SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2605.01336 · 2026

A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis

Yufang Hou, Mbzuai, Umer Siddique, Preslav Nakov, Muhammad Arslan Manzoor, Zain Mujahid, Dilshod Azizov, Daniil Orel

arXiv · PDF · Open in the Atlas

Code that ran

3 of 11 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 8 no recorded run), measured 2026-11-22; 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/2605.01336.json · badge: /api/ran/2605.01336.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
codelucas/newspaper canonical (classifier label)
classifier basis: census
3 ran · 7 no recorded run
marslanm/multi-graph-perspective canonical (classifier label)
classifier basis: census
0 ran · 1 no recorded run
FunctionStatusWhere it lives
get_html Ran
ran; our contract draft was wrong, not the code
codelucas/newspaper/newspaper/network.py
code served (permissive licence) · get_code("29867e7307439883")
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 str. 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 logging
import requests
from unittest.mock import Mock, MagicMock
import requests.utils

log = logging.getLogger(__name__)

FAIL_ENCODING = 'ISO-8859-1'

class Configuration:
    def __init__(self):
        self.browser_user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
        self.request_timeout = 10
        self.proxies = {}
        self.headers = {'User-Agent': 'Custom-Agent'}
        self.ignored_content_types_defaults = {
            'application/pdf': '<pdf>',
            'application/zip': '<zip>',
        }
        self.http_success_only = False

def cj():
    """Dummy cookie jar"""
    return {}

# Create mock response object
mock_response = Mock()
mock_response.status_code = 200
mock_response.headers = {
    'content-type': 'text/html; charset=utf-8',
    'content-encoding': 'utf-8'
}
mock_response.encoding = 'utf-8'
mock_response.text = '<html><body>Test content</body></html>'
mock_response.content = b'<html><body>Test content</body></html>'
mock_response.raise_for_status = Mock()

# Create config
config = Configuration()

# Define ARGS
ARGS = {
    'url': 'https://example.com',
    'config': config,
    'response': mock_response
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
requests — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
get_html_2XX_only Ran
ran; our contract draft was wrong, not the code
codelucas/newspaper/newspaper/network.py
code served (permissive licence) · get_code("c44e117b96ad9d8b")
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 str. 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 requests
from unittest.mock import Mock, patch, MagicMock
import io

class CookieJar:
    """Stand-in for requests.cookies.RequestsCookieJar"""
    pass

def cj():
    """Stand-in for requests.cookies.RequestsCookieJar()"""
    return CookieJar()

class Configuration:
    """Stand-in Configuration class with required attributes"""
    def __init__(self):
        self.browser_user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
        self.request_timeout = 10
        self.proxies = {}
        self.headers = None
        self.ignored_content_types_defaults = {
            'application/json': '{"error": "json"}',
            'text/plain': 'plain text content'
        }
        self.http_success_only = False

# Create mock response object
mock_response = Mock()
mock_response.headers = {
    'content-type': 'text/html; charset=utf-8'
}
mock_response.encoding = 'utf-8'
mock_response.text = '<html><body>Test HTML Content</body></html>'
mock_response.content = b'<html><body>Test HTML Content</body></html>'
mock_response.raise_for_status = Mock(return_value=None)

# Create config
config = Configuration()

# Create valid URL
url = "https://example.com"

# Define ARGS mapping all parameters
ARGS = {
    'url': url,
    'config': config,
    'response': mock_response
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
requests — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
sbs Ran
ran, honoured the contract we drafted
codelucas/newspaper/newspaper/nlp.py
code served (permissive licence) · get_code("743a812554d3af79")
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 re
import math
from collections import Counter

ideal = 20.0
stopwords = set()

def split_words(text):
    """Split a string into array of words
    """
    try:
        text = re.sub('[^\\w ]', '', text)
        return [x.strip('.').lower() for x in text.split()]
    except TypeError:
        return None

def sbs(words, keywords):
    score = 0.0
    if len(words) == 0:
        return 0
    for word in words:
        if word in keywords:
            score += keywords[word]
    return 1.0 / math.fabs(len(words)) * score / 10.0

# Construct valid arguments for the sbs function
words = ["hello", "world", "test", "example", "hello"]
keywords = {
    "hello": 1.5,
    "world": 2.3,
    "test": 0.8
}

ARGS = {
    "words": words,
    "keywords": keywords
}
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 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
evaluate_model_performance Not yet run
unverified (harvested, no recorded run)
marslanm/multi-graph-perspective/RL_fusion/dynamic_fusion_env.py
pointer only (licence: NONE) · get_code("189d8c43609dcca4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, marslanm/multi-graph-perspective 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. No invocation recorded.

fulltext Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/api.py
code served (permissive licence) · get_code("6c6a38183cc78162")
How it ran

no invocation recorded.

get_request_kwargs Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/network.py
code served (permissive licence) · get_code("e66a13aa1cbf44ac")
How it ran

no invocation recorded.

image_to_str Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/images.py
code served (permissive licence) · get_code("1c8cb7807885aa25")
How it ran

no invocation recorded.

prepare_image Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/images.py
code served (permissive licence) · get_code("845d4d23d8c0c811")
How it ran

no invocation recorded.

score Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/nlp.py
code served (permissive licence) · get_code("491f58b8741fe8d7")
How it ran

no invocation recorded.

str_to_image Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/images.py
code served (permissive licence) · get_code("27708524bfb8c66d")
How it ran

no invocation recorded.

summarize Not yet run
unverified (harvested, no recorded run)
codelucas/newspaper/newspaper/nlp.py
code served (permissive licence) · get_code("7809cbc4a95980a1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

News outlets shape public opinion on a scale that makes automated detection of political bias and factuality essential. Yet, the field still lacks unified resources, comprehensive evaluations in diverse approaches, and systematic analyzes of the representations and fusion strategies that matter the most, especially under label sparsity and dataset diversity. In addition, there is little empirical work that reports broad observationdriven findings about what consistently works, what fails, and why. We address these gaps with four contributions: (i) MBFC-2025, a largescale label set that covers ∼2,600 outlets from Media Bias/Fact Check (MBFC); (ii) multiview representations for ACL-2020 (Panayotov et al., 2022) (∼900 outlets) and MBFC-2025, spanning Alexa graphs, hyperlink graphs, LLM-derived graphs, articles, and Wikipedia descriptions; (iii) systematic evaluation and analysis of embedding views and fusion strategies, including an RL-based fusion variant; and (iv) extensive experiments that achieve stateof-the-art results on ACL-2020 and establish strong benchmarks on MBFC-2025.

For agents

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

get_harvested_code_for_paper("2605.01336")
get_code_for_paper("2605.01336")
have("2605.01336")

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

curl https://syntology.ai/api/ran/2605.01336.json

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

[![Syntology run record](https://syntology.ai/api/ran/2605.01336.svg)](https://syntology.ai/paper/2605.01336)

Connect an agent — have() is free.