SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.13166 · ICLR · 2025

An Evolved Universal Transformer Memory

Edoardo Cetin, Yujin Tang, Qi Sun, Tianyu Zhao

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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, 3 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 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/2410.13166.json · badge: /api/ran/2410.13166.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
SakanaAI/evo-memory canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_recency Ran
ran, honoured the contract we drafted
SakanaAI/evo-memory/memory_policy/base_dynamic.py
pointer only (licence: NONE) · get_code("8979b56a0788125e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

compute_recency_scores Ran
ran; our contract draft was wrong, not the code
SakanaAI/evo-memory/memory_policy/base_dynamic.py
pointer only (licence: NONE) · get_code("b138114d7116560c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

convert_to_tensor Ran
ran, violated the contract we drafted
SakanaAI/evo-memory/memory_policy/deep_embedding.py
pointer only (licence: NONE) · get_code("aa010c2bd0aa74b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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_cma_defaults Ran
ran; our contract draft was wrong, not the code
SakanaAI/evo-memory/memory_evolution/cma_es.py
pointer only (licence: NONE) · get_code("a6c6ee847acad66b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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_property_list_from_elements Ran
ran; our contract draft was wrong, not the code
SakanaAI/evo-memory/memory_policy/base_deep_components.py
pointer only (licence: NONE) · get_code("36754005e03e2458")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

reduce_stats Ran
ran; our contract draft was wrong, not the code
SakanaAI/evo-memory/memory_policy/deep.py
pointer only (licence: NONE) · get_code("82650da99214bdf2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

stat_fn_list Ran
ran; our contract draft was wrong, not the code
SakanaAI/evo-memory/memory_policy/deep.py
pointer only (licence: NONE) · get_code("941a06561780b35a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

stat_fn_tensor Ran
ran; our contract draft was wrong, not the code
SakanaAI/evo-memory/memory_policy/deep.py
pointer only (licence: NONE) · get_code("ed9673e65d4694aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

threshold_score_idxs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SakanaAI/evo-memory/memory_policy/base_dynamic.py
pointer only (licence: NONE) · get_code("5033508c5b925cb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

true_for_all Ran
ran, violated the contract we drafted
SakanaAI/evo-memory/memory_policy/base_deep_components.py
pointer only (licence: NONE) · get_code("998a8e8e5f062104")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

true_for_any Ran
ran, violated the contract we drafted
SakanaAI/evo-memory/memory_policy/base_deep_components.py
pointer only (licence: NONE) · get_code("62e579d3352bdb8e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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.

full_eigen_decomp Not yet run
unverified (harvested, no recorded run)
SakanaAI/evo-memory/memory_evolution/cma_es.py
pointer only (licence: NONE) · get_code("0c0fa69e90becc08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SakanaAI/evo-memory 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 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 12 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

Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable to any model using selfattention as they condition exclusively on the values in the produced attention matrices. Learning NAMMs on a small set of problems, we achieve substantial performance improvements across multiple long-context benchmarks while cutting the model's input contexts up to a fraction of the original sizes. We show the generality of our conditioning enables zero-shot transfer of NAMMs trained only on language to entirely new transformer architectures even across input modalities, with their benefits carrying over to vision and reinforcement learning. Our source code is available at https://github.com/SakanaAI/evo-memory.

For agents

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

get_harvested_code_for_paper("2410.13166")
get_code_for_paper("2410.13166")
have("2410.13166")

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

curl https://syntology.ai/api/ran/2410.13166.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.13166.svg)](https://syntology.ai/paper/2410.13166)

Connect an agent — have() is free.