SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.04744 · 2024

Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-21; 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/2402.04744.json · badge: /api/ran/2402.04744.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
abhibambhaniya/progressive_gradient_flow_nm_sparsity canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
count_params Ran
ran, honoured the contract we drafted
abhibambhaniya/progressive_gradient_flow_nm_sparsity/benchmark.py
code served (permissive licence) · get_code("410bffb8a07b52e3")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T23:28:41Z). 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)

# Build 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()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
checkpoint_metric Ran
ran, honoured the contract we drafted
abhibambhaniya/progressive_gradient_flow_nm_sparsity/avg_checkpoints.py
code served (permissive licence) · get_code("33bca8cbc866bf64")
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 float, 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 tempfile
import os

torch.manual_seed(0)

# Create a temporary checkpoint file with a 'metric' key
with tempfile.NamedTemporaryFile(delete=False, suffix='.pt') as f:
    checkpoint_path = f.name
    checkpoint_data = {
        'metric': 0.95,
        'model_state': torch.randn(2, 4),
        'epoch': 10
    }
    torch.save(checkpoint_data, checkpoint_path)

ARGS = {
    'checkpoint_path': checkpoint_path
}
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 float, 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
cmd_from_args Ran
ran; our contract draft was wrong, not the code
abhibambhaniya/progressive_gradient_flow_nm_sparsity/bulk_runner.py
code served (permissive licence) · get_code("e69e9b0108bef81c")
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 os
import sys
from argparse import Namespace

class MockArgs:
    def __init__(self, no_python=False, module=False, script='test.py', script_args=None):
        self.no_python = no_python
        self.module = module
        self.script = script
        self.script_args = script_args if script_args is not None else []

ARGS = {
    'args': MockArgs(
        no_python=False,
        module=False,
        script='example.py',
        script_args=['--arg1', 'value1', '--arg2', 'value2']
    )
}
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 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
cuda_timestamp Ran
ran, honoured the contract we drafted
abhibambhaniya/progressive_gradient_flow_nm_sparsity/benchmark.py
code served (permissive licence) · get_code("50d653ee6a59955c")
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) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 time
import torch
import torch.nn.parallel

torch.manual_seed(0)

ARGS = {
    "sync": False,
    "device": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
hard_sigmoid_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations_jit.py
code served (permissive licence) · get_code("91c27523dde7eb4a")
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 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 hard_sigmoid_jit takes:
# - x: a tensor (used with clamp, div operations)
# - inplace: a bool (default False)

# Create a small tensor for x
x = torch.randn(2, 4)

# Set inplace parameter
inplace = False

ARGS = {
    "x": x,
    "inplace": inplace,
}
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 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
map_mx_to_torch_model Ran
ran; our contract draft was wrong, not the code
abhibambhaniya/progressive_gradient_flow_nm_sparsity/convert/convert_from_mxnet.py
code served (permissive licence) · get_code("5bed58ca17652913")
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 str. 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

def map_mx_to_torch_model(mx_name):
    torch_name = mx_name.lower()
    if torch_name.startswith('se_'):
        torch_name = torch_name.replace('se_', 'se')
    elif torch_name.startswith('senet_'):
        torch_name = torch_name.replace('senet_', 'senet')
    elif torch_name.startswith('inceptionv3'):
        torch_name = torch_name.replace('inceptionv3', 'inception_v3')
    torch_name = 'gluon_' + torch_name
    return torch_name

ARGS = {
    'mx_name': 'SE_ResNet50'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
mish Ran
ran; our contract draft was wrong, not the code
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations.py
code served (permissive licence) · get_code("801c85b8903bfff5")
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 2, dtype family float, shape (2, 4) 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.functional as F

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    'x': x,
    'inplace': 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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
mish_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations_jit.py
code served (permissive licence) · get_code("14eddd8cc4c65fe0")
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 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
from torch.nn import functional as F

torch.manual_seed(0)

# Create a small input tensor
x = torch.randn(2, 4)

# Create the ARGS dictionary with all parameters
ARGS = {
    "x": x,
    "_inplace": 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 Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
sigmoid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations.py
code served (permissive licence) · get_code("d83b6ecf3cdc1d6a")
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 2, dtype family float, shape (2, 4) 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 a small tensor for the sigmoid function to operate on
x = torch.randn(2, 4)

# Define ARGS mapping all parameters to values
ARGS = {
    "x": x,
    "inplace": 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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
swish Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations.py
code served (permissive licence) · get_code("717e4d22b6d103e6")
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 2, dtype family float, shape (2, 4) 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

torch.manual_seed(0)

# Create a small tensor for the swish function
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "inplace": 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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
swish_jit Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations_jit.py
code served (permissive licence) · get_code("8e341f8585b3fe94")
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 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)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Define ARGS with all parameters for swish_jit
ARGS = {
    'x': x,
    'inplace': 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 Tensor, ndim 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
swish_jit_bwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations_me.py
code served (permissive licence) · get_code("ccf59d4aa2ccacdb")
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 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)

# Create small test tensors
x = torch.randn(2, 4, requires_grad=True)
grad_output = torch.randn(2, 4)

ARGS = {
    "x": x,
    "grad_output": grad_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 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
swish_jit_fwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations_me.py
code served (permissive licence) · get_code("2d53e47b891cd927")
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 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 swish_jit_fwd takes a single tensor x and applies swish activation
# (element-wise multiplication with sigmoid)
# We need to provide a small tensor as input

