SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1409.3215 · NeurIPS · 2014

Sequence to Sequence Learning with Neural Networks

Quoc Le, Oriol Vinyals, Ilya Sutskever

arXiv · PDF · Open in the Atlas

Code that ran

21 of 25 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; 3 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 9 failures of our instrument; 4 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/1409.3215.json · badge: /api/ran/1409.3215.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
la-serene/English-German-Translation-System community (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
2023-MindSpore-1/ms-code-61 community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
rileynwong/pytorch-seq2seq-joke2punchline reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
IvanVassi/Seq2Seq-w-attention-dialogue-model reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
Guillem96/pointer-nn-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
hnt4499/seq2seq reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
a1085728420/seq2seq-mindspore community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
yash-nishaant/Seq2Seq-Chatbot reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
batch Ran
ran, honoured the contract we drafted
Guillem96/pointer-nn-pytorch/data.py
pointer only (licence: GPL-3.0) · get_code("796b2511367209ba")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Guillem96/pointer-nn-pytorch, is not in the permissive set Syntology serves inline. 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.

clean_text Ran
ran; our contract draft was wrong, not the code
yash-nishaant/Seq2Seq-Chatbot/chatbot.py
pointer only (licence: NONE) · get_code("8eaa3f3c2fa1ed5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yash-nishaant/Seq2Seq-Chatbot 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.

count_parameters Ran
ran, honoured the contract we drafted
hnt4499/seq2seq/seq2seq/model.py
code served (permissive licence) · get_code("0f26a596e83c5565")
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 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 torch.nn as nn

torch.manual_seed(0)

# Build a small model with trainable parameters
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

model = SimpleModel()

ARGS = {
    "model": model
}
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 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
expand_contractions Ran
ran on a synthesized input
la-serene/English-German-Translation-System/clean_data.py
code served (permissive licence) · get_code("f7dc02b250498341")
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 str. 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 re

en_contraction_map = {"let's": 'let us', "'d better": ' had better', "'s": ' is', "'re": ' are', "'m": ' am', "'ll": ' will', "'d": ' would', "'ve": ' have', "'em": ' them', "won't": 'will not', "n't": ' not', 'cannot': 'can not'}

ger_contraction_map = {"'s": ' ist', 'ä': 'ae', 'ö': 'oe', 'ü': 'ue', 'ß': 'ss', "'ne ": 'eine ', "'n ": 'ein ', 'am ': 'an dem ', 'aufs ': 'auf das ', 'durchs ': 'durch das ', 'fuers ': 'fuer das ', 'hinterm ': 'hinter dem ', 'im ': 'in dem ', 'uebers ': 'ueber das ', 'ums ': 'um das ', 'unters ': 'unter das ', 'unterm ': 'unter dem ', 'vors ': 'vor das ', 'vorm ': 'vor dem ', 'zum ': 'zu dem ', 'ins ': 'in das ', 'ans ': 'an das ', 'vom ': 'von dem', 'beim ': 'bei dem ', 'zur  ': 'zu der '}

def expand_contractions(text, lang='en'):
    mapping = en_contraction_map
    if lang == 'ger':
        mapping = ger_contraction_map
    for key, value in mapping.items():
        text = re.sub(key, value, text)
    return text

ARGS = {
    'text': "I can't believe it's already noon. Let's go won't we?",
    'lang': 'en'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_instance_features Ran
ran on a synthesized input
2023-MindSpore-1/ms-code-61/src/create_data.py
code served (permissive licence) · get_code("1e7dce39d953aaa5")
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 collections
import numpy as np

class MockTokenizer:
    def __init__(self, vocab_size=100):
        self.vocab_size = vocab_size
    
    def convert_tokens_to_ids(self, tokens):
        # Simple mock: convert token strings to ids based on hash
        return [hash(token) % self.vocab_size for token in tokens]

class SampleInstance:
    def __init__(self, source_tokens, target_tokens):
        self.source_tokens = source_tokens
        self.target_tokens = target_tokens

# Create tokenizers
tokenizer_src = MockTokenizer(vocab_size=100)
tokenizer_trg = MockTokenizer(vocab_size=100)

# Create a sample instance with source and target tokens
instance = SampleInstance(
    source_tokens=["hello", "world"],
    target_tokens=["bonjour", "monde", "comment"]
)

