SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.12962 · 2020

GPS-Net: Graph Property Sensing Network for Scene Graph Generation

arXiv · PDF · Open in the Atlas

Code that ran

7 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 4 have no contract verdict; 3 failures of our instrument; 1 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/2003.12962.json · badge: /api/ran/2003.12962.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
taksau/GPS-Net canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
get_ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
taksau/GPS-Net/gpsnet-detectron/lib/datasets_rel/ap_eval_rel.py
code served (permissive licence) · get_code("e3ba7c0c024ad75d")
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 float64, ndim 0, 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

# Construct valid arguments for get_ap function
# The function expects:
# - rec: recall values (array-like, sorted)
# - prec: precision values (array-like, same length as rec)

# Create small, valid recall and precision arrays
# Recall should be monotonically increasing values between 0 and 1
rec = np.array([0.1, 0.3, 0.5, 0.7, 0.9])

# Precision should be values between 0 and 1
# Typically decreases or stays same as recall increases
prec = np.array([0.9, 0.8, 0.7, 0.6, 0.5])

ARGS = {
    "rec": rec,
    "prec": prec
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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_ranking Ran
ran; our contract draft was wrong, not the code
taksau/GPS-Net/lib/pytorch_misc.py
pointer only (licence: MIT); the stored copy get_code serves, from declare-lab/lg-vqa, is pointer only (licence: NONE) · get_code("a1e587129dd2dfaf")
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 declare-lab/lg-vqa, 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.

load_info Ran
ran on a synthesized input
taksau/GPS-Net/lib/dataloaders/visual_genome.py
code served (permissive licence) · get_code("da2ae147332ee568")
How it ran

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

import json
import tempfile
import os

# Create a temporary JSON file with the required structure
temp_dir = tempfile.mkdtemp()
info_file_path = os.path.join(temp_dir, "info.json")

info_data = {
    "label_to_idx": {
        "person": 1,
        "car": 2,
        "dog": 3,
        "cat": 4
    },
    "predicate_to_idx": {
        "sitting on": 1,
        "standing on": 2,
        "holding": 3,
        "driving": 4
    }
}

with open(info_file_path, 'w') as f:
    json.dump(info_data, f)

ARGS = {
    "info_file": info_file_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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
mc_matmul Ran
ran on a synthesized input
taksau/GPS-Net/lib/direction_aware_context.py
code served (permissive licence) · get_code("9bd7267a7be37916")
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, 15) 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)

# tensor3d: shape (batch, height, depth) where depth is the last dimension
# The function iterates over tensor3d.size(-1), so we need a 3D tensor
# mat: a 2D matrix that will be matrix-multiplied with each (batch, height) slice
tensor3d = torch.randn(2, 4, 3)  # batch=2, height=4, depth=3

# mat must be compatible for torch.mm with tensor3d[:, :, i]
# tensor3d[:, :, i] has shape (2, 4), so mat should have shape (4, 5)
# to produce output (2, 5)
mat = torch.randn(4, 5)

ARGS = {
    "tensor3d": tensor3d,
    "mat": mat,
}
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, 15) — shape (2, 15) 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
optimistic_restore Ran
ran on a synthesized input
taksau/GPS-Net/lib/pytorch_misc.py
code served (permissive licence) · get_code("6d0daf87a6ec7e39")
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 bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple neural network
class SimpleNetwork(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

# Create network instance
network = SimpleNetwork()

# Create a state dict that will be partially compatible
# Include some matching keys, one unexpected key, and one missing key
state_dict = {
    'linear1.weight': torch.randn(3, 4),  # matches network's linear1.weight size
    'linear1.bias': torch.randn(3),       # matches network's linear1.bias size
    'linear2.weight': torch.randn(2, 3),  # matches network's linear2.weight size
    'linear2.bias': torch.randn(2),       # matches network's linear2.bias size
    'unexpected_key': torch.randn(5, 5),  # unexpected key not in network
}

# The network has: linear1.weight, linear1.bias, linear2.weight, linear2.bias
# The state_dict has all of those plus 'unexpected_key'
# This means linear2.weight and linear2.bias will be missing from the "missing" set
# and 'unexpected_key' will trigger the mismatch

ARGS = {
    'network': network,
    'state_dict': state_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
pairwise Ran
ran; our contract draft was wrong, not the code
taksau/GPS-Net/lib/pytorch_misc.py
code served (permissive licence) · get_code("fef49730c9e9a2b8")
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 zip. 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
from itertools import tee

torch.manual_seed(0)

# The pairwise function takes an iterable and returns consecutive pairs
# It uses: tee() to create independent iterators, next() to advance one, and zip() to pair them
# The iterable parameter just needs to be any iterable object

# Create a simple iterable - a list of distinct values
iterable_input = [1, 2, 3, 4, 5]

ARGS = {
    "iterable": iterable_input
}
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 zip — a zip output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a zip 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
random_crop Ran
ran on a synthesized input
taksau/GPS-Net/lib/dataloaders/image_transforms.py
code served (permissive licence) · get_code("5097daf8530eeaa5")
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.

from PIL import Image
import numpy as np

# Create a simple PIL image (100x80 pixels, RGB)
img = Image.new('RGB', (100, 80), color='red')

# Create ground truth boxes in format [x1, y1, x2, y2]
# These boxes are in a scaled coordinate system (box_scale units)
# Using box_scale=1024, so we need boxes that make sense at that scale
boxes = np.array([
    [100, 100, 300, 250],
    [400, 150, 600, 400]
], dtype=np.float32)

ARGS = {
    'img': img,
    'boxes': boxes,
    'box_scale': 1024,
    'round_boxes': True,
    'max_crop_fraction': 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, 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
node_priority_sensitive_loss Not yet run
unverified (harvested, no recorded run)
taksau/GPS-Net/lib/nps_loss.py
code served (permissive licence) · get_code("ea27b0d3cafa05fe")
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, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
pairwise 9 other papers
2 dated earlier, 7 later
1812.01880 (2018-12)
Learning to Compose Dynamic Tree Structures for Visual Contexts
1903.03326 (2019-03)
Knowledge-Embedded Routing Network for Scene Graph Generation
2006.09623 (2020-06)
Learning Visual Commonsense for Robust Scene Graph Generation
and 6 more not named here
get_ranking 5 other papers
2 dated earlier, 3 later
1812.01880 (2018-12)
Learning to Compose Dynamic Tree Structures for Visual Contexts
1903.03326 (2019-03)
Knowledge-Embedded Routing Network for Scene Graph Generation
2006.09623 (2020-06)
Learning Visual Commonsense for Robust Scene Graph Generation
and 2 more not named here
optimistic_restore 4 other papers
2 dated earlier, 2 later
1812.01880 (2018-12)
Learning to Compose Dynamic Tree Structures for Visual Contexts
1903.03326 (2019-03)
Knowledge-Embedded Routing Network for Scene Graph Generation
2006.09623 (2020-06)
Learning Visual Commonsense for Robust Scene Graph Generation
and 1 more not named here
get_ap 1 other paper
1 later
2404.02072 (2024-04)
EGTR: Extracting Graph from Transformer for Scene Graph Generation

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

Scene graph generation (SGG) aims to detect objects in an image along with their pairwise relationships. There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the difference in priority between nodes, and the long-tailed distribution of relationships. Accordingly, in this paper, we propose a Graph Property Sensing Network (GPS-Net) that fully explores these three properties for SGG. First, we propose a novel message passing module that augments the node feature with node-specific contextual information and encodes the edge direction information via a tri-linear model. Second, we introduce a node priority sensitive loss to reflect the difference in priority between nodes during training. This is achieved by designing a mapping function that adjusts the focusing parameter in the focal loss. Third, since the frequency of relationships is affected by the long-tailed distribution problem, we mitigate this issue by first softening the distribution and then enabling it to be adjusted for each subject-object pair according to their visual appearance. Systematic experiments demonstrate the effectiveness of the proposed techniques. Moreover, GPS-Net achieves state-of-the-art performance on three popular databases: VG, OI, and VRD by significant gains under various settings and metrics. The code and models are available at \url{https://github.com/taksau/GPS-Net}.

For agents

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

get_harvested_code_for_paper("2003.12962")
get_code_for_paper("2003.12962")
have("2003.12962")

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

curl https://syntology.ai/api/ran/2003.12962.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.12962.svg)](https://syntology.ai/paper/2003.12962)

Connect an agent — have() is free.