SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.02439 · ACL · 2020

Contextualizing Hate Speech Classifiers with Post-hoc Explanation

Xisen Jin, Xiang Ren, Aida Davani, Morteza Dehghani, Brendan Kennedy

arXiv · PDF · Open in the Atlas

Code that ran

10 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 5 failures of our instrument; 8 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-21; 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/2005.02439.json · badge: /api/ran/2005.02439.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
owaisCS/TestHateSpeech community (classifier label)
classifier basis not recorded on the link
8 ran · 7 no recorded run
BrendanKennedy/contextualizing-hate-speech-models-with-explanations marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
owaisCS/TestHateSpeech/bert/modeling.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:33:52Z). 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 swish takes a single parameter 'x' which is used with:
# - torch.sigmoid(x) - requires a tensor
# - x * ... - requires a tensor that supports multiplication
# So x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 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
DotDict Ran
ran on a synthesized input · constructed an object; no result was computed
BrendanKennedy/contextualizing-hate-speech-models-with-explanations/hiex/soc_algo.py
code served (permissive licence) · get_code("d1f57751ec604230")
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 an instance of its own class, DotDict: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

# DotDict is a simple class that converts keyword arguments into object attributes
# It doesn't actually USE any parameters in a meaningful way - it just stores them
# So we can pass any valid keyword arguments

ARGS = {
    'key1': 'value1',
    'key2': 42,
    'key3': [1, 2, 3],
    'key4': {'nested': 'dict'},
    'key5': torch.randn(2, 4),
}
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 DotDict — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DotDict 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
_SamplingAndOcclusionBaseAlgo Ran
ran on a synthesized input · constructed an object; no result was computed
BrendanKennedy/contextualizing-hate-speech-models-with-explanations/hiex/soc_algo.py
code served (permissive licence) · get_code("6557fd36dd52f015")
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 an instance of its own class, _SamplingAndOcclusionBaseAlgo: the run constructed the object and did not call it, so no result was computed. 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
import torch
import torch.nn as nn
from collections import defaultdict

torch.manual_seed(0)

# Create a minimal tokenizer stand-in
class MockTokenizer:
    def __init__(self):
        self.vocab = {
            '[PAD]': 0,
            '[CLS]': 101,
            '[SEP]': 102,
            'word1': 1,
            'word2': 2,
        }

# Create a minimal model stand-in
class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(768, 2)
    
    def forward(self, input_ids, attention_mask=None, token_type_ids=None):
        batch_size = input_ids.shape[0]
        output = torch.randn(batch_size, 2)
        return output

# Create a minimal config stand-in
class MockConfig:
    def __init__(self):
        self.max_seq_length = 128
        self.batch_size = 2
        self.nb_range = 3

# Build the arguments
model = MockModel()
tokenizer = MockTokenizer()
output_path = "/tmp/test_output"
configs = MockConfig()

ARGS = {
    "model": model,
    "tokenizer": tokenizer,
    "output_path": output_path,
    "configs": configs,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type _SamplingAndOcclusionBaseAlgo — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a _SamplingAndOcclusionBaseAlgo 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
acc_and_f1 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
owaisCS/TestHateSpeech/run_model.py
code served (permissive licence) · get_code("8005c9f347f0326a")
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

torch_seed = 0

# Create prediction and label arrays
# preds: class predictions (0 or 1 for binary classification)
# labels: ground truth labels (0 or 1 for binary classification)
# pred_probs: probability scores for each class, shape (batch_size, 2)

preds = np.array([0, 1, 1, 0, 1, 1])
labels = np.array([0, 1, 0, 0, 1, 1])
pred_probs = np.array([
    [0.9, 0.1],
    [0.2, 0.8],
    [0.7, 0.3],
    [0.8, 0.2],
    [0.3, 0.7],
    [0.1, 0.9]
])

