SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.01565 · 2020

Stance Detection Benchmark: How Robust Is Your Stance Detection?

arXiv · PDF · Open in the Atlas

Code that ran

9 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; 2 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 2 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/2001.01565.json · badge: /api/ran/2001.01565.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
UKPLab/mdl-stance-robustness canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
create_sample_list_pair Ran
ran on a synthesized input
UKPLab/mdl-stance-robustness/data_utils/glue_utils.py
code served (permissive licence) · get_code("b9de0da0c0405d07")
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)

# Construct X: a list of (premise, hypothesis) tuples
X = [
    ("The cat is on the mat", "The cat is sitting"),
    ("It is raining outside", "The weather is wet")
]

# Construct y: a list of labels (integers)
y = [0, 1]

ARGS = {
    'X': X,
    'y': y
}
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
create_sample_list_single Ran
ran on a synthesized input
UKPLab/mdl-stance-robustness/data_utils/glue_utils.py
code served (permissive licence) · get_code("7e4f856cc2416800")
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)

# X should be an iterable of premises (strings or similar)
X = [
    "The cat sat on the mat",
    "Dogs are loyal animals"
]

# y should be an iterable of labels
y = [0, 1]

ARGS = {
    'X': X,
    'y': y
}
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
gelu Ran
ran; our contract draft was wrong, not the code
UKPLab/mdl-stance-robustness/module/common.py
code served (permissive licence) · get_code("53ebf6e30980ffe9")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 math

torch.manual_seed(0)

# The function gelu takes a single parameter x which is used in:
# 1. Multiplication with 0.5
# 2. torch.erf() function call
# 3. Division by math.sqrt(2.0)
# So x must be a tensor that supports these operations

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
generate_decoder_opt Ran
ran on a synthesized input
UKPLab/mdl-stance-robustness/data_utils/label_map.py
code served (permissive licence) · get_code("a45d66c0712a81bd")
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 int, ndim 0, dtype family int, 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)

SAN_META = {'snopes': 1, 'argmin': 1, 'semeval2016t6': 1, 'semeval2019t7': 0, 'scd': 0, 'perspectrum': 1, 'ibmcs': 1, 'fnc1': 1, 'arc': 1, 'iac1': 1}

def generate_decoder_opt(task, max_opt):
    assert task in SAN_META
    opt_v = 0
    if SAN_META[task] and max_opt < 3:
        opt_v = max_opt
    return opt_v

ARGS = {
    'task': 'snopes',
    'max_opt': 2
}
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 int, ndim 0, dtype family int, 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
generate_mask Ran
ran on a synthesized input
UKPLab/mdl-stance-robustness/module/san.py
code served (permissive licence) · get_code("809cfdb94234ea27")
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 Tensor, ndim 2, dtype family float, shape (2, 4) 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 random
from torch.autograd import Variable

torch.manual_seed(0)

# Create a tensor that will be used as new_data
# The function calls .zero_(), .size(0), and .size(1) on it
# It also indexes with [i][one], so it needs to be 2D
new_data = torch.ones(2, 4)

dropout_p = 0.5
is_training = True

ARGS = {
    "new_data": new_data,
    "dropout_p": dropout_p,
    "is_training": is_training,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
linear Ran
ran, honoured the contract we drafted
UKPLab/mdl-stance-robustness/module/common.py
pointer only (licence: MIT); the stored copy get_code serves, from MrHuff/Sumo-Net, is pointer only (licence: NONE) · get_code("691b566282a42d88")
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 MrHuff/Sumo-Net, 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.

swish Ran
ran; our contract draft was wrong, not the code
UKPLab/mdl-stance-robustness/module/common.py
pointer only (licence: MIT); the stored copy get_code serves, from cliang1453/super-structured-lottery-tickets, is pointer only (licence: MIT) · get_code("47cf8803722c3336")
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 cliang1453/super-structured-lottery-tickets, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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.

warmup_linear_xdl Ran
ran, honoured the contract we drafted
UKPLab/mdl-stance-robustness/module/bert_optim.py
code served (permissive licence) · get_code("dea985d5f4e928e8")
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) 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

torch.manual_seed(0)

# The function takes two parameters:
# - x: a float value between 0 and 1 (representing training progress)
# - warmup: a float value representing the warmup fraction (default 0.002)

# Looking at the function body:
# - x is compared with warmup (< operator)
# - x and warmup are used in arithmetic operations (division, subtraction)
# - The function returns float values

# Create valid arguments
x_value = 0.5  # A float representing progress through training (between 0 and 1)
warmup_value = 0.1  # A float representing the warmup fraction

ARGS = {
    "x": x_value,
    "warmup": warmup_value,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
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
weight_norm Ran
ran on a synthesized input
UKPLab/mdl-stance-robustness/module/my_optim.py
code served (permissive licence) · get_code("0f9a0dbc776dbc60")
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 Linear. 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 torch
import torch.nn as nn
from torch.nn import Parameter

torch.manual_seed(0)

# Create a simple linear module to apply weight norm to
module = nn.Linear(4, 3)

# The function uses:
# - module._parameters to iterate and access weights
# - module.register_parameter() to register g and v parameters
# - getattr/setattr/hasattr for accessing weight parameters
# - register_forward_pre_hook to attach the hook
# All of these are standard nn.Module functionality

ARGS = {
    'module': module,
    'weights': None,  # Will auto-detect weights in _parameters
    'dim': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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_random_indices Not yet run
unverified (harvested, no recorded run)
UKPLab/mdl-stance-robustness/prepro.py
code served (permissive licence) · get_code("8dbe6dcc5c31662f")
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, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 4 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.

FunctionAlso present inEarliest-datedOthers named
gelu 198 other papers
34 dated earlier, 1 the same month, 161 later, 2 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
linear 6 other papers
2 dated earlier, 4 later · 1 only as an assembly brick
1803.06585 (2018-03)
Learning Long Term Dependencies via Fourier Recurrent Units
1901.11504 (2019-01)
Multi-Task Deep Neural Networks for Natural Language Understanding
2104.04886 (2021-04)
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
and 3 more not named here
swish 2 other papers
2 later
2104.04886 (2021-04)
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
2105.12002 (2021-05)
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization
warmup_linear_xdl 2 other papers
2 later
2105.12002 (2021-05)
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization
2202.02664 (2022-02)
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models

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

Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim and has become a key component in applications like fake news detection, claim validation, and argument search. However, while stance is easily detected by humans, machine learning models are clearly falling short of this task. Given the major differences in dataset sizes and framing of StD (e.g. number of classes and inputs), we introduce a StD benchmark that learns from ten StD datasets of various domains in a multi-dataset learning (MDL) setting, as well as from related tasks via transfer learning. Within this benchmark setup, we are able to present new state-of-the-art results on five of the datasets. Yet, the models still perform well below human capabilities and even simple adversarial attacks severely hurt the performance of MDL models. Deeper investigation into this phenomenon suggests the existence of biases inherited from multiple datasets by design. Our analysis emphasizes the need of focus on robustness and de-biasing strategies in multi-task learning approaches. The benchmark dataset and code is made available.

For agents

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

get_harvested_code_for_paper("2001.01565")
get_code_for_paper("2001.01565")
have("2001.01565")

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

curl https://syntology.ai/api/ran/2001.01565.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.01565.svg)](https://syntology.ai/paper/2001.01565)

Connect an agent — have() is free.