SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.02093 · 2020

Point Proposal Network: Accelerating Point Source Detection Through Deep Learning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 2 no recorded run), 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/2008.02093.json · badge: /api/ran/2008.02093.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
tilleyd/point-proposal-net canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
create_labeled_set Ran
ran on a synthesized input
tilleyd/point-proposal-net/ppn/data.py
code served (permissive licence) · get_code("e59b2cce4743e328")
How it ran

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

import torch
import numpy as np

torch.manual_seed(0)

# Create a minimal stand-in for ppn._data_labeling module
class MockDataLabeling:
    @staticmethod
    def get_anchors(config):
        # Return a simple anchor array - shape (num_anchors, 4)
        return np.array([[0, 0, 10, 10], [5, 5, 15, 15], [10, 10, 20, 20]], dtype=np.float32)
    
    @staticmethod
    def get_anchor_labels(anchors, coords, config):
        # Return confidence and regression labels for one patch
        # conf: (num_anchors,) array of binary labels
        # reg: (num_anchors, 4) array of regression targets
        num_anchors = len(anchors)
        patch_conf = np.random.randint(0, 2, size=(num_anchors,), dtype=np.int32)
        patch_reg = np.random.randn(num_anchors, 4).astype(np.float32)
        return patch_conf, patch_reg

# Inject mock module into sys.modules so imports work
import sys
sys.modules['ppn'] = type(sys)('ppn')
sys.modules['ppn._data_labeling'] = MockDataLabeling()

# Create a config dictionary with necessary fields
config = {
    'anchor_scales': [8, 16, 32],
    'anchor_ratios': [0.5, 1.0, 2.0],
    'image_stride': 16,
    'num_classes': 2
}

# Create a raw dataset dictionary
dataset = {
    'maps': torch.randn(2, 4, 8, 8),  # 2 patches, 4 channels, 8x8 spatial
    'coords': [
        np.array([[10, 10, 50, 50], [20, 20, 80, 80]], dtype=np.float32),  # 2 bounding boxes for patch 1
        np.array([[15, 15, 60, 60]], dtype=np.float32)  # 1 bounding box for patch 2
    ]
}

ARGS = {
    'dataset': dataset,
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, ppn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
generate_patches Ran
ran on a synthesized input
tilleyd/point-proposal-net/ppn/data.py
code served (permissive licence) · get_code("d546b7758541a7d2")
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 numpy as np

# Create a small test image (7x5)
img = np.random.randint(0, 256, size=(7, 5), dtype=np.uint8)

# Define patch size (3x3)
patch_size = (3, 3)

# Define overlap
overlap = 0

ARGS = {
    "img": img,
    "patch_size": patch_size,
    "overlap": overlap,
}
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 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
get_anchor_labels Ran
ran on a synthesized input
tilleyd/point-proposal-net/ppn/_data_labeling.py
code served (permissive licence) · get_code("3eccb02d87cc6f32")
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 numpy as np

# Create a small config dictionary with required keys
config = {
    'r_near': 2.0,
    'r_far': 5.0,
    'image_size': 64,
    'feature_size': 8,
}

# Generate anchors: one anchor per feature cell
# Shape should be (feature_size * feature_size, 2)
feature_size = config['feature_size']
image_size = config['image_size']
step = image_size / feature_size
anchors = np.zeros((feature_size * feature_size, 2), dtype=np.float32)
for r in range(feature_size):
    for c in range(feature_size):
        idx = r * feature_size + c
        anchors[idx] = [c * step + step * 0.5, r * step + step * 0.5]

# Create a list of ground truth point coordinates
# A few points scattered around the image
coords = [
    (16.0, 16.0),
    (48.0, 32.0),
    (40.0, 50.0),
]

ARGS = {
    'anchors': anchors,
    'coords': coords,
    'config': config,
}
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 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
get_anchors Ran
ran on a synthesized input
tilleyd/point-proposal-net/ppn/_data_labeling.py
code served (permissive licence) · get_code("c18af27725d9e822")
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 (64, 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

ARGS = {
    'config': {
        'image_size': 256,
        'feature_size': 8
    }
}
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 (64, 2) — shape (64, 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_resnet_constructor Ran
ran on a synthesized input
tilleyd/point-proposal-net/ppn/_base_resnet.py
code served (permissive licence) · get_code("0fc1b77ee47a974b")
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 tensorflow.compat.v1 as tf
import numpy as np

# Disable v2 behavior for TensorFlow 1.x compatibility
tf.disable_v2_behavior()

# Create a minimal resnet_config dictionary
resnet_config = {
    'initial_filters': 64,
    'initial_kernel': 7,
    'structure': [3, 4, 6, 3]  # Number of blocks in each layer
}

ARGS = {
    'resnet_config': resnet_config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
precision_recall Ran
ran on a synthesized input
tilleyd/point-proposal-net/ppn/metrics.py
code served (permissive licence) · get_code("227036f759e04b0e")
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 numpy as np

ARGS = {
    'pred_coords': [(10.5, 20.3), (15.2, 25.1), (30.0, 35.5)],
    'gt_coords': [(10.0, 20.0), (15.5, 25.0), (50.0, 60.0)],
    'gt_J': [1, 2, 3],
    'config': {
        'dist_thr': 2.0,
        'image_size': 512,
        'feature_size': 32,
    },
    'dist_thr': None,
}
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 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
ResNetBaseModel Not yet run
unverified (harvested, no recorded run)
tilleyd/point-proposal-net/ppn/_base_resnet.py
code served (permissive licence) · get_code("0eedca5bc1da3633")
How it ran

no invocation recorded.

get_fake_prediction Not yet run
unverified (harvested, no recorded run)
tilleyd/point-proposal-net/ppn/_data_labeling.py
code served (permissive licence) · get_code("2d35622570a8e30f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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.

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

Point source detection techniques are used to identify and localise point sources in radio astronomical surveys. With the development of the Square Kilometre Array (SKA) telescope, survey images will see a massive increase in size from Gigapixels to Terapixels. Point source detection has already proven to be a challenge in recent surveys performed by SKA pathfinder telescopes. This paper proposes the Point Proposal Network (PPN): a point source detector that utilises deep convolutional neural networks for fast source detection. Results measured on simulated MeerKAT images show that, although less precise when compared to leading alternative approaches, PPN performs source detection faster and is able to scale to large images, unlike the alternative approaches.

For agents

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

get_harvested_code_for_paper("2008.02093")
get_code_for_paper("2008.02093")
have("2008.02093")

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

curl https://syntology.ai/api/ran/2008.02093.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.02093.svg)](https://syntology.ai/paper/2008.02093)

Connect an agent — have() is free.