SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.02596 · ICML · 2024

Slow and Steady Wins the Race Maintaining Plasticity with Hare and Tortoise Networks

Clare Lyle, Jaegul Choo, Hojoon Lee, Hyunseung Kim, Donghu Kim, Hyeonseo Cho, Dugki Min

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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, 1 violated it and 1 has no contract verdict; 9 failures of our instrument; 2 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/2406.02596.json · badge: /api/ran/2406.02596.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
dojeon-ai/hare-tortoise canonical (classifier label)
classifier basis: census
12 ran · 2 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dojeon-ai/hare-tortoise/src/common/metrics.py
pointer only (licence: NONE) · get_code("642233ee988813eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

all_subclasses Ran
ran on a synthesized input
dojeon-ai/hare-tortoise/src/common/class_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from dojeon-ai/atari-pb, is pointer only (licence: NONE) · get_code("d56ca611b75a2f1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

figure_to_array Ran
ran, honoured the contract we drafted
dojeon-ai/hare-tortoise/src/common/vis_utils.py
pointer only (licence: NONE) · get_code("8b9828a518d4865a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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_all_submodules Ran
ran; our contract draft was wrong, not the code
dojeon-ai/hare-tortoise/src/common/class_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from dojeon-ai/atari-pb, is pointer only (licence: NONE) · get_code("9474fe78e7e7660d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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_grad_norm_stats Ran
ran; our contract draft was wrong, not the code
dojeon-ai/hare-tortoise/src/common/metrics.py
pointer only (licence: NONE) · get_code("d2958b7e3a064ef5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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_rank Ran
ran; our contract draft was wrong, not the code
dojeon-ai/hare-tortoise/src/common/metrics.py
pointer only (licence: NONE) · get_code("ed281db32072a644")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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_redo_masks Ran
ran; our contract draft was wrong, not the code
dojeon-ai/hare-tortoise/src/common/redo.py
pointer only (licence: NONE) · get_code("cbc7964ba3c9b796")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

init_activation Ran
ran; our contract draft was wrong, not the code
dojeon-ai/hare-tortoise/src/models/layers.py
pointer only (licence: NONE) · get_code("ee5f1b736da9bd08")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

init_normalization Ran
ran; our contract draft was wrong, not the code
dojeon-ai/hare-tortoise/src/models/layers.py
pointer only (licence: NONE) · get_code("43a026a3ea7b4e3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

str2bool Ran
ran, violated the contract we drafted
dojeon-ai/hare-tortoise/src/common/class_utils.py
pointer only (licence: NONE); the stored copy get_code serves, from dojeon-ai/atari-pb, is pointer only (licence: NONE) · get_code("f60e944791ee0f26")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

visualize_plot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dojeon-ai/hare-tortoise/src/common/vis_utils.py
pointer only (licence: NONE) · get_code("fa49589233206702")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

visualize_trisurf Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dojeon-ai/hare-tortoise/src/common/vis_utils.py
pointer only (licence: NONE) · get_code("cca93078047c7f04")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

compose_transform Not yet run
unverified (harvested, no recorded run)
dojeon-ai/hare-tortoise/src/datasets/data_aug.py
pointer only (licence: NONE) · get_code("0ba0a0301cc98289")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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.

reset_dormant_neurons Not yet run
unverified (harvested, no recorded run)
dojeon-ai/hare-tortoise/src/common/redo.py
pointer only (licence: NONE) · get_code("42859fc08181728c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dojeon-ai/hare-tortoise 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 3 the same month, 0 later) and 11 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.

FunctionAlso present inEarliest-datedOthers named
all_subclasses 1 other paper
1 the same month
2406.06037 (2024-06)
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
get_all_submodules 1 other paper
1 the same month
2406.06037 (2024-06)
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
str2bool 1 other paper
1 the same month
2406.06037 (2024-06)
Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning

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

This study investigates the loss of generalization ability in neural networks, revisiting warmstarting experiments from Ash & Adams (2020). Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining trainability provide limited benefits to generalization. While reinitializing the network can be effective, it also risks losing valuable prior knowledge. To this end, we introduce the Hare & Tortoise, inspired by the brain's complementary learning system. Hare & Tortoise consists of two components: the Hare network, which rapidly adapts to new information analogously to the hippocampus, and the Tortoise network, which gradually integrates knowledge akin to the neocortex. By periodically reinitializing the Hare network to the Tortoise's weights, our method preserves plasticity while retaining general knowledge. Hare & Tortoise can effectively maintain the network's ability to generalize, which improves advanced reinforcement learning algorithms on the Atari-100k benchmark. The code is available at https://github. com/dojeon-ai/hare-tortoise.

For agents

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

get_harvested_code_for_paper("2406.02596")
get_code_for_paper("2406.02596")
have("2406.02596")

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

curl https://syntology.ai/api/ran/2406.02596.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.02596.svg)](https://syntology.ai/paper/2406.02596)

Connect an agent — have() is free.