-representation-learning/rnn_weights_representation_learning/dataset_classes.py
pointer only (licence: NONE) · get_code("745af9db259597d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vincentherrmann/rnn-weights-representation-learning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

task_random_criterion Ran
ran, honoured the contract we drafted
vincentherrmann/rnn-weights-representation-learning/rnn_weights_representation_learning/dataset_classes.py
pointer only (licence: NONE) · get_code("8db20376ac400c5c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vincentherrmann/rnn-weights-representation-learning when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that facilitate RNN analysis as well as downstream tasks? While the mechanistic approach directly looks at some RNN's weights to predict its behavior, the functionalist approach analyzes its overall functionality-specifically, its input-output mapping. We consider several mechanistic approaches for RNN weights and adapt the permutation equivariant Deep Weight Space layer for RNNs. Our two novel functionalist approaches extract information from RNN weights by 'interrogating' the RNN through probing inputs. We develop a theoretical framework that demonstrates conditions under which the functionalist approach can generate rich representations that help determine RNN behavior. We release the first two 'model zoo' datasets for RNN weight representation learning. One consists of generative models of a class of formal languages, and the other one of classifiers of sequentially processed MNIST digits. With the help of an emulation-based self-supervised learning technique we compare and evaluate the different RNN weight encoding techniques on multiple downstream applications. On the most challenging one, namely predicting which exact task the RNN was trained on, functionalist approaches show clear superiority.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.11998")
get_code_for_paper("2403.11998")
have("2403.11998")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.11998.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.11998.svg)](https://syntology.ai/paper/2403.11998)

Connect an agent — have() is free.