SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.07461 · EMNLP · 2018

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Felix Hill, Amanpreet Singh, Alex Wang, Samuel Bowman, Julian Michael, Omer Levy

arXiv · PDF · Open in the Atlas

Code that ran

14 of 14 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, 1 violated it and 6 have no contract verdict; 5 failures of our instrument; 0 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/1804.07461.json · badge: /api/ran/1804.07461.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
jsalt18-sentence-repl/jiant canonical (classifier label)
classifier basis: census
13 ran · 0 no recorded run
nyu-mll/GLUE-baselines canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
batched_index_select Ran
ran; our contract draft was wrong, not the code
jsalt18-sentence-repl/jiant/jiant/ext/allennlp.py
code served (permissive licence) · get_code("e445a3b7d6a58154")
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, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Set up the arguments for batched_index_select
# The function signature is:
# batched_index_select(target: torch.Tensor, indices: torch.LongTensor, flattened_indices: Optional[torch.LongTensor]=None)

# target: torch.Tensor of shape (batch_size, sequence_length, embedding_size)
batch_size = 2
sequence_length = 5
embedding_size = 4
target = torch.randn(batch_size, sequence_length, embedding_size)

# indices: torch.LongTensor of shape (batch_size, d_1, ..., d_n)
# Let's use shape (batch_size, 3) where each index is in range [0, sequence_length)
indices = torch.randint(0, sequence_length, (batch_size, 3), dtype=torch.long)

# flattened_indices: Optional[torch.LongTensor] - we can pass None and let the function compute it
flattened_indices = None

ARGS = {
    "target": target,
    "indices": indices,
    "flattened_indices": flattened_indices,
}
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, 4) — shape (2, 3, 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
compare_dataset_with_metadata Ran
ran on a synthesized input
jsalt18-sentence-repl/jiant/jiant/shared/caching.py
code served (permissive licence) · get_code("eaa6b3cef2ce9444")
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 bool, 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 torch.utils.data

torch.manual_seed(0)

# Create a simple dataset wrapper class that mimics torch.utils.data.TensorDataset
class DatasetWithMetadata:
    def __init__(self, tensors, metadata):
        self.dataset = torch.utils.data.TensorDataset(*tensors)
        self.metadata = metadata

# Create tensors for the first dataset
tensors1 = [
    torch.randn(2, 4),
    torch.randn(2, 3)
]
metadata1 = {"name": "dataset1", "version": 1}
d1 = DatasetWithMetadata(tensors1, metadata1)

# Create identical tensors for the second dataset (to make them equal)
tensors2 = [
    tensors1[0].clone(),
    tensors1[1].clone()
]
metadata2 = {"name": "dataset1", "version": 1}
d2 = DatasetWithMetadata(tensors2, metadata2)

ARGS = {
    "d1": d1,
    "d2": d2
}
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 bool, 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
compare_tensor_tuples Ran
ran on a synthesized input
jsalt18-sentence-repl/jiant/jiant/shared/caching.py
code served (permissive licence) · get_code("0f5c37217af75b26")
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 bool, 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)

# Create two tuples of tensors that are equal
tup1 = (
    torch.randn(2, 4),
    torch.randn(2, 3),
    torch.randn(2, 5)
)

# Create identical tensors for tup2 to test equality
tup2 = (
    tup1[0].clone(),
    tup1[1].clone(),
    tup1[2].clone()
)

ARGS = {
    "tup1": tup1,
    "tup2": tup2
}
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 bool, 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
complex_backpropagate Ran
ran on a synthesized input
jsalt18-sentence-repl/jiant/jiant/shared/runner.py
code served (permissive licence) · get_code("9b5f1ac1298e3440")
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 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

# Create optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a loss tensor (simulating output from loss computation)
# For n_gpu > 1 case, loss should be a 1D tensor that can be averaged
loss = torch.tensor([0.5, 0.3], dtype=torch.float32, requires_grad=True)

ARGS = {
    "loss": loss,
    "optimizer": optimizer,
    "model": model,
    "fp16": False,
    "n_gpu": 2,
    "gradient_accumulation_steps": 2,
    "max_grad_norm": 1.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
apex, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
convert_to_chunks Ran
ran; our contract draft was wrong, not the code
jsalt18-sentence-repl/jiant/jiant/shared/caching.py
code served (permissive licence) · get_code("b91635f00cdc7b71")
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.

