SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.04264 · ICLR · 2024

Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement

Nayara Fonseca, Soufiane Hayou, Yoonsoo Nam, Seok Lee, Chris Mingard, Ard Louis, Niclas Goring, Ouns Harzli, Abdurrahman Hadi Erturk

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2410.04264.json · badge: /api/ran/2410.04264.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
yoonsoonam119/PrEF community
Papers with Code archive
3 ran · 2 no recorded run
FunctionStatusWhere it lives
Y_Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
yoonsoonam119/PrEF/src/pref.py
pointer only (licence: NONE) · get_code("46918cd32fd307fd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yoonsoonam119/PrEF 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.

get_d_lr Ran
ran, honoured the contract we drafted
yoonsoonam119/PrEF/src/pref.py
pointer only (licence: NONE) · get_code("c001ee0375316a97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yoonsoonam119/PrEF 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.

smart_dim Ran
ran, honoured the contract we drafted
yoonsoonam119/PrEF/src/pref.py
pointer only (licence: NONE) · get_code("c6bfb30cf38ffb9e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yoonsoonam119/PrEF 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.

PrEF Not yet run
unverified (harvested, no recorded run)
yoonsoonam119/PrEF/src/pref.py
pointer only (licence: NONE) · get_code("08345f68e65ac3c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yoonsoonam119/PrEF 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. No invocation recorded.

center Not yet run
unverified (harvested, no recorded run)
yoonsoonam119/PrEF/src/pref.py
pointer only (licence: NONE) · get_code("b38de58bd1947c8f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yoonsoonam119/PrEF 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. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Dynamic feature transformation (the rich regime) does not always align with predictive performance (better representation), yet accuracy is often used as a proxy for richness, limiting analysis of their relationship. We propose a computationally efficient, performance-independent metric of richness grounded in the low-rank bias of rich dynamics, which recovers neural collapse as a special case. The metric is empirically more stable than existing alternatives and captures known lazy-torich transitions (e.g., grokking) without relying on accuracy. We further use it to examine how training factors (e.g., learning rate) relate to richness, confirming recognized assumptions and highlighting new observations (e.g., batch normalization promotes rich dynamics). An eigendecomposition-based visualization is also introduced to support interpretability, together providing a diagnostic tool for studying the relationship between training factors, dynamics, and representations.

For agents

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

get_harvested_code_for_paper("2410.04264")
get_code_for_paper("2410.04264")
have("2410.04264")

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

curl https://syntology.ai/api/ran/2410.04264.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.04264.svg)](https://syntology.ai/paper/2410.04264)

Connect an agent — have() is free.