SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.03246 · 2019

End-to-End Wireframe Parsing

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 10 have no contract verdict; 3 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/1905.03246.json · badge: /api/ran/1905.03246.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
zhou13/lcnn canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhou13/lcnn/lcnn/metric.py
code served (permissive licence) · get_code("6cc7fd04d6d9a593")
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 float64, 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 numpy as np

# The function `ap` takes two parameters: tp and fp
# Both should be numpy arrays based on how they're used:
# - They're concatenated with np.concatenate
# - They're indexed with np.where
# - They support arithmetic operations (tp / (tp + fp))

# Create small numpy arrays for tp and fp
tp = np.array([0.1, 0.3, 0.5, 0.7, 0.9])
fp = np.array([0.05, 0.1, 0.15, 0.2, 0.25])

ARGS = {
    "tp": tp,
    "fp": fp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
argsort2d Ran
ran on a synthesized input
zhou13/lcnn/lcnn/utils.py
code served (permissive licence) · get_code("de532658ea931902")
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 int, shape (9, 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 numpy as np

# Create a simple 2D numpy array to pass to argsort2d
arr = np.array([
    [3, 1, 4],
    [1, 5, 9],
    [2, 6, 5]
], dtype=np.float32)

ARGS = {
    "arr": arr
}
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 int, shape (9, 2) — shape (9, 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
c Ran
ran on a synthesized input
zhou13/lcnn/lcnn/trainer.py
code served (permissive licence) · get_code("3ca1c4cac81ac852")
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 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
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt

torch.manual_seed(0)

cmap = plt.get_cmap('jet')
norm = mpl.colors.Normalize(vmin=0.4, vmax=1.0)
sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)

def c(x):
    return sm.to_rgba(x)

ARGS = {
    'x': 0.7
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, 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 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
collate Ran
ran; our contract draft was wrong, not the code
zhou13/lcnn/lcnn/datasets.py
code served (permissive licence) · get_code("624365544af5330a")
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
import torch.nn as nn
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

# The collate function expects a batch where each element is a tuple of (tensor, label, tensor)
# It uses default_collate on b[0] and b[2], and keeps b[1] as a list

batch = [
    (torch.randn(2, 4), "label_0", torch.randn(3, 4)),
    (torch.randn(2, 4), "label_1", torch.randn(3, 4)),
]

ARGS = {
    "batch": batch
}
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
cross_entropy_loss Ran
ran on a synthesized input
zhou13/lcnn/lcnn/models/multitask_learner.py
code served (permissive licence) · get_code("0d148fed48dc7e0f")
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 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.functional as F

torch.manual_seed(0)

# Analyze the function:
# - logits: passed to F.log_softmax(logits, dim=0), so needs to be a tensor
# - positive: multiplied with nlogp[1] and (1-positive) with nlogp[0], then .mean(2).mean(1)
#   This suggests positive should be a tensor compatible with broadcasting
# - nlogp has shape from log_softmax on dim=0, so it will have 2 elements along dim 0
# - The operations .mean(2).mean(1) suggest logits/positive need at least 3 dimensions
# 
# Working backwards from .mean(2).mean(1):
# - After (positive * nlogp[1] + (1 - positive) * nlogp[0]), we need dims 1 and 2 to exist
# - nlogp[1] selects along dim 0, reducing that dimension
# - So if logits is (2, batch, height, width), nlogp[1] becomes (batch, height, width)
# - positive should broadcast with this shape
# - .mean(2).mean(1) reduces the last two dimensions

# Let's construct:
# logits: (2, 2, 4, 3) - dim 0 has 2 (for softmax), batch=2, height=4, width=3
# positive: (2, 4, 3) - batch=2, height=4, width=3

logits = torch.randn(2, 2, 4, 3)
positive = torch.rand(2, 4, 3)

ARGS = {
    "logits": logits,
    "positive": positive,
}
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 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
l2loss Ran
ran on a synthesized input
zhou13/lcnn/lcnn/models/multitask_learner.py
code served (permissive licence) · get_code("b7cac97656e1f50f")
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 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

torch.manual_seed(0)

# The function l2loss computes: ((target - input) ** 2).mean(2).mean(1)
# This means it:
# - Takes input and target tensors
# - Computes squared difference
# - Takes mean over dimension 2
# - Takes mean over dimension 1
# 
# For this to work without errors, we need tensors with at least 3 dimensions
# After mean(2).mean(1), we get a 1D tensor with batch size as the only dimension
# 
# Let's use shape (batch=2, feature=3, seq=4) to have distinct dimensions
# - dim 0: batch size = 2
# - dim 1: features = 3
# - dim 2: sequence/time = 4

input_tensor = torch.randn(2, 3, 4)
target_tensor = torch.randn(2, 3, 4)

ARGS = {
    "input": input_tensor,
    "target": target_tensor,
}
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 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
non_maximum_suppression Ran
ran; our contract draft was wrong, not the code
zhou13/lcnn/lcnn/models/line_vectorizer.py
code served (permissive licence) · get_code("c972983944d63a38")
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 (2, 1, 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 torch
import torch.nn.functional as F

torch.manual_seed(0)

# The function takes a single parameter 'a' which is used with F.max_pool2d
# F.max_pool2d expects a 4D tensor (batch, channels, height, width)
# Create a small tensor with batch=2, channels=1, height=4, width=3
a = torch.randn(2, 1, 4, 3)

ARGS = {
    "a": a
}
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 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 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
np_softmax Ran
ran on a synthesized input
zhou13/lcnn/lcnn/utils.py
code served (permissive licence) · get_code("51b1ab837451a9ae")
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 (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 numpy as np