ARGS = {
    'preds': preds,
    'labels': labels,
    'pred_probs': pred_probs
}
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
build_tf_to_pytorch_map Ran
ran; our contract draft was wrong, not the code
owaisCS/TestHateSpeech/bert/modeling_transfo_xl.py
code served (permissive licence) · get_code("35ef111fc00c21b4")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class Config:
    def __init__(self):
        self.tie_projs = [False]
        self.tie_weight = True
        self.untie_r = False

class LayerNorm(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.weight = nn.Parameter(torch.randn(dim))
        self.bias = nn.Parameter(torch.randn(dim))

class DecAttn(nn.Module):
    def __init__(self, d_model=4, d_head=2):
        super().__init__()
        self.layer_norm = LayerNorm(d_model)
        self.o_net = nn.Linear(d_model, d_model)
        self.qkv_net = nn.Linear(d_model, 3 * d_model)
        self.r_net = nn.Linear(d_model, d_model)
        self.r_r_bias = nn.Parameter(torch.randn(d_model))
        self.r_w_bias = nn.Parameter(torch.randn(d_model))

class PosFeedForward(nn.Module):
    def __init__(self, d_model=4, d_ff=8):
        super().__init__()
        self.layer_norm = LayerNorm(d_model)
        self.CoreNet = nn.Sequential(
            nn.Linear(d_model, d_ff),
            nn.ReLU(),
            nn.Linear(d_ff, d_ff),
            nn.Linear(d_ff, d_model)
        )

class TransformerLayer(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.dec_attn = DecAttn(d_model)
        self.pos_ff = PosFeedForward(d_model)

class WordEmb(nn.Module):
    def __init__(self, vocab_size=100, d_model=4, n_cutoffs=1):
        super().__init__()
        self.emb_layers = nn.ModuleList([nn.Embedding(vocab_size, d_model) for _ in range(n_cutoffs)])
        self.emb_projs = nn.ModuleList([nn.Linear(d_model, d_model) for _ in range(n_cutoffs)])

class AdaptiveSoftmax(nn.Module):
    def __init__(self, vocab_size=100, d_model=4, n_cutoffs=1):
        super().__init__()
        self.cluster_weight = nn.Parameter(torch.randn(n_cutoffs, d_model))
        self.cluster_bias = nn.Parameter(torch.randn(n_cutoffs))
        self.out_layers = nn.ModuleList([nn.Linear(d_model, vocab_size) for _ in range(n_cutoffs)])
        self.out_projs = nn.ModuleList([nn.Linear(d_model, d_model) for _ in range(n_cutoffs)])

class Transformer(nn.Module):
    def __init__(self, d_model=4, n_layers=2, n_cutoffs=1):
        super().__init__()
        self.word_emb = WordEmb(vocab_size=100, d_model=d_model, n_cutoffs=n_cutoffs)
        self.layers = nn.ModuleList([TransformerLayer(d_model) for _ in range(n_layers)])
        self.r_r_bias = nn.Parameter(torch.randn(d_model))
        self.r_w_bias = nn.Parameter(torch.randn(d_model))

class Model(nn.Module):
    def __init__(self, d_model=4, n_layers=2, n_cutoffs=1):
        super().__init__()
        self.transformer = Transformer(d_model=d_model, n_layers=n_layers, n_cutoffs=n_cutoffs)
        self.crit = AdaptiveSoftmax(vocab_size=100, d_model=d_model, n_cutoffs=n_cutoffs)

config = Config()
model = Model(d_model=4, n_layers=2, n_cutoffs=1)

ARGS = {
    'model': model,
    'config': config
}
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 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
convert_examples_to_features_sst Ran
ran on a synthesized input
owaisCS/TestHateSpeech/hiex/soc_algo.py
code served (permissive licence) · get_code("a6e55b7bc228bc28")
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

class DotDict:
    def __init__(self, **kwargs):
        for k, v in kwargs.items():
            setattr(self, k, v)

class SimpleTokenizer:
    def convert_tokens_to_ids(self, tokens):
        # Simple mapping: each token maps to its position
        return list(range(len(tokens)))

