SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.00405 · 2021

Avalanche: an End-to-End Library for Continual Learning

arXiv · PDF · Open in the Atlas

Code that ran

13 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; 0 honoured the contract we drafted, 0 violated it and 6 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/2104.00405.json · badge: /api/ran/2104.00405.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
lrzpellegrini/avalanche community (classifier label)
classifier basis not recorded on the link
10 ran · 0 no recorded run
continualai/avalanche-rl community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
AE_loss Ran
ran; our contract draft was wrong, not the code
lrzpellegrini/avalanche/avalanche/models/expert_gate.py
code served (permissive licence) · get_code("2f71e37b6d375654")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for target and reconstruction
# Using distinct dimensions: batch=2, features=4
target = torch.randn(2, 4)
reconstruction = torch.randn(2, 4)

ARGS = {
    "target": target,
    "reconstruction": reconstruction,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
VAE_loss Ran
ran on a synthesized input
lrzpellegrini/avalanche/avalanche/models/generator.py
code served (permissive licence) · get_code("e862522ea659bb09")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
input_dim = 4

# X: Original input batch
X = torch.randn(batch_size, input_dim)

# X_hat: Reconstructed input (same shape as X)
X_hat = torch.randn(batch_size, input_dim)

# mean: Mean of the VAE output distribution
mean = torch.randn(batch_size, input_dim)

# logvar: Log variance of the VAE output distribution
logvar = torch.randn(batch_size, input_dim)

# forward_output: Triplet of (X_hat, mean, logvar)
forward_output = (X_hat, mean, logvar)

ARGS = {
    'X': X,
    'forward_output': forward_output
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
batch_norm Ran
ran on a synthesized input
lrzpellegrini/avalanche/avalanche/models/icarl_resnet.py
code served (permissive licence) · get_code("4a3907baf03af341")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned BatchNorm2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.nn import BatchNorm2d

torch.manual_seed(0)

ARGS = {
    "num_channels": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BatchNorm2d — a BatchNorm2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BatchNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compare_keys Ran
ran; our contract draft was wrong, not the code
lrzpellegrini/avalanche/avalanche/models/dynamic_optimizers.py
code served (permissive licence) · get_code("4468c94aca4d060f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function compares keys between two dictionaries
# It uses .keys() method on both dicts and performs set operations
# No actual values are accessed, only keys matter

old_dict = {
    "key1": torch.randn(2, 4),
    "key2": "value2",
    "key3": 42,
    "shared_key": [1, 2, 3]
}

new_dict = {
    "shared_key": torch.randn(3, 5),
    "key4": "new_value",
    "key5": {"nested": "dict"},
    "key1": None
}

ARGS = {
    "old_dict": old_dict,
    "new_dict": new_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
conv3x3 Ran
ran on a synthesized input
lrzpellegrini/avalanche/avalanche/models/icarl_resnet.py
code served (permissive licence) · get_code("f522c857bf857a12")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Conv2d. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.nn import Conv2d

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
copy_params_dict Ran
ran; our contract draft was wrong, not the code
continualai/avalanche-rl/avalanche_rl/training/utils.py
code served (permissive licence) · get_code("ebe8ff761cc06550")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small model with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Initialize gradients by doing a forward/backward pass
x = torch.randn(2, 4)
y = torch.randn(2, 2)
output = model(x)
loss = nn.MSELoss()(output, y)
loss.backward()

ARGS = {
    "model": model,
    "copy_grad": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
deprecated Ran
ran; our contract draft was wrong, not the code
lrzpellegrini/avalanche/avalanche/_annotations.py
code served (permissive licence) · get_code("667a50347702db96")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import warnings
import functools
import inspect


def deprecated(version: float, reason: str):
    """Decorator to mark functions as deprecated.

    Emits a warning when the function is used.

    :param version: when it will be removed
    :param reason: motivation for deprecation, possibly with suggested
        alternative
    :return:
    """

    def decorator(func):
        if inspect.isclass(func):
            msg_prefix = 'Call to deprecated class {name}'
        else:
            msg_prefix = 'Call to deprecated function {name}'
        msg_suffix = ' (removal in version {version}: {reason})'
        msg = msg_prefix + msg_suffix
        if func.__doc__ is None:
            func.__doc__ = ''
        else:
            func.__doc__ += '\n\n'
        func.__doc__ += 'Warning: Deprecated' + msg_suffix.format(name=func.__name__, version=version, reason=reason)

        @functools.wraps(func)
        def wrapper(*args, **kwargs):
            warnings.simplefilter('always', DeprecationWarning)
            warnings.warn(msg.format(name=func.__name__, version=version, reason=reason), category=DeprecationWarning, stacklevel=2)
            warnings.simplefilter('default', DeprecationWarning)
            return func(*args, **kwargs)
        return wrapper
    return decorator


# Test function to decorate
def sample_function():
    """This is a sample function."""
    return "result"


# Setup arguments for the deprecated decorator
ARGS = {
    'version': 2.0,
    'reason': 'Use new_function() instead for better performance'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
experimental Ran
ran; our contract draft was wrong, not the code
lrzpellegrini/avalanche/avalanche/_annotations.py
code served (permissive licence) · get_code("9bd77285b9ea9767")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import functools
from typing import Optional

def experimental(reason: Optional[str]=None):
    """Decorator for experimental API.

    Experimental APIs are newer functionality.
    They are well tested, but due to their novelty there may be minor bugs
    or their intergace may still change in the next releases.

    It can be used to decorate methods.

    .. code-block:: python
        from avalanche._annotations import ExperimentalAPI
        @DeveloperAPI
        def shining_new_method():
            print("Hello, world!")