# Define parameters
max_seq_length = 50
bucket = [8, 16, 32, 64]

ARGS = {
    "instance": instance,
    "tokenizer_src": tokenizer_src,
    "tokenizer_trg": tokenizer_trg,
    "max_seq_length": max_seq_length,
    "bucket": bucket
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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_model_metadata Ran
ran on a synthesized input
la-serene/English-German-Translation-System/utils.py
code served (permissive licence) · get_code("8f313e40a3c2781f")
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 json
import tempfile
import os

# Create a temporary directory and a temporary JSONL file with model metadata
temp_dir = tempfile.mkdtemp()
save_path = os.path.join(temp_dir, 'weights.jsonl')

# Write test data to the file
test_data = {
    "model_v1": {
        "version": "1.0",
        "layers": 12,
        "hidden_dim": 768,
        "parameters": 110000000
    },
    "model_v2": {
        "version": "2.0",
        "layers": 24,
        "hidden_dim": 1024,
        "parameters": 350000000
    }
}

with open(save_path, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    'model_name': 'model_v1',
    'save_path': save_path
}
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 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_vocab Ran
ran on a synthesized input
la-serene/English-German-Translation-System/tokenizer.py
code served (permissive licence) · get_code("a6697bcb0adf201d")
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 torch.nn as nn

class MockTokenizer:
    def get_vocabulary(self):
        return ["<pad>", "hello", "world", "test"]

tokenizer = MockTokenizer()

ARGS = {
    "tokenizer": tokenizer
}
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 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
get_word_to_idx Ran
ran on a synthesized input
la-serene/English-German-Translation-System/tokenizer.py
code served (permissive licence) · get_code("81ea9cff1f78cbfc")
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.

class MockTokenizer:
    def __init__(self):
        self.vocabulary = ["hello", "world", "python", "test", "code"]
    
    def get_vocabulary(self):
        return self.vocabulary

tokenizer = MockTokenizer()

ARGS = {
    "tokenizer": tokenizer
}
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
is_model_exist Ran
ran on a synthesized input
la-serene/English-German-Translation-System/utils.py
code served (permissive licence) · get_code("a083cb6994fa7695")
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 json
import tempfile
import os

# Create a temporary directory and a temporary JSONL file
temp_dir = tempfile.mkdtemp()
save_path = os.path.join(temp_dir, 'weights.jsonl')

# Create a valid JSON file with some model names
test_data = {
    "model_v1": {"path": "path/to/model1", "size": 1000},
    "model_v2": {"path": "path/to/model2", "size": 2000},
    "bert_base": {"path": "path/to/bert", "size": 3000}
}

with open(save_path, 'w') as f:
    json.dump(test_data, f)

# Define arguments for is_model_exist
ARGS = {
    'model_name': 'model_v1',
    'save_path': save_path
}
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 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
load_result_data Ran
ran on a synthesized input
a1085728420/seq2seq-mindspore/src/seq2seq_model/bleu_calculate.py
code served (permissive licence) · get_code("e06ad5de44fed837")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np
import tempfile
import os

# Create a temporary numpy file to use as input
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_result.npy")

# Create sample data and save it
sample_data = np.array([1, 2, 3, 4], dtype=np.float32)
np.save(temp_file, sample_data)

ARGS = {
    "result_npy_addr": temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
merge Ran
ran; our contract draft was wrong, not the code
2023-MindSpore-1/ms-code-61/model_utils/config.py
code served (permissive licence) · get_code("b9e24c3e3e0e88a7")
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 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 argparse

torch.manual_seed(0)

# Create a mock args object with some attributes
args = argparse.Namespace(
    learning_rate=0.001,
    batch_size=32,
    epochs=10,
    model_name="test_model",
    debug=True,
    seed=42
)

# Create a base configuration dictionary
cfg = {
    "default_lr": 0.0001,
    "default_batch": 16,
    "dataset": "cifar10"
}