import torch
import numpy as np
import math

torch.manual_seed(0)

# Create sample data - a simple list of numbers
data = list(range(20))

# Define chunk_size
chunk_size = 6

# Build ARGS dictionary
ARGS = {
    "data": data,
    "chunk_size": chunk_size,
}
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 — 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
flat_collate_fn Ran
ran, honoured the contract we drafted
jsalt18-sentence-repl/jiant/jiant/tasks/core.py
code served (permissive licence) · get_code("8f7619b2828926ea")
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 int, shape (2, 3) 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 numpy as np
import torch.utils.data.dataloader as dataloader

torch_seed = 0

# Test case 1: numpy array batch
batch_numpy = [np.array([1, 2, 3]), np.array([4, 5, 6])]

# Test case 2: int batch
batch_int = [1, 2, 3]

# Test case 3: float batch
batch_float = [1.5, 2.5, 3.5]

# Test case 4: string batch
batch_str = ["hello", "world"]

# Test case 5: list batch (should return as-is)
batch_list = [[1, 2], [3, 4]]

# Test case 6: dict batch (should return as-is)
batch_dict = [{"a": 1}, {"b": 2}]

# Test case 7: set batch (should return as-is)
batch_set = [{"x", "y"}, {"z"}]

# We'll use the numpy array batch as the primary test
ARGS = {
    "batch": batch_numpy
}
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 Tensor, ndim 2, dtype family int, shape (2, 3) — shape (2, 3) 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
get_tasks Ran
ran; our contract draft was wrong, not the code
nyu-mll/GLUE-baselines/download_glue_data.py
pointer only (licence: NONE) · get_code("3caf26b311c98658")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nyu-mll/GLUE-baselines 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.

init_cuda_from_args Ran
ran on a synthesized input
jsalt18-sentence-repl/jiant/jiant/shared/initialization.py
code served (permissive licence) · get_code("fa0fcf05318dae3d")
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 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

ARGS = {
    'no_cuda': True,
    'local_rank': -1,
    'fp16': False,
    'verbose': True
}
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 tuple, ndim 1, dtype family float — 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
init_seed Ran
ran on a synthesized input
jsalt18-sentence-repl/jiant/jiant/shared/initialization.py
code served (permissive licence) · get_code("540028e9d806d8a8")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 numpy as np
import random
import torch

torch.manual_seed(0)

ARGS = {
    "given_seed": 42,
    "n_gpu": 0,
    "verbose": True
}
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
masked_softmax Ran
ran on a synthesized input
jsalt18-sentence-repl/jiant/jiant/ext/allennlp.py
code served (permissive licence) · get_code("16cde5ff8ae0a586")
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

torch.manual_seed(0)

# Create a small vector tensor with shape (2, 4) - batch_size=2, num_classes=4
vector = torch.randn(2, 4)

# Create a mask tensor with shape (2,) that will be unsqueezed to match vector dimensions
mask = torch.tensor([[1.0, 1.0, 0.0, 1.0], [1.0, 0.0, 1.0, 0.0]])

ARGS = {
    "vector": vector,
    "mask": mask,
    "dim": -1
}
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
metadata_collate_fn Ran
ran; our contract draft was wrong, not the code
jsalt18-sentence-repl/jiant/jiant/tasks/core.py
code served (permissive licence) · get_code("61ffc5549a75fe3c")
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 numpy as np

torch.manual_seed(0)

# The function takes a list of dictionaries and collates them by grouping
# values for each key. We need to create a list of metadata dictionaries.

metadata = [
    {
        "id": 1,
        "name": "sample_1",
        "tensor": torch.randn(2, 4),
        "score": 0.95
    },
    {
        "id": 2,
        "name": "sample_2",
        "tensor": torch.randn(2, 4),
        "score": 0.87
    }
]

ARGS = {
    "metadata": metadata
}
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 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
resolve_is_lower_case Ran
ran, violated the contract we drafted
jsalt18-sentence-repl/jiant/jiant/shared/model_resolution.py
code served (permissive licence) · get_code("e17e83a5650fd73c")
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 bool, 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 transformers
from transformers import BertTokenizer, AlbertTokenizer
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a mock BertTokenizer with the required attributes
bert_tokenizer = MagicMock(spec=BertTokenizer)
bert_tokenizer.basic_tokenizer = MagicMock()
bert_tokenizer.basic_tokenizer.do_lower_case = True