    :param reason: a message to append to the documentation explaining
        the motivation for the experimental tag.
    :return:
    """
    if reason is None:
        reason = ''

    def decorator(func):
        if func.__doc__ is None:
            func.__doc__ = ''
        else:
            func.__doc__ += '\n\n'
        func.__doc__ += 'Warning: Experimental API. ' + reason

        @functools.wraps(func)
        def wrapper(*args, **kwargs):
            return func(*args, **kwargs)
        return wrapper
    return decorator


# Setup code to construct valid arguments for the experimental function

ARGS = {
    'reason': 'This API is still under active development and may change in future releases.'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_all_dataset Ran
ran on a synthesized input
continualai/avalanche-rl/avalanche_rl/training/utils.py
code served (permissive licence) · get_code("2b7620b46c538347")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.utils.data import Dataset

torch.manual_seed(0)

class SimpleDataset(Dataset):
    def __init__(self, size=8, include_task_labels=False):
        self.size = size
        self.include_task_labels = include_task_labels
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        x = torch.randn(4)
        y = torch.tensor(idx % 2)
        if self.include_task_labels:
            t = torch.tensor(idx % 3)
            return (x, y, t)
        else:
            return (x, y)

dataset = SimpleDataset(size=8, include_task_labels=False)

ARGS = {
    "dataset": dataset,
    "num_workers": 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_icarl_net Ran
ran on a synthesized input
lrzpellegrini/avalanche/avalanche/models/icarl_resnet.py
code served (permissive licence) · get_code("6631136159e03f28")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned IcarlNet. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Construct the arguments for make_icarl_net
ARGS = {
    'num_classes': 10,
    'n': 5,
    'c': 3,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type IcarlNet — a IcarlNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a IcarlNet output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reset_optimizer Ran
ran on a synthesized input
lrzpellegrini/avalanche/avalanche/models/dynamic_optimizers.py
code served (permissive licence) · get_code("b1dc2f5c2df88238")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from collections import defaultdict
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model with named parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

# Create an optimizer with a single parameter group
optimizer = SGD(model.parameters(), lr=0.01)

ARGS = {
    'optimizer': optimizer,
    'model': model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
update_optimizer Ran
ran; our contract draft was wrong, not the code
lrzpellegrini/avalanche/avalanche/models/dynamic_optimizers.py
code served (permissive licence) · get_code("319194e1151e6dc5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Linear(4, 3)
        self.layer2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.layer2(self.layer1(x))

# Create initial model and optimizer
model = SimpleModel()
optimizer = SGD(model.parameters(), lr=0.01)

# Create the old optimized params dict (what was being optimized before)
old_params = {}
for name, param in model.named_parameters():
    old_params[name] = param

# Now simulate a model adaptation scenario where:
# - Some parameters remain (layer1.weight, layer1.bias)
# - Some parameters are removed (layer2.weight, layer2.bias)
# - New parameters are added

# Create a modified model for the new task
model_new = SimpleModel()

# Get new parameters but exclude some and add new ones
new_params = {}
for name, param in model_new.named_parameters():
    if name in ['layer1.weight', 'layer1.bias']:
        # Keep old parameter objects to simulate "in_both"
        new_params[name] = old_params[name]

# Add a new parameter not in old_params
new_param = nn.Parameter(torch.randn(2, 3))
new_params['layer3.weight'] = new_param

ARGS = {
    'optimizer': optimizer,
    'new_params': new_params,
    'optimized_params': old_params,
    'reset_state': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
zerolike_params_dict Ran
ran; our contract draft was wrong, not the code
continualai/avalanche-rl/avalanche_rl/training/utils.py
code served (permissive licence) · get_code("8c5d045f631021ea")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple model with a few parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_all_atari_envs_id Not yet run
unverified (harvested, no recorded run)
continualai/avalanche-rl/avalanche_rl/benchmarks/rl_benchmark_generators.py
code served (permissive licence) · get_code("231f4993e819471c")
How it ran

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, 10 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 10 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.

FunctionAlso present inEarliest-datedOthers named
batch_norm 2 other papers
2 later
2205.13452 (2022-05)
Continual evaluation for lifelong learning: Identifying the stability gap
2304.00933 (2023-04)
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
conv3x3 2 other papers
2 later
2205.13452 (2022-05)
Continual evaluation for lifelong learning: Identifying the stability gap
2304.00933 (2023-04)
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
make_icarl_net 2 other papers
2 later
2205.13452 (2022-05)
Continual evaluation for lifelong learning: Identifying the stability gap
2304.00933 (2023-04)
Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting
AE_loss 1 other paper
1 later
2311.04898 (2023-11)
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
compare_keys 1 other paper
1 later
2311.04898 (2023-11)
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
copy_params_dict 1 other paper
1 later
2306.14884 (2023-06)
Learning to Modulate pre-trained Models in RL
deprecated 1 other paper
1 later
2311.04898 (2023-11)
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
experimental 1 other paper
1 later
2311.04898 (2023-11)
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
update_optimizer 1 other paper
1 later
2311.04898 (2023-11)
Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
zerolike_params_dict 1 other paper
1 later
2306.14884 (2023-06)
Learning to Modulate pre-trained Models in RL

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

Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.

For agents

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

get_harvested_code_for_paper("2104.00405")
get_code_for_paper("2104.00405")
have("2104.00405")

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

curl https://syntology.ai/api/ran/2104.00405.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.00405.svg)](https://syntology.ai/paper/2104.00405)

Connect an agent — have() is free.