SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.13830 · 2020

Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure 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/2003.13830.json · badge: /api/ran/2003.13830.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
neccam/slt canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
OvrK12/slt community (classifier label)
classifier basis: plan_row
1 ran · 1 no recorded run
FunctionStatusWhere it lives
build_gradient_clipper Ran
ran on a synthesized input
neccam/slt/signjoey/builders.py
code served (permissive licence) · get_code("8eaa021a52970450")
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 function. 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
from torch import nn

torch.manual_seed(0)

# Test case 1: config with clip_grad_val
config_clip_val = {
    'clip_grad_val': 1.0
}

# Test case 2: config with clip_grad_norm
config_clip_norm = {
    'clip_grad_norm': 2.0
}

# Test case 3: empty config (no clipping)
config_empty = {}

# We'll use the first config as the main test case
ARGS = {
    'config': config_clip_val
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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_optimizer Ran
ran on a synthesized input
neccam/slt/signjoey/builders.py
code served (permissive licence) · get_code("31c62f8ab3831b97")
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 Adam. 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)

# Create a simple neural network model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Instantiate the model
model = SimpleModel()

# Create a configuration dictionary with optimizer settings
config = {
    'optimizer': 'adam',
    'learning_rate': 0.001,
    'weight_decay': 0.0001,
    'eps': 1e-8,
    'betas': (0.9, 0.999),
    'amsgrad': False
}

# Get the model parameters
parameters = model.parameters()

ARGS = {
    'config': config,
    'parameters': parameters
}
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 Adam — a Adam output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Adam 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_scheduler Ran
ran on a synthesized input
neccam/slt/signjoey/builders.py
code served (permissive licence) · get_code("ba6e0870421f0eea")
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. 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 torch.nn as nn
from torch.optim import Adam, Optimizer

torch.manual_seed(0)

# Create a minimal model to optimize
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = Adam(model.parameters(), lr=0.001)

# Create a minimal config dict with scheduling information
config = {
    'scheduling': 'plateau',
    'decrease_factor': 0.1,
    'patience': 10
}

# Define the arguments for build_scheduler
ARGS = {
    'config': config,
    'optimizer': optimizer,
    'scheduler_mode': 'min',
    'hidden_size': 512
}
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
get_activation Ran
ran on a synthesized input
neccam/slt/signjoey/embeddings.py
code served (permissive licence) · get_code("3ec1d5ba938c34ce")
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 ReLU. 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
from torch import nn

torch.manual_seed(0)

ARGS = {
    'activation_type': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
load_dataset_file Ran
ran; our contract draft was wrong, not the code
OvrK12/slt/signjoey/dataset.py
code served (permissive licence) · get_code("d7bddbc9c40ab1bc")
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 pickle
import gzip
import tempfile
import os

# Create a temporary gzip file with pickled data
temp_dir = tempfile.mkdtemp()
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "data"}
}

filename = os.path.join(temp_dir, "test_dataset.pkl.gz")
with gzip.open(filename, 'wb') as f:
    pickle.dump(test_data, f)

ARGS = {
    "filename": filename
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
token_batch_size_fn Ran
ran on a synthesized input
neccam/slt/signjoey/data.py
code served (permissive licence) · get_code("59df93d528ae3dc8")
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

torch.manual_seed(0)

# The function accesses new.sgn, new.gls, new.txt
# Each of these should be sequences (lists or tensors) with len()
class Sample:
    def __init__(self, sgn, gls, txt):
        self.sgn = sgn
        self.gls = gls
        self.txt = txt

# Create a sample object with list attributes of different lengths
new = Sample(
    sgn=[1, 2, 3],           # length 3
    gls=[4, 5],              # length 2
    txt=[6, 7, 8, 9]         # length 4
)

# Function parameters: new, count, sofar
ARGS = {
    "new": new,
    "count": 1,
    "sofar": 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 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
create_config Not yet run
unverified (harvested, no recorded run)
OvrK12/slt/configs/generate_config.py
code served (permissive licence) · get_code("e6f5331cdef4924c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 5 later) and 2 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
load_dataset_file 2 other papers
2 later
2204.04916 (2022-04)
A Token-level Contrastive Framework for Sign Language Translation
2607.11215 (2026-07)
Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation
build_gradient_clipper 1 other paper
1 later
2204.04916 (2022-04)
A Token-level Contrastive Framework for Sign Language Translation
build_scheduler 1 other paper
1 later
2204.04916 (2022-04)
A Token-level Contrastive Framework for Sign Language Translation
get_activation 1 other paper
1 later
2204.04916 (2022-04)
A Token-level Contrastive Framework for Sign Language Translation
token_batch_size_fn 1 other paper
1 later
2204.04916 (2022-04)
A Token-level Contrastive Framework for Sign Language Translation

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

Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the-art in translation requires gloss level tokenization in order to work. We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation while being trainable in an end-to-end manner. This is achieved by using a Connectionist Temporal Classification (CTC) loss to bind the recognition and translation problems into a single unified architecture. This joint approach does not require any ground-truth timing information, simultaneously solving two co-dependant sequence-to-sequence learning problems and leads to significant performance gains. We evaluate the recognition and translation performances of our approaches on the challenging RWTH-PHOENIX-Weather-2014T (PHOENIX14T) dataset. We report state-of-the-art sign language recognition and translation results achieved by our Sign Language Transformers. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models, in some cases more than doubling the performance (9.58 vs. 21.80 BLEU-4 Score). We also share new baseline translation results using transformer networks for several other text-to-text sign language translation tasks.

For agents

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

get_harvested_code_for_paper("2003.13830")
get_code_for_paper("2003.13830")
have("2003.13830")

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

curl https://syntology.ai/api/ran/2003.13830.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.13830.svg)](https://syntology.ai/paper/2003.13830)

Connect an agent — have() is free.