# Create example objects
example1 = DotDict(
    text=['hello', 'world', 'test'],
    mapping=[0, 1, 2],
    label=1,
    offset=0
)

example2 = DotDict(
    text=['foo', 'bar'],
    mapping=[0, 1],
    label=0,
    offset=1
)

examples = [example1, example2]

tokenizer = SimpleTokenizer()

max_seq_length = 8

ARGS = {
    'examples': examples,
    'max_seq_length': max_seq_length,
    'tokenizer': tokenizer
}
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
owaisCS/TestHateSpeech/bert/modeling_gpt2.py
code served (permissive licence) · get_code("8d23fbe2b99b840b")
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 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)

# Create a small tensor for testing
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 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
gelu Ran
ran, honoured the contract we drafted
owaisCS/TestHateSpeech/bert/modeling.py
pointer only (licence: MIT); the stored copy get_code serves, from tanmay1618/text_to_sql_bert, is pointer only (licence: NONE) · get_code("fdc64f4c72036ae4")
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 tanmay1618/text_to_sql_bert, 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.

pearson_and_spearman Ran
ran on a synthesized input
owaisCS/TestHateSpeech/run_model.py
code served (permissive licence) · get_code("0e2ab003fa4ca542")
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
from scipy.stats import pearsonr, spearmanr

# The function takes preds and labels as arguments
# and calls pearsonr and spearmanr on them
# These functions expect 1D array-like objects

# Create small prediction and label arrays
np.random.seed(0)
preds = np.array([0.1, 0.5, 0.3, 0.8, 0.2, 0.9])
labels = np.array([0.15, 0.48, 0.35, 0.75, 0.25, 0.85])

ARGS = {
    'preds': preds,
    'labels': labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
sample_logits Ran
ran; our contract draft was wrong, not the code
owaisCS/TestHateSpeech/bert/modeling_transfo_xl_utilities.py
code served (permissive licence) · get_code("93228a3eb5c4d179")
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 3, dtype family float, shape (2, 3, 6) 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 torch.nn as nn

torch.manual_seed(0)

# Small embedding layer
n_vocab = 20
n_emb = 4
embedding = nn.Embedding(n_vocab, n_emb)

# Bias vector
bias = torch.randn(n_vocab)

# Labels: [b1, b2] with valid vocab indices
b1, b2 = 2, 3
labels = torch.randint(0, n_vocab, (b1, b2))

# Inputs: [b1, b2, n_emb]
inputs = torch.randn(b1, b2, n_emb)

# Sampler that implements the sample() method
class LogUniformSampler:
    def __init__(self, n_vocab, n_sample=5):
        self.n_vocab = n_vocab
        self.n_sample = n_sample
    
    def sample(self, labels):
        # Sample negative samples
        neg_samples = torch.randint(0, self.n_vocab, (self.n_sample,))
        
        # Log probabilities
        true_log_probs = torch.randn(labels.size(0), labels.size(1))
        samp_log_probs = torch.randn(self.n_sample)
        
        return true_log_probs, samp_log_probs, neg_samples

sampler = LogUniformSampler(n_vocab=n_vocab, n_sample=5)

ARGS = {
    "embedding": embedding,
    "bias": bias,
    "labels": labels,
    "inputs": inputs,
    "sampler": sampler
}
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 3, dtype family float, shape (2, 3, 6) — shape (2, 3, 6) 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
_SamplingAndOcclusionAlgo Not yet run
unverified (harvested, no recorded run)
BrendanKennedy/contextualizing-hate-speech-models-with-explanations/hiex/soc_algo.py
code served (permissive licence) · get_code("8075d776e4211fb5")
How it ran

no invocation recorded.

examples_to_bow Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/run_baselines.py
code served (permissive licence) · get_code("7151c8535ee0144d")
How it ran

no invocation recorded.

