SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.12537 · AAAI · 2022

Socially Fair Mitigation of Misinformation on Social Networks via Constraint Stochastic Optimization

Morten Goodwin, Ole-Christoffer Granmo, Ahmed Abouzeid, Christian Webersik

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 5 have no contract verdict; 0 failures of our instrument; 1 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/2203.12537.json · badge: /api/ran/2203.12537.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
Ahmed-Abouzeid/MMSS canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
calc_avg_abs_err Ran
ran on a synthesized input
Ahmed-Abouzeid/MMSS/utils.py
code served (permissive licence) · get_code("b5e5a69bb15c1b59")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - calc_avg_abs_err takes 3 parameters: pred_stamps, real_stamps, realization_bounds
# - pred_stamps and real_stamps are used as dictionaries with .keys() method
# - They map user_id to lists of timestamps (floats)
# - realization_bounds is a list/sequence where realization_bounds[0] is accessed
# - The function chunks timestamps by time bounds and compares counts in last chunk

# Create small valid test data
pred_stamps = {
    0: [0.5, 1.2, 1.8, 2.3, 3.5],
    1: [0.3, 1.1, 2.2, 2.9]
}

real_stamps = {
    0: [0.6, 1.3, 1.9, 2.4, 3.4],
    1: [0.4, 1.0, 2.1, 3.0]
}

# realization_bounds should be increasing values representing time chunk boundaries
# realization_bounds[0] is used as the chunk width
realization_bounds = [1.0, 2.0, 3.0, 4.0]

ARGS = {
    "pred_stamps": pred_stamps,
    "real_stamps": real_stamps,
    "realization_bounds": realization_bounds
}
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 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
calc_correlation Ran
ran on a synthesized input
Ahmed-Abouzeid/MMSS/Comparable_Network_Measures.py
code served (permissive licence) · get_code("e35cad12997c7db0")
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 torch
import numpy as np

torch.manual_seed(0)

# The function expects two lists of numeric values (averaged exposures at each stage)
# It iterates through fake_news_avg_exposures and multiplies each element with corresponding true_news_avg_exposures element

fake_news_avg_exposures = [0.1, 0.2, 0.3, 0.4]
true_news_avg_exposures = [0.5, 0.6, 0.7, 0.8]

ARGS = {
    "fake_news_avg_exposures": fake_news_avg_exposures,
    "true_news_avg_exposures": true_news_avg_exposures
}
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 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
calc_difference Ran
ran on a synthesized input
Ahmed-Abouzeid/MMSS/Comparable_Network_Measures.py
code served (permissive licence) · get_code("23dc26db92702d83")
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 torch
import numpy as np

torch.manual_seed(0)

# The function takes two lists of averaged values (one for each stage)
# and computes the difference at each stage.
# We need to create two lists with the same length representing different stages.

fake_news_avg_exposures = [0.85, 0.72, 0.63, 0.51]
true_news_avg_exposures = [0.45, 0.38, 0.29, 0.22]

ARGS = {
    "fake_news_avg_exposures": fake_news_avg_exposures,
    "true_news_avg_exposures": true_news_avg_exposures,
}
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 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
get_counts Ran
ran on a synthesized input
Ahmed-Abouzeid/MMSS/utils.py
code served (permissive licence) · get_code("0453cc4d59f4b1bd")
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 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)

# Construct chunked_stamps: a list of lists where each inner list contains iterables
# The function accesses user_stamps[compare_realization_id - 1], so we need at least
# that many elements. Each element should be iterable (list-like).
chunked_stamps = [
    [[1, 2, 3], [4, 5], [6]],  # user 0: 3 realization options
    [[7, 8], [9, 10, 11, 12], [13, 14]],  # user 1: 3 realization options
]

# compare_realization_id: used as compare_realization_id - 1 for indexing
compare_realization_id = 1

# priority_x: boolean flag
priority_x = True

# x: list that gets appended to or checked against
x = []

ARGS = {
    "chunked_stamps": chunked_stamps,
    "compare_realization_id": compare_realization_id,
    "priority_x": priority_x,
    "x": x,
}
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 2, dtype family int — 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
get_selected_users_per_stage Ran
ran on a synthesized input
Ahmed-Abouzeid/MMSS/Comparable_Network_Measures.py
code served (permissive licence) · get_code("54d04c98589d7ac7")
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. 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.

# Analyze the function to understand what it needs
# The function takes fake_news_most_exposed_users which is:
# - a list of n stages lists
# - each stage contains a list of triples (tuples/lists with at least 3 elements)
# - each triple has a user_id as the first element (result[0])

# Create a small example that matches this structure
fake_news_most_exposed_users = [
    # Stage 0: list of triples where each triple is [user_id, exposure_count, something_else]
    [
        [101, 5, 0.8],
        [102, 3, 0.6],
        [103, 7, 0.9],
    ],
    # Stage 1: list of triples
    [
        [204, 4, 0.7],
        [205, 6, 0.85],
    ],
    # Stage 2: list of triples
    [
        [310, 2, 0.5],
    ],
]

ARGS = {
    "fake_news_most_exposed_users": fake_news_most_exposed_users,
}
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 list — a list 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_network_metadata Not yet run
unverified (harvested, no recorded run)
Ahmed-Abouzeid/MMSS/utils.py
code served (permissive licence) · get_code("c3f9a17e8960e32d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Recent social networks' misinformation mitigation approaches tend to investigate how to reduce misinformation by considering a whole-network statistical scale. However, unbalanced misinformation exposures among individuals urge to study fair allocation of mitigation resources. Moreover, the network has random dynamics which change over time. Therefore, we introduce a stochastic and non-stationary knapsack problem, and we apply its resolution to mitigate misinformation in social network campaigns. We further propose a generic misinformation mitigation algorithm that is robust to different social networks' misinformation statistics, allowing a promising impact in real-world scenarios. A novel loss function ensures fair mitigation among users. We achieve fairness by intelligently allocating a mitigation incentivization budget to the knapsack, and optimizing the loss function. To this end, a team of Learning Automata (LA) drives the budget allocation. Each LA is associated with a user and learns to minimize its exposure to misinformation by performing a non-stationary and stochastic walk over its state space. Our results show how our LA-based method is robust and outperforms similar misinformation mitigation methods in how the mitigation is fairly influencing the network users.

For agents

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

get_harvested_code_for_paper("2203.12537")
get_code_for_paper("2203.12537")
have("2203.12537")

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

curl https://syntology.ai/api/ran/2203.12537.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.12537.svg)](https://syntology.ai/paper/2203.12537)

Connect an agent — have() is free.