SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1911.00147 · 2019

Predicting the Politics of an Image Using Webly Supervised Data

arXiv · PDF · Open in the Atlas

Code that ran

2 of 9 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 2 have no contract verdict; 0 failures of our instrument; 7 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/1911.00147.json · badge: /api/ran/1911.00147.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
dragnet-org/dragnet canonical (classifier label)
classifier basis: census
2 ran · 7 no recorded run
FunctionStatusWhere it lives
evaluate_model_predictions Ran
ran on a synthesized input
dragnet-org/dragnet/dragnet/model_training.py
code served (permissive licence) · get_code("7cf68e6e56e9446e")
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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Create simple binary classification predictions and ground truth
# Using small arrays for efficiency

# Case 1: Simple 1D arrays
y_true_1d = np.array([0, 1, 1, 0, 1, 1, 0, 0])
y_pred_1d = np.array([0, 1, 0, 0, 1, 1, 0, 1])
weights_1d = np.array([1.0, 1.0, 1.5, 1.0, 2.0, 1.0, 1.0, 1.0])

# Case 2: List of numpy arrays (which the function concatenates)
y_true_list = [np.array([0, 1, 1]), np.array([0, 1]), np.array([1, 0, 0])]
y_pred_list = [np.array([0, 1, 0]), np.array([0, 1]), np.array([1, 1, 0])]
weights_list = [np.array([1.0, 1.0, 1.5]), np.array([1.0, 2.0]), np.array([1.0, 1.0, 1.0])]

# Create ARGS with simple 1D arrays (most straightforward case)
ARGS = {
    'y_true': y_true_1d,
    'y_pred': y_pred_1d,
    'weights': weights_1d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
evaluation_metrics Ran
ran on a synthesized input
dragnet-org/dragnet/dragnet/util.py
code served (permissive licence) · get_code("9f34a097938066d0")
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

torch.manual_seed(0)

# Construct arguments for evaluation_metrics
predicted = ["cat", "dog", "bird", "fish"]
actual = ["cat", "dog", "elephant", "fish"]

ARGS = {
    "predicted": predicted,
    "actual": actual,
    "bow": True,
}
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 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
bytes_cast Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/compat.py
code served (permissive licence) · get_code("1fc6189843b47c19")
How it ran

no invocation recorded.

dameraulevenshtein Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/util.py
code served (permissive licence) · get_code("0b240d50631fc9ab")
How it ran

no invocation recorded.

evaluate_extracted_tokens Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/model_training.py
code served (permissive licence) · get_code("62deb766c0a114dd")
How it ran

no invocation recorded.

get_and_union_features Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/util.py
code served (permissive licence) · get_code("6d6b719f28e0ad54")
How it ran

no invocation recorded.

read_html_file Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/data_processing.py
code served (permissive licence) · get_code("a2c27af65db0ee69")
How it ran

no invocation recorded.

str_cast Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/compat.py
code served (permissive licence) · get_code("39461510fffca969")
How it ran

no invocation recorded.

str_list_cast Not yet run
unverified (harvested, no recorded run)
dragnet-org/dragnet/dragnet/compat.py
code served (permissive licence) · get_code("533a11c8e71b54ee")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
bytes_cast 1 other paper
1 dated earlier
1607.01759 (2016-07)
Bag of Tricks for Efficient Text Classification
dameraulevenshtein 1 other paper
1 dated earlier
1607.01759 (2016-07)
Bag of Tricks for Efficient Text Classification
evaluation_metrics 1 other paper
1 dated earlier
1607.01759 (2016-07)
Bag of Tricks for Efficient Text Classification
get_and_union_features 1 other paper
1 dated earlier
1607.01759 (2016-07)
Bag of Tricks for Efficient Text Classification
str_cast 1 other paper
1 dated earlier
1607.01759 (2016-07)
Bag of Tricks for Efficient Text Classification
str_list_cast 1 other paper
1 dated earlier
1607.01759 (2016-07)
Bag of Tricks for Efficient Text Classification

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

The news media shape public opinion, and often, the visual bias they contain is evident for human observers. This bias can be inferred from how different media sources portray different subjects or topics. In this paper, we model visual political bias in contemporary media sources at scale, using webly supervised data. We collect a dataset of over one million unique images and associated news articles from left- and right-leaning news sources, and develop a method to predict the image's political leaning. This problem is particularly challenging because of the enormous intra-class visual and semantic diversity of our data. We propose a two-stage method to tackle this problem. In the first stage, the model is forced to learn relevant visual concepts that, when joined with document embeddings computed from articles paired with the images, enable the model to predict bias. In the second stage, we remove the requirement of the text domain and train a visual classifier from the features of the former model. We show this two-stage approach facilitates learning and outperforms several strong baselines. We also present extensive qualitative results demonstrating the nuances of the data.

For agents

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

get_harvested_code_for_paper("1911.00147")
get_code_for_paper("1911.00147")
have("1911.00147")

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

curl https://syntology.ai/api/ran/1911.00147.json

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

[![Syntology run record](https://syntology.ai/api/ran/1911.00147.svg)](https://syntology.ai/paper/1911.00147)

Connect an agent — have() is free.