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
swish_me Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/timm/layers/activations_me.py
code served (permissive licence) · get_code("51a2f9920a170144")
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 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)

# Create a small tensor for input
# The function applies SwishJitAutoFn which expects a tensor
x = torch.randn(2, 4, requires_grad=True)

# inplace parameter is defined but not actually used in the function body
inplace = False

ARGS = {
    'x': x,
    'inplace': inplace,
}
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 2, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
timestamp Ran
ran, honoured the contract we drafted
abhibambhaniya/progressive_gradient_flow_nm_sparsity/benchmark.py
code served (permissive licence) · get_code("475160c5a1a1225a")
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) and returned float, 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 time

def timestamp(sync=False):
    return time.perf_counter()

ARGS = {
    "sync": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 float, 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
clean_checkpoint Not yet run
unverified (harvested, no recorded run)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/clean_checkpoint.py
code served (permissive licence) · get_code("8024519a2a934824")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
abhibambhaniya/progressive_gradient_flow_nm_sparsity/validate.py
code served (permissive licence) · get_code("dddaf76c153d839d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 15 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 9 the same month, 12 later) and 2 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
count_params 10 other papers
8 dated earlier, 2 later
2108.01390 (2021-08)
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
2201.09792 (2022-01)
Patches Are All You Need?
ijcai2023_0106 (2023 (year only))
SWAT: Spatial Structure Within and Among Tokens
and 7 more not named here
cuda_timestamp 10 other papers
8 dated earlier, 2 later
2108.01390 (2021-08)
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
2201.09792 (2022-01)
Patches Are All You Need?
ijcai2023_0106 (2023 (year only))
SWAT: Spatial Structure Within and Among Tokens
and 7 more not named here
swish 10 other papers
5 dated earlier, 2 the same month, 3 later
2207.14676 (2022-07)
Global-Local Self-Distillation for Visual Representation Learning
Lee_BAAM_Monocular_3D_Pose_and_Shape_Reconstruction_With_Bi-Contextual_Attention_CVPR_2023_paper (2023 (year only))
BAAM: Monocular 3D pose and shape reconstruction with bi-contextual attention module and attention-guided modeling
2308.13177 (2023-08)
How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection
and 7 more not named here
timestamp 10 other papers
8 dated earlier, 2 later
2108.01390 (2021-08)
Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer
2201.09792 (2022-01)
Patches Are All You Need?
ijcai2023_0106 (2023 (year only))
SWAT: Spatial Structure Within and Among Tokens
and 7 more not named here
mish 7 other papers
2 dated earlier, 2 the same month, 3 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 4 more not named here
sigmoid 7 other papers
2 dated earlier, 2 the same month, 3 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 4 more not named here
hard_sigmoid_jit 6 other papers
2 dated earlier, 2 the same month, 2 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 3 more not named here
mish_jit 6 other papers
2 dated earlier, 2 the same month, 2 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 3 more not named here
swish_jit 6 other papers
2 dated earlier, 2 the same month, 2 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 3 more not named here
checkpoint_metric 4 other papers
4 dated earlier
2201.09792 (2022-01)
Patches Are All You Need?
2305.17190 (2023-05)
Multiplication-Free Transformer Training via Piecewise Affine Operations
2305.17205 (2023-05)
Ghost Noise for Regularizing Deep Neural Networks
and 1 more not named here
swish_jit_bwd 4 other papers
1 dated earlier, 2 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
and 1 more not named here
swish_jit_fwd 4 other papers
1 dated earlier, 2 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
and 1 more not named here
swish_me 4 other papers
1 dated earlier, 2 the same month, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
and 1 more not named here
map_mx_to_torch_model 2 other papers
2 dated earlier
2201.09792 (2022-01)
Patches Are All You Need?
2401.17992 (2024-01)
Multilinear Operator Networks
cmd_from_args 1 other paper
1 dated earlier
2401.17992 (2024-01)
Multilinear Operator Networks

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 2026-11-21.

Repositories linked to this paper

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

Abstract

N:M Structured sparsity has garnered significant interest as a result of relatively modest overhead and improved efficiency. Additionally, this form of sparsity holds considerable appeal for reducing the memory footprint owing to their modest representation overhead. There have been efforts to develop training recipes for N:M structured sparsity, they primarily focus on low-sparsity regions ($\sim$50\%). Nonetheless, performance of models trained using these approaches tends to decline when confronted with high-sparsity regions ($>$80\%). In this work, we study the effectiveness of existing sparse training recipes at \textit{high-sparsity regions} and argue that these methods fail to sustain the model quality on par with low-sparsity regions. We demonstrate that the significant factor contributing to this disparity is the presence of elevated levels of induced noise in the gradient magnitudes. To mitigate this undesirable effect, we employ decay mechanisms to progressively restrict the flow of gradients towards pruned elements. Our approach improves the model quality by up to 2$\%$ and 5$\%$ in vision and language models at high sparsity regime, respectively. We also evaluate the trade-off between model accuracy and training compute cost in terms of FLOPs. At iso-training FLOPs, our method yields better performance compared to conventional sparse training recipes, exhibiting an accuracy improvement of up to 2$\%$. The source code is available at https://github.com/abhibambhaniya/progressive_gradient_flow_nm_sparsity.

For agents

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

get_harvested_code_for_paper("2402.04744")
get_code_for_paper("2402.04744")
have("2402.04744")

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

curl https://syntology.ai/api/ran/2402.04744.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.04744.svg)](https://syntology.ai/paper/2402.04744)

Connect an agent — have() is free.