ARGS = {
    "args": args,
    "cfg": cfg
}
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 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
normalizeString Ran
ran; our contract draft was wrong, not the code
IvanVassi/Seq2Seq-w-attention-dialogue-model/backend/inference.py
pointer only (licence: NONE) · get_code("98d5880d13c72280")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, IvanVassi/Seq2Seq-w-attention-dialogue-model 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.

normalize_string Ran
ran; our contract draft was wrong, not the code
rileynwong/pytorch-seq2seq-joke2punchline/seq2seq.py
pointer only (licence: NONE) · get_code("0249f2927bd76913")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rileynwong/pytorch-seq2seq-joke2punchline 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.

parse_arguments Ran
ran; our contract draft was wrong, not the code
hnt4499/seq2seq/scripts/train_and_evaluate.py
code served (permissive licence) · get_code("2a74b7a19b47b566")
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 Namespace. 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 argparse
import tempfile
import os

# Create temporary config file for testing
temp_dir = tempfile.mkdtemp()
config_path = os.path.join(temp_dir, "config.yaml")
with open(config_path, 'w') as f:
    f.write("model: seq2seq\nbatch_size: 32\n")

# Create temporary resume directory
resume_dir = os.path.join(temp_dir, "resume_checkpoint")
os.makedirs(resume_dir, exist_ok=True)

# Create temporary model path
load_path = os.path.join(temp_dir, "model.pt")
with open(load_path, 'w') as f:
    f.write("dummy model")

ARGS = {
    'argv': ['-c', config_path]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
parse_cli_to_yaml Ran
ran; our contract draft was wrong, not the code
2023-MindSpore-1/ms-code-61/model_utils/config.py
code served (permissive licence) · get_code("738456e1b7388e7e")
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 Namespace. 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 argparse
import ast

# Create minimal parent parser
parent_parser = argparse.ArgumentParser(add_help=False)

# Create base configuration dict with various types
cfg = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'epochs': 10,
    'use_cuda': False,
    'model_name': 'resnet50',
    'dropout': 0.5,
    'debug': True,
    'nested_list': [1, 2, 3],  # This will be skipped since it's a list
    'nested_dict': {'a': 1},   # This will be skipped since it's a dict
}

# Create helper descriptions
helper = {
    'learning_rate': 'Learning rate for optimizer',
    'batch_size': 'Batch size for training',
    'epochs': 'Number of training epochs',
    'use_cuda': 'Whether to use CUDA',
    'model_name': 'Name of the model architecture',
    'dropout': 'Dropout rate',
    'debug': 'Enable debug mode',
}

# Create choices for specific parameters
choices = {
    'model_name': ['resnet50', 'vgg16', 'mobilenet'],
}

# Set config path
cfg_path = 'default_config.yaml'

ARGS = {
    'parser': parent_parser,
    'cfg': cfg,
    'helper': helper,
    'choices': choices,
    'cfg_path': cfg_path,
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
parse_yaml Ran
ran on a synthesized input
2023-MindSpore-1/ms-code-61/model_utils/config.py
code served (permissive licence) · get_code("96a9939953d5992d")
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 tempfile
import os
import yaml

# Create a temporary YAML file with valid config structure
temp_dir = tempfile.mkdtemp()
yaml_path = os.path.join(temp_dir, "config.yaml")

# Write a valid YAML file with 3 documents: config, helper, and choices
yaml_content = """
model: resnet50
learning_rate: 0.001
batch_size: 32
---
model: "Model architecture to use"
learning_rate: "Learning rate for optimization"
batch_size: "Batch size for training"
---
model: [resnet50, resnet101, vgg16]
learning_rate: [0.0001, 0.001, 0.01]
batch_size: [16, 32, 64]
"""

with open(yaml_path, 'w') as f:
    f.write(yaml_content)

ARGS = {
    "yaml_path": yaml_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
readLangs Ran
ran; our contract draft was wrong, not the code
rileynwong/pytorch-seq2seq-joke2punchline/seq2seq.py
pointer only (licence: NONE) · get_code("52625852fa241e82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rileynwong/pytorch-seq2seq-joke2punchline 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.

retrieve_all_models Ran
ran on a synthesized input
la-serene/English-German-Translation-System/utils.py
code served (permissive licence) · get_code("a092c91e31ab7f49")
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 json
import tempfile
import os