# Test with different tokenizer types
ARGS = {
    "tokenizer": bert_tokenizer
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
resolve_warmup_steps Ran
ran, honoured the contract we drafted
jsalt18-sentence-repl/jiant/jiant/shared/model_setup.py
code served (permissive licence) · get_code("36c8a80131f2e20a")
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)

# Analyzing the function:
# - t_total: used in multiplication with warmup_proportion, so needs to be numeric
# - warmup_steps: can be None or a numeric value
# - warmup_proportion: can be None or a numeric value between 0 and 1
# The function validates that exactly one of warmup_steps or warmup_proportion is provided

# Test case 1: warmup_steps is provided, warmup_proportion is None
ARGS = {
    "t_total": 1000,
    "warmup_steps": 100,
    "warmup_proportion": None
}
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
weighted_sum Ran
ran; our contract draft was wrong, not the code
jsalt18-sentence-repl/jiant/jiant/ext/allennlp.py
code served (permissive licence) · get_code("2f417d486bcad523")
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

torch.manual_seed(0)

# Test case 1: 2D attention, 3D matrix (batch_size=2, num_words=3, embedding_dim=4)
matrix_1 = torch.randn(2, 3, 4)
attention_1 = torch.randn(2, 3)
attention_1 = torch.nn.functional.softmax(attention_1, dim=-1)

ARGS = {
    "matrix": matrix_1,
    "attention": attention_1,
}
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

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 14 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 14 later) and 0 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
get_tasks 13 other papers
1 dated earlier, 12 later
1711.05225 (2017-11)
CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.02762 (2019-06)
Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
and 10 more not named here
weighted_sum 5 other papers
1 dated earlier, 4 later
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
and 2 more not named here
metadata_collate_fn 4 other papers
4 later
2003.02249 (2020-03)
jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
2112.01753 (2021-12)
Probing Linguistic Information For Logical Inference In Pre-trained Language Models
and 1 more not named here
batched_index_select 3 other papers
1 dated earlier, 2 later
1609.08144 (2016-09)
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
2112.01753 (2021-12)
Probing Linguistic Information For Logical Inference In Pre-trained Language Models
flat_collate_fn 3 other papers
3 later
2003.02249 (2020-03)
jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
2112.01753 (2021-12)
Probing Linguistic Information For Logical Inference In Pre-trained Language Models
2404.02827 (2024-04)
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
masked_softmax 2 other papers
2 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
2112.01753 (2021-12)
Probing Linguistic Information For Logical Inference In Pre-trained Language Models
resolve_is_lower_case 2 other papers
2 later
2112.01753 (2021-12)
Probing Linguistic Information For Logical Inference In Pre-trained Language Models
2404.02827 (2024-04)
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
resolve_warmup_steps 2 other papers
2 later
2112.01753 (2021-12)
Probing Linguistic Information For Logical Inference In Pre-trained Language Models
2404.02827 (2024-04)
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
compare_dataset_with_metadata 1 other paper
1 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
compare_tensor_tuples 1 other paper
1 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
complex_backpropagate 1 other paper
1 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
convert_to_chunks 1 other paper
1 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
init_cuda_from_args 1 other paper
1 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data
init_seed 1 other paper
1 later
2010.04762 (2020-10)
Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data

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

For natural language understanding (NLU) technology to be maximally useful, it must be able to process language in a way that is not exclusive to a single task, genre, or dataset. In pursuit of this objective, we introduce the General Language Understanding Evaluation (GLUE) benchmark, a collection of tools for evaluating the performance of models across a diverse set of existing NLU tasks. By including tasks with limited training data, GLUE is designed to favor and encourage models that share general linguistic knowledge across tasks. GLUE also includes a hand-crafted diagnostic test suite that enables detailed linguistic analysis of models. We evaluate baselines based on current methods for transfer and representation learning and find that multi-task training on all tasks performs better than training a separate model per task. However, the low absolute performance of our best model indicates the need for improved general NLU systems. 1 To evaluate on the private test data, users of the benchmark must submit to gluebenchmark.com

For agents

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

get_harvested_code_for_paper("1804.07461")
get_code_for_paper("1804.07461")
have("1804.07461")

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

curl https://syntology.ai/api/ran/1804.07461.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.07461.svg)](https://syntology.ai/paper/1804.07461)

Connect an agent — have() is free.