load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/bert/modeling.py
pointer only (licence: MIT); the stored copy get_code serves, from sreyan88/toxicity-detection-in-spoken-utterances, is pointer only (licence: NONE) · get_code("b1a7180868dd8d6a")
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 sreyan88/toxicity-detection-in-spoken-utterances, 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. No invocation recorded.

load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/bert/modeling_gpt2.py
code served (permissive licence) · get_code("a62604f618a8cc82")
How it ran

no invocation recorded.

load_tf_weights_in_openai_gpt Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/bert/modeling_openai.py
code served (permissive licence) · get_code("46f305675277e757")
How it ran

no invocation recorded.

load_tf_weights_in_transfo_xl Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/bert/modeling_transfo_xl.py
code served (permissive licence) · get_code("1ebc2bf2c3cddc4d")
How it ran

no invocation recorded.

plot_score_array Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/visualize.py
code served (permissive licence) · get_code("d7e129db40fdbd06")
How it ran

no invocation recorded.

simple_accuracy Not yet run
unverified (harvested, no recorded run)
owaisCS/TestHateSpeech/run_model.py
code served (permissive licence) · get_code("3c241ecfe3749a6d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 12 are also present in other papers whose code we hold (10 with at least one paper dated earlier, 6 the same month, 9 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
swish 206 other papers
35 dated earlier, 3 the same month, 167 later, 1 same year, order not determinable · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
gelu 198 other papers
47 dated earlier, 5 the same month, 144 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
simple_accuracy 59 other papers
16 dated earlier, 1 the same month, 41 later, 1 same year, order not determinable
1506.05865 (2015-06)
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
1509.01626 (2015-09)
Character-level Convolutional Networks for Text Classification *
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 56 more not named here
gelu 51 other papers
16 dated earlier, 1 the same month, 34 later · 8 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
and 48 more not named here
load_tf_weights_in_bert 15 other papers
6 dated earlier, 7 later, 2 same year, order not determinable
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
1911.00720 (2019-11)
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
and 12 more not named here
sample_logits 14 other papers
8 dated earlier, 1 the same month, 5 later · 2 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
and 11 more not named here
build_tf_to_pytorch_map 10 other papers
7 dated earlier, 1 the same month, 2 later
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
and 7 more not named here
load_tf_weights_in_gpt2 4 other papers
4 dated earlier
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
1911.00720 (2019-11)
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
and 1 more not named here
load_tf_weights_in_openai_gpt 3 other papers
3 dated earlier
1906.01698 (2019-06)
Open Sesame: Getting Inside BERT's Linguistic Knowledge
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
1911.00720 (2019-11)
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
load_tf_weights_in_transfo_xl 3 other papers
3 dated earlier
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
1908.09355 (2019-08)
Patient Knowledge Distillation for BERT Model Compression
1911.00720 (2019-11)
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
DotDict
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2103.10415 (2021-03)
Refining Language Models with Compositional Explanations
acc_and_f1 1 other paper
1 later
2103.10415 (2021-03)
Refining Language Models with Compositional Explanations

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways. Such biases manifest in false positives when these identifiers are present, due to models' inability to learn the contexts which constitute a hateful usage of identifiers. We extract post-hoc explanations from fine-tuned BERT classifiers to detect bias towards identity terms. Then, we propose a novel regularization technique based on these explanations that encourages models to learn from the context of group identifiers in addition to the identifiers themselves. Our approach improved over baselines in limiting false positives on out-of-domain data while maintaining or improving in-domain performance. † * Authors contributed equally † Code is available here

For agents

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

get_harvested_code_for_paper("2005.02439")
get_code_for_paper("2005.02439")
have("2005.02439")

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

curl https://syntology.ai/api/ran/2005.02439.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.02439.svg)](https://syntology.ai/paper/2005.02439)

Connect an agent — have() is free.