SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.13995 · CVPR · 2023

LINe: Out-of-Distribution Detection by Leveraging Important Neurons

arXiv · PDF · Open in the Atlas

Code that ran

17 of 20 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, 1 violated it and 7 have no contract verdict; 9 failures of our instrument; 3 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/2303.13995.json · badge: /api/ran/2303.13995.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
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons canonical (classifier label)
classifier basis not recorded on the link
17 ran · 3 no recorded run
FunctionStatusWhere it lives
conv1x1 Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/resnetv2.py
code served (permissive licence) · get_code("ee80cf467065076b")
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 StdConv2d. 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)

ARGS = {
    'cin': 3,
    'cout': 16,
    'stride': 1,
    'bias': False,
}
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 StdConv2d — a StdConv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StdConv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/resnetv2.py
code served (permissive licence) · get_code("f01b8d3901f0b289")
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 StdConv2d. 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)

ARGS = {
    'cin': 3,
    'cout': 16,
    'stride': 1,
    'groups': 1,
    'bias': False,
}
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 StdConv2d — a StdConv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a StdConv2d 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
create_dat Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/lbtoolbox.py
code served (permissive licence) · get_code("c89634a262bdea21")
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 ndarray, ndim 2, dtype family float, shape (4, 3) 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 numpy as np
import tempfile
import os

# Create a temporary directory for test files
tmpdir = tempfile.mkdtemp()
basename = os.path.join(tmpdir, "test_array")

ARGS = {
    'basename': basename,
    'dtype': np.float32,
    'shape': (4, 3),
    'fillvalue': 0.5,
    'custom_key': 'custom_value',
    'another_meta': 42
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) 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
dir Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/common.py
code served (permissive licence) · get_code("28ea57a8f1e61ffb")
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 os
import tempfile

# Create a temporary directory path for testing
temp_dir = tempfile.gettempdir()
test_path = os.path.join(temp_dir, "test_dir_creation_" + str(os.getpid()))

ARGS = {
    "path": test_path
}
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 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
format_time Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/common.py
pointer only (licence: MIT); the stored copy get_code serves, from JunlinHan/YOCO, is pointer only (licence: NONE) · get_code("8d7ec010c29e813b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from JunlinHan/YOCO, and GitHub detected no licence in that repository 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_mixup Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/hyperrule.py
code served (permissive licence) · get_code("7d63034d0bfadd78")
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 numpy as np

torch.manual_seed(0)

# The function get_mixup takes dataset_size as a parameter
# It returns 0.0 if dataset_size < 20000, else 0.1
# We need to construct a valid dataset_size argument

# Test with a small dataset size (less than 20000)
dataset_size_small = 15000

# Test with a large dataset size (>= 20000)
dataset_size_large = 25000

# We can use either one; let's use the large one to test the else branch
ARGS = {
    "dataset_size": 25000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
get_msp_score Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/score.py
code served (permissive licence) · get_code("8511dff685e73d9d")
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 ndarray, ndim 1, dtype family float, shape (2,) 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
import numpy as np

torch.manual_seed(0)

# Create a simple model that takes inputs and outputs logits
class SimpleClassifier(nn.Module):
    def __init__(self, input_dim, num_classes):
        super().__init__()
        self.linear = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.linear(x)

# Create model instance
model = SimpleClassifier(input_dim=4, num_classes=3)
model.eval()

# Create sample inputs: batch size 2, feature dimension 4
inputs = torch.randn(2, 4)

# Create method_args dict (empty dict is valid since function doesn't use it)
method_args = {}

ARGS = {
    "inputs": inputs,
    "model": model,
    "method_args": method_args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
get_resolution Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/hyperrule.py
code served (permissive licence) · get_code("a933bb17fdb8ebb4")
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 1, dtype family int; 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 takes original_resolution as a parameter
# It expects a tuple or sequence with at least 2 elements (H, W)
# It accesses original_resolution[0] and original_resolution[1]
# and performs multiplication and comparison operations

ARGS = {
    "original_resolution": (100, 100)
}
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 1, dtype family int — 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
get_resolution_from_dataset Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/hyperrule.py
code served (permissive licence) · get_code("53256b67d70b0daf")
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 1, dtype family int; 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

ARGS = {
    'dataset': 'cifar10'
}
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 1, dtype family int — 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
get_rowl_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/score.py
code served (permissive licence) · get_code("3574d883f0468bc9")
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 ndarray, ndim 1, dtype family float, shape (2,) 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
import torch.nn.functional as F

torch.manual_seed(0)

# Define a simple model that takes inputs and produces outputs
class SimpleModel(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Create model with input_dim=4, output_dim=5 (5 classes: 0-4, where class 4 is num_classes)
model = SimpleModel(input_dim=4, output_dim=5)
model.eval()