# Create a small numpy array to pass as x
x = np.array([[1.0, 2.0, 3.0, 4.0],
              [2.0, 3.0, 4.0, 5.0]])

# Define ARGS dictionary with all parameters
ARGS = {
    'x': x,
    'axis': 0
}
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 (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
plambda Ran
ran on a synthesized input
zhou13/lcnn/lcnn/postprocess.py
code served (permissive licence) · get_code("aedb982c50ded01d")
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)

# plambda computes the projection parameter of point (x, y) onto a line segment
# from (x1, y1) to (x2, y2). All parameters are scalars or can be treated as scalars.

x1 = 1.0
y1 = 2.0
x2 = 4.0
y2 = 6.0
x = 2.5
y = 3.5

ARGS = {
    "x1": x1,
    "y1": y1,
    "x2": x2,
    "y2": y2,
    "x": x,
    "y": y,
}
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
pline Ran
ran on a synthesized input
zhou13/lcnn/lcnn/postprocess.py
code served (permissive licence) · get_code("ae5012499d510902")
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)

# Analyze the function:
# - x1, y1, x2, y2, x, y are all numeric scalar values (floats or ints)
# - The function computes distance from point (x, y) to line segment from (x1, y1) to (x2, y2)
# - All parameters are used in arithmetic operations

ARGS = {
    "x1": 0.0,
    "y1": 0.0,
    "x2": 3.0,
    "y2": 4.0,
    "x": 1.0,
    "y": 1.0,
}
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
psegment Ran
ran on a synthesized input
zhou13/lcnn/lcnn/postprocess.py
code served (permissive licence) · get_code("3aa94f5be3b33ec4")
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)

# This function computes the squared distance from point (x, y) to a line segment
# defined by endpoints (x1, y1) and (x2, y2).
# All parameters are scalars (floats or ints).

ARGS = {
    "x1": 0.0,
    "y1": 0.0,
    "x2": 3.0,
    "y2": 4.0,
    "x": 1.5,
    "y": 2.0
}
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
recursive_to Ran
ran on a synthesized input
zhou13/lcnn/lcnn/utils.py
code served (permissive licence) · get_code("8d9fbb5d4ca74b8d")
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)

# Test Case 1: Tensor input
tensor_input = torch.randn(2, 4)
device = 'cpu'

# Test Case 2: Dict with tensors
dict_input = {
    'tensor1': torch.randn(2, 4),
    'tensor2': torch.randn(3, 5),
    'key': torch.randn(1, 2)
}

# Test Case 3: List with tensors and nested structures
list_input = [
    torch.randn(2, 4),
    torch.randn(3, 5),
    {
        'nested_tensor': torch.randn(1, 2),
        'another': torch.randn(4, 3)
    },
    [torch.randn(2, 2), torch.randn(1, 3)]
]

# Use the simplest case: a single tensor
ARGS = {
    'input': tensor_input,
    'device': device
}
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
sigmoid_l1_loss Ran
ran on a synthesized input
zhou13/lcnn/lcnn/models/multitask_learner.py
code served (permissive licence) · get_code("4b7c4f699c29396a")
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 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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# logits: shape (batch=2, height=3, width=4)
logits = torch.randn(2, 3, 4)

# target: same shape as logits
target = torch.rand(2, 3, 4)

# offset: scalar float
offset = 0.5

# mask: same shape as logits
mask = torch.ones(2, 3, 4)
mask[0, 1, :] = 0  # Create some variation in mask

ARGS = {
    "logits": logits,
    "target": target,
    "offset": offset,
    "mask": mask,
}
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 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
APJ Not yet run
unverified (harvested, no recorded run)
zhou13/lcnn/lcnn/metric.py
code served (permissive licence) · get_code("02b2ffeb173ebb15")
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, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 7 later) and 7 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
ap 2 other papers
1 the same month, 1 later
1905.07482 (2019-05)
Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
2104.11207 (2021-04)
Fully Convolutional Line Parsing
APJ 1 other paper
1 later
2104.11207 (2021-04)
Fully Convolutional Line Parsing
argsort2d 1 other paper
1 later
1910.06316 (2019-10)
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
c 1 other paper
1 later
1910.06316 (2019-10)
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
collate 1 other paper
1 later
2104.11207 (2021-04)
Fully Convolutional Line Parsing
non_maximum_suppression 1 other paper
1 later
2103.15087 (2021-03)
Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes
np_softmax 1 other paper
1 later
1910.06316 (2019-10)
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution

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

We present a conceptually simple yet effective algorithm to detect wireframes in a given image. Compared to the previous methods which first predict an intermediate heat map and then extract straight lines with heuristic algorithms, our method is end-to-end trainable and can directly output a vectorized wireframe that contains semantically meaningful and geometrically salient junctions and lines. To better understand the quality of the outputs, we propose a new metric for wireframe evaluation that penalizes overlapped line segments and incorrect line connectivities. We conduct extensive experiments and show that our method significantly outperforms the previous state-of-the-art wireframe and line extraction algorithms. We hope our simple approach can be served as a baseline for future wireframe parsing studies. Code has been made publicly available at https://github.com/zhou13/lcnn.

For agents

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

get_harvested_code_for_paper("1905.03246")
get_code_for_paper("1905.03246")
have("1905.03246")

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

curl https://syntology.ai/api/ran/1905.03246.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.03246.svg)](https://syntology.ai/paper/1905.03246)

Connect an agent — have() is free.