# Create a temporary directory and a temporary weights.jsonl file
temp_dir = tempfile.mkdtemp()
weights_file = os.path.join(temp_dir, 'weights.jsonl')

# Write valid JSON data to the file
sample_data = {
    "model_1": {"weights": [0.1, 0.2, 0.3]},
    "model_2": {"weights": [0.4, 0.5, 0.6]},
    "model_3": {"weights": [0.7, 0.8, 0.9]}
}

with open(weights_file, 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    'path': weights_file
}
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
sample Ran
ran, honoured the contract we drafted
Guillem96/pointer-nn-pytorch/data.py
pointer only (licence: GPL-3.0) · get_code("8b887331144b7967")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Guillem96/pointer-nn-pytorch, is not in the permissive set Syntology serves inline. 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.

unicodeToAscii Ran
ran; our contract draft was wrong, not the code
IvanVassi/Seq2Seq-w-attention-dialogue-model/backend/inference.py
pointer only (licence: NONE) · get_code("449b4c4b43a64aca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, IvanVassi/Seq2Seq-w-attention-dialogue-model 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.

unicode_to_ascii Ran
ran; our contract draft was wrong, not the code
rileynwong/pytorch-seq2seq-joke2punchline/seq2seq.py
pointer only (licence: NONE) · get_code("a2ec1e65cd2e8ef4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rileynwong/pytorch-seq2seq-joke2punchline 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.

calculate_sacrebleu Not yet run
unverified (harvested, no recorded run)
a1085728420/seq2seq-mindspore/src/seq2seq_model/bleu_calculate.py
code served (permissive licence) · get_code("80d2a0f8303dc622")
How it ran

no invocation recorded.

convert_to_tf_dataset Not yet run
unverified (harvested, no recorded run)
la-serene/English-German-Translation-System/prepare_data.py
code served (permissive licence) · get_code("26859637d0f6ef9e")
How it ran

no invocation recorded.

prepr Not yet run
unverified (harvested, no recorded run)
IvanVassi/Seq2Seq-w-attention-dialogue-model/backend/inference.py
pointer only (licence: NONE) · get_code("10dca0b4c48e590f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, IvanVassi/Seq2Seq-w-attention-dialogue-model 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.

tokenize_dataset Not yet run
unverified (harvested, no recorded run)
la-serene/English-German-Translation-System/prepare_data.py
code served (permissive licence) · get_code("2be8d8a248dd1ac5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 12 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 7 the same month, 9 later) and 13 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
merge 28 other papers
1 dated earlier, 27 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 25 more not named here
parse_cli_to_yaml 20 other papers
1 dated earlier, 19 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 17 more not named here
parse_yaml 15 other papers
1 dated earlier, 14 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 12 more not named here
batch 2 other papers
1 the same month, 1 later
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1506.03134 (2015-06)
Pointer Networks
count_parameters 2 other papers
1 the same month, 1 later
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1508.04025 (2015-08)
Effective Approaches to Attention-based Neural Machine Translation
get_instance_features 2 other papers
1 dated earlier, 1 later
1406.1078 (2014-06)
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
1902.05509 (2019-02)
MultiGrain: a unified image embedding for classes and instances
parse_arguments 2 other papers
1 the same month, 1 later
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1508.04025 (2015-08)
Effective Approaches to Attention-based Neural Machine Translation
sample 2 other papers
1 the same month, 1 later
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
1506.03134 (2015-06)
Pointer Networks
unicodeToAscii 2 other papers
2 later
1507.04808 (2015-07)
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
2202.13330 (2022-02)
DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
normalize_string 1 other paper
1 the same month
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
readLangs 1 other paper
1 the same month
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate
unicode_to_ascii 1 other paper
1 the same month
1409.0473 (2014-09)
Neural Machine Translation by Jointly Learning to Align and Translate

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

More are linked than shown here.

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

Abstract

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

For agents

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

get_harvested_code_for_paper("1409.3215")
get_code_for_paper("1409.3215")
have("1409.3215")

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

curl https://syntology.ai/api/ran/1409.3215.json

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

[![Syntology run record](https://syntology.ai/api/ran/1409.3215.svg)](https://syntology.ai/paper/1409.3215)

Connect an agent — have() is free.