# Create input tensor: batch_size=2, feature_dim=4
inputs = torch.randn(2, 4)

# Create method_args dict with num_classes
method_args = {
    'num_classes': 4
}

# Define ARGS mapping all parameters
ARGS = {
    'inputs': inputs,
    'model': model,
    'method_args': method_args,
    'raw_score': 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 ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
get_sofl_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/score.py
code served (permissive licence) · get_code("f3bc884f0d0d3994")
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 ndarray, ndim 1, dtype family float, shape (2,) 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
import torch.nn.functional as F
import numpy as np

torch.manual_seed(0)

# Build a minimal model that takes inputs and outputs logits
class SimpleModel(nn.Module):
    def __init__(self, input_dim, output_dim):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Create inputs: batch size 2, input dimension 4
inputs = torch.randn(2, 4)

# Create model: input_dim=4, output_dim=6 (to have classes beyond num_classes)
model = SimpleModel(input_dim=4, output_dim=6)

# Create method_args with num_classes=3 (so indices 3:6 will be summed)
method_args = {
    'num_classes': 3
}

ARGS = {
    'inputs': inputs,
    'model': model,
    'method_args': method_args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
log_f Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/common.py
code served (permissive licence) · get_code("b7607d4d2ee295e2")
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 io

p = print

def log_f(f, console=True):
    def log(msg):
        f.write(msg)
        f.write('\n')
        if console:
            p(msg)
    return log

# Create a StringIO object to act as a file-like object
file_obj = io.StringIO()

ARGS = {
    'f': file_obj,
    'console': True
}
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
mobilenet_v2 Ran
ran; our contract draft was wrong, not the code
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/mobilenetv2.py
code served (permissive licence) · get_code("3c3391fd28fbb0aa")
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 MobileNetV2. 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 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 import nn

torch.manual_seed(0)

# Build the arguments for MobileNetV2
ARGS = {
    'num_classes': 10,
    'width_mult': 1.0,
    'inverted_residual_setting': None,
    'round_nearest': 8,
    'block': None,
    'norm_layer': None,
    'p': None,
    'info': None,
    'clip_threshold': 10000000000.0,
    'LU': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MobileNetV2 — a MobileNetV2 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MobileNetV2 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
pil_loader Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/dataset_largescale.py
code served (permissive licence) · get_code("bfe25354cd38a1d7")
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 Image. 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 io
from PIL import Image
import torch

# Create a small valid image in memory
img = Image.new('RGB', (4, 3), color='red')
img_bytes = io.BytesIO()
img.save(img_bytes, format='PNG')
img_bytes.seek(0)

# We need to save this to a temporary path-like object that PIL can open
# Since we can't do real file I/O, we'll create a minimal file-like object wrapper
class FakeImagePath:
    def __init__(self, img_bytes):
        self.img_bytes = img_bytes
    
    def __str__(self):
        return "fake_image.png"

# Actually, PIL.Image.open needs a real file path or file object
# Let's use a BytesIO object directly since Image.open accepts file-like objects
img_bytes.seek(0)

ARGS = {
    'img_str': img_bytes,
    'str': 'RGB'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
tf2th Ran
ran, violated the contract we drafted
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/resnetv2.py
code served (permissive licence) · get_code("7023eb86801bb3a3")
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 4, dtype family float, shape (6, 5, 3, 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 numpy as np

torch.manual_seed(0)

# Create a 4D numpy array in HWIO format (Height, Width, Input channels, Output channels)
# Using distinct dimensions: H=3, W=4, I=5, O=6
conv_weights = np.random.randn(3, 4, 5, 6).astype(np.float32)

ARGS = {
    "conv_weights": conv_weights
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (6, 5, 3, 4) — shape (6, 5, 3, 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
unpickle Ran
ran on a synthesized input
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/dataset_largescale.py
code served (permissive licence) · get_code("80aea57f14a9774f")
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 pickle
import tempfile
import os

# Create a temporary file with pickled data
temp_dir = tempfile.mkdtemp()
test_filename = os.path.join(temp_dir, "test.pkl")

# Create sample data to pickle
sample_data = {
    b'key1': 'value1',
    b'key2': [1, 2, 3],
    b'key3': {'nested': 'dict'}
}

# Write the pickled data to file
with open(test_filename, 'wb') as fo:
    pickle.dump(sample_data, fo)

ARGS = {
    'filename': test_filename
}
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 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
load_dat Not yet run
unverified (harvested, no recorded run)
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/util/lbtoolbox.py
code served (permissive licence) · get_code("dab6ee6664758d5f")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/resnet.py
code served (permissive licence) · get_code("5bb09b6a9cad75f6")
How it ran

no invocation recorded.

resnet50 Not yet run
unverified (harvested, no recorded run)
yonghyun-ahn/line-out-of-distribution-detection-by-leveraging-important-neurons/models/resnet.py
code served (permissive licence) · get_code("47a0a26e9f0185c8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 20 are also present in other papers whose code we hold (19 with at least one paper dated earlier, 5 the same month, 9 later) and 0 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
conv3x3 686 other papers
459 dated earlier, 10 the same month, 210 later, 7 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
resnet18 89 other papers
60 dated earlier, 1 the same month, 27 later, 1 same year, order not determinable
1705.09759 (2017-05)
CASENet: Deep Category-Aware Semantic Edge Detection
1801.07698 (2018-01)
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
1803.00839 (2018-03)
Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
and 86 more not named here
format_time 37 other papers
33 dated earlier, 4 later
1603.05027 (2016-03)
Identity Mappings in Deep Residual Networks
1605.07146 (2016-05)
Wide Residual Networks
1805.11327 (2018-05)
Lightweight Probabilistic Deep Networks
and 34 more not named here
conv1x1 33 other papers
24 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable · 3 only as an assembly brick
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2102.04306 (2021-02)
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
and 30 more not named here
conv3x3 33 other papers
24 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable · 3 only as an assembly brick
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2102.04306 (2021-02)
TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
and 30 more not named here
tf2th 17 other papers
12 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
1912.11370 (2019-12)
Big Transfer (BiT): General Visual Representation Learning
2104.02610 (2021-04)
On the Robustness of Vision Transformers to Adversarial Examples
2106.01127 (2021-06)
Towards Robust Classification Model by Counterfactual and Invariant Data Generation
and 14 more not named here
resnet50 13 other papers
5 dated earlier, 8 later
1603.04992 (2016-03)
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
1905.03244 (2019-05)
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
2006.05734 (2020-06)
3D Human Mesh Regression with Dense Correspondence
and 10 more not named here
create_dat 4 other papers
4 dated earlier
2108.02833 (2021-08)
Elaborative Rehearsal for Zero-shot Action Recognition
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
and 1 more not named here
get_mixup 4 other papers
4 dated earlier
2108.02833 (2021-08)
Elaborative Rehearsal for Zero-shot Action Recognition
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
and 1 more not named here
load_dat 4 other papers
4 dated earlier
2108.02833 (2021-08)
Elaborative Rehearsal for Zero-shot Action Recognition
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2204.08491 (2022-04)
Active Learning Helps Pretrained Models Learn the Intended Task
and 1 more not named here
get_msp_score 3 other papers
2 dated earlier, 1 later
2006.15207 (2020-06)
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2411.14049 (2024-11)
Out-Of-Distribution Detection with Diversification (Provably)
get_resolution 3 other papers
3 dated earlier
2108.02833 (2021-08)
Elaborative Rehearsal for Zero-shot Action Recognition
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
get_resolution_from_dataset 3 other papers
3 dated earlier
2108.02833 (2021-08)
Elaborative Rehearsal for Zero-shot Action Recognition
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
2205.09723 (2022-05)
Robust and Efficient Medical Imaging with Self-Supervision
mobilenet_v2 3 other papers
2 later, 1 same year, order not determinable
Wang_Practical_Network_Acceleration_With_Tiny_Sets_CVPR_2023_paper (2023 (year only))
Practical Network Acceleration with Tiny Sets
2411.02853 (2024-11)
ADOPT: Modified Adam Can Converge with Any β 2 with the Optimal Rate
2508.21695 (2025-08)
Activation Subspaces for Out-of-Distribution Detection
get_rowl_score 2 other papers
2 dated earlier
2006.15207 (2020-06)
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
get_sofl_score 2 other papers
2 dated earlier
2006.15207 (2020-06)
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
dir 1 other paper
1 dated earlier
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
log_f 1 other paper
1 dated earlier
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
pil_loader 1 other paper
1 dated earlier
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection
unpickle 1 other paper
1 dated earlier
2111.09805 (2021-11)
DICE: Leveraging Sparsification for Out-of-Distribution Detection

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

It is important to quantify the uncertainty of input samples, especially in mission-critical domains such as autonomous driving and healthcare, where failure predictions on out-of-distribution (OOD) data are likely to cause big problems. OOD detection problem fundamentally begins in that the model cannot express what it is not aware of. Post-hoc OOD detection approaches are widely explored because they do not require an additional re-training process which might degrade the model's performance and increase the training cost. In this study, from the perspective of neurons in the deep layer of the model representing high-level features, we introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data. We propose a novel method, Leveraging Important Neurons (LINe), for post-hoc Out of distribution detection. Shapley value-based pruning reduces the effects of noisy outputs by selecting only high-contribution neurons for predicting specific classes of input data and masking the rest. Activation clipping fixes all values above a certain threshold into the same value, allowing LINe to treat all the class-specific features equally and just consider the difference between the number of activated feature differences between in-distribution and OOD data. Comprehensive experiments verify the effectiveness of the proposed method by outperforming state-of-the-art post-hoc OOD detection methods on CIFAR-10, CIFAR-100, and ImageNet datasets.

For agents

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

get_harvested_code_for_paper("2303.13995")
get_code_for_paper("2303.13995")
have("2303.13995")

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

curl https://syntology.ai/api/ran/2303.13995.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.13995.svg)](https://syntology.ai/paper/2303.13995)

Connect an agent — have() is free.