SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.04790 · NeurIPS · 2020

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Douwe Kiela, Hamed Firooz, Aravind Mohan

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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 1 has no contract verdict; 0 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/2005.04790.json · badge: /api/ran/2005.04790.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
SebKleiner/Hateful_Memes community (classifier label)
classifier basis not recorded on the link
1 ran · 3 no recorded run
FunctionStatusWhere it lives
vectorize Ran
ran on a synthesized input
SebKleiner/Hateful_Memes/predict.py
code served (permissive licence) · get_code("05027f25ccd8edb8")
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 DataFrame. 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 pickle
import pandas as pd
import tempfile
import os
from sklearn.feature_extraction.text import TfidfVectorizer

# Create temporary directory for mock pickle files
temp_dir = tempfile.mkdtemp()
models_dir = os.path.join(temp_dir, 'models')
os.makedirs(models_dir, exist_ok=True)

# Create mock TfidfVectorizer instances and save them
tfid_labels = TfidfVectorizer()
tfid_labels.fit(['cat dog', 'bird fish', 'car truck'])
with open(os.path.join(models_dir, 'tfid_labels.pkl'), 'wb') as f:
    pickle.dump(tfid_labels, f)

tfid_objects = TfidfVectorizer()
tfid_objects.fit(['wheel window', 'paw ear', 'wing tail'])
with open(os.path.join(models_dir, 'tfid_objects.pkl'), 'wb') as f:
    pickle.dump(tfid_objects, f)

tfid_text = TfidfVectorizer()
tfid_text.fit(['hello world', 'this is text', 'meme caption here'])
with open(os.path.join(models_dir, 'tfid_text.pkl'), 'wb') as f:
    pickle.dump(tfid_text, f)

# Change to temp directory so relative paths work
original_dir = os.getcwd()
os.chdir(temp_dir)

# Define arguments for the function
ARGS = {
    'labels': ['cat', 'dog', 'bird'],
    'objects': ['wheel', 'window', 'paw'],
    'text': 'hello world this is a meme'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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_prediction Not yet run
unverified (harvested, no recorded run)
SebKleiner/Hateful_Memes/predict.py
code served (permissive licence) · get_code("fc4cf27b573fc027")
How it ran

no invocation recorded.

get_probabilities Not yet run
unverified (harvested, no recorded run)
SebKleiner/Hateful_Memes/predict.py
code served (permissive licence) · get_code("194f8a8874868ed4")
How it ran

no invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
SebKleiner/Hateful_Memes/processing/processing.py
code served (permissive licence) · get_code("6a82ada7b852ae28")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans, illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community. * Equal contribution. Preprint. Under review.

For agents

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

get_harvested_code_for_paper("2005.04790")
get_code_for_paper("2005.04790")
have("2005.04790")

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

curl https://syntology.ai/api/ran/2005.04790.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.04790.svg)](https://syntology.ai/paper/2005.04790)

Connect an agent — have() is free.