SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.03912 · ICLR · 2020

A Probabilistic Formulation of Unsupervised Text Style Transfer

Junxian He, Xinyi Wang, Graham Neubig, Taylor Berg-Kirkpatrick

arXiv · PDF · Open in the Atlas

Code that ran

18 of 25 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (13 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 7 failures of our instrument; 7 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/2002.03912.json · badge: /api/ran/2002.03912.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
thu-coai/NAST community
Papers with Code archive
9 ran · 4 no recorded run
cindyxinyiwang/TextStyleTransfer community
Papers with Code archive
6 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Beam Ran
ran on a synthesized input · constructed an object; no result was computed
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("2a0fe14622f8497d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

DecoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("f62647ab841d8eac")
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, DecoderLayer: 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
import math

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
seq_len = 3
d_model = 4
num_heads = 2

# Create decoder layer
decoder_layer = nn.Module()

# Arguments for DecoderLayer.__init__
d_model_arg = 4
h_arg = 2
dropout_arg = 0.1

# Create mask tensors (batch, num_heads, seq_len, seq_len)
# False means attend, True means mask out
src_mask = torch.zeros(batch_size, num_heads, seq_len, seq_len, dtype=torch.bool)
tgt_mask = torch.zeros(batch_size, num_heads, seq_len, seq_len, dtype=torch.bool)

# Create input tensors
x = torch.randn(batch_size, seq_len, d_model)
memory = torch.randn(batch_size, seq_len, d_model)

ARGS = {
    'd_model': d_model_arg,
    'h': h_arg,
    'dropout': dropout_arg
}
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 DecoderLayer — 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 DecoderLayer 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
Embedding Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
this paper's copy was not recorded; identical code first harvested from marvinchung/hw5-textstyletransfer
pointer only; the stored copy get_code serves, from marvinchung/hw5-textstyletransfer, is pointer only (licence: NONE) · get_code("cc6417e762730325")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

EmbeddingLayer Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("fd281e0df749b749")
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, EmbeddingLayer: 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