SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.05148 · ICLR · 2023

Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection

Edward De Brouwer, Martijn Oldenhof, Adam Arany, Yves Moreau

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 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; 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/2303.05148.json · badge: /api/ran/2303.05148.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
molden/ProbKT canonical (classifier label)
classifier basis not recorded on the link
7 ran · 3 no recorded run
FunctionStatusWhere it lives
all_gather Ran
ran; our contract draft was wrong, not the code
molden/ProbKT/robust_detection/dpl_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from windygoo/promptnucseg, is pointer only (licence: NONE) · get_code("345f34217e670c58")
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 windygoo/promptnucseg, 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.

calculate_iou Ran
ran on a synthesized input
molden/ProbKT/generate_data/generate_data.py
code served (permissive licence) · get_code("b1083ea5a382f718")
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 float32, 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

# Create sample bounding boxes in [xmin, ymin, xmax, ymax] format
prediction_box = np.array([10.0, 20.0, 50.0, 60.0], dtype=np.float32)
gt_box = np.array([15.0, 25.0, 55.0, 65.0], dtype=np.float32)

ARGS = {
    "prediction_box": prediction_box,
    "gt_box": gt_box
}
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 float32, 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
compute_iou_all Ran
ran on a synthesized input
molden/ProbKT/generate_data/generate_data.py
code served (permissive licence) · get_code("7727e91e83edda8c")
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 list, 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

# Create sample bounding boxes in format [xmin, ymin, xmax, ymax]
# Bounding box 1: a box from (10, 20) to (50, 60)
bbox = np.array([10.0, 20.0, 50.0, 60.0])

# Multiple ground truth bounding boxes
# Box 1: overlapping with bbox
# Box 2: non-overlapping with bbox
# Box 3: partially overlapping with bbox
all_bboxes = [
    np.array([30.0, 40.0, 70.0, 80.0]),  # partial overlap
    np.array([100.0, 100.0, 150.0, 150.0]),  # no overlap
    np.array([5.0, 15.0, 25.0, 35.0]),  # partial overlap
]

ARGS = {
    "bbox": bbox,
    "all_bboxes": all_bboxes
}
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 list, ndim 1, dtype family float — a list 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
molden/ProbKT/robust_detection/baselines/cnn_model.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.

read_labels Ran
ran on a synthesized input
molden/ProbKT/generate_data/visualize_dataset.py
code served (permissive licence) · get_code("6d30a340fe4349c7")
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 pathlib
import tempfile
import numpy as np

# Create a temporary directory and a temporary label file
temp_dir = tempfile.mkdtemp()
label_path = pathlib.Path(temp_dir) / "labels.txt"

# Write a sample label file with header and data rows
# Format: label, xmin, ymin, xmax, ymax
with open(label_path, 'w') as f:
    f.write("label,xmin,ymin,xmax,ymax\n")
    f.write("1,10,20,100,200\n")
    f.write("2,50,60,150,250\n")
    f.write("3,5,15,95,195\n")

ARGS = {
    "label_path": label_path
}
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
reduce_dict Ran
ran; our contract draft was wrong, not the code
molden/ProbKT/robust_detection/dpl_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from kellyiss/situformer, is pointer only (licence: NONE) · get_code("05992505df9ef0cd")
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 kellyiss/situformer, 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.

tight_bbox Ran
ran on a synthesized input
molden/ProbKT/generate_data/generate_data.py
code served (permissive licence) · get_code("9f8cdb526db9564f")
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 list, 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
import numpy as np

torch.manual_seed(0)

# Create a small digit tensor (simulating a binary mask or image)
# The function iterates over columns and rows to find non-zero values
# Shape: (height, width) = (4, 3) for distinct dimensions
digit = torch.tensor([
    [0, 0, 0],
    [1, 1, 0],
    [1, 1, 0],
    [0, 0, 0]
], dtype=torch.float32)

# Original bounding box: [xmin, ymin, xmax, ymax]
orig_bbox = [10, 20, 15, 28]

ARGS = {
    "digit": digit,
    "orig_bbox": orig_bbox
}
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 list, ndim 1, dtype family int — a list 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
evaluate Not yet run
unverified (harvested, no recorded run)
molden/ProbKT/robust_detection/engine.py
code served (permissive licence) · get_code("cd1489fc7bc435dd")
How it ran

no invocation recorded.

filter_data Not yet run
unverified (harvested, no recorded run)
molden/ProbKT/robust_detection/dpl_utils.py
code served (permissive licence) · get_code("d2cb704276043c27")
How it ran

no invocation recorded.

train_one_epoch Not yet run
unverified (harvested, no recorded run)
molden/ProbKT/robust_detection/engine.py
code served (permissive licence) · get_code("c33a0bbdb30c8123")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 3 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
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
reduce_dict 33 other papers
15 dated earlier, 1 the same month, 17 later
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
1811.10200 (2018-11)
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments
2007.02419 (2020-07)
Attention-based Joint Detection of Object and Semantic Part
and 30 more not named here
all_gather 3 other papers
1 dated earlier, 2 later
2204.06859 (2022-04)
Semi-Supervised Training to Improve Player and Ball Detection in Soccer
2311.15939 (2023-11)
Unleashing the Power of Prompt-driven Nucleus Instance Segmentation
2406.20095 (2024-06)
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

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

Training object detection models usually requires instance-level annotations, such as the positions and labels of all objects present in each image. Such supervision is unfortunately not always available and, more often, only image-level information is provided, also known as weak supervision. Recent works have addressed this limitation by leveraging knowledge from a richly annotated domain. However, the scope of weak supervision supported by these approaches has been very restrictive, preventing them to use all available information. In this work, we propose ProbKT, a framework based on probabilistic logical reasoning that allows to train object detection models with arbitrary types of weak supervision. We empirically show on different datasets that using all available information is beneficial as our ProbKT leads to significant improvement on target domain and better generalization compared to existing baselines. We also showcase the ability of our approach to handle complex logic statements as supervision signal. Our code is available at https://github.com/molden/ProbKT

For agents

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

get_harvested_code_for_paper("2303.05148")
get_code_for_paper("2303.05148")
have("2303.05148")

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

curl https://syntology.ai/api/ran/2303.05148.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.05148.svg)](https://syntology.ai/paper/2303.05148)

Connect an agent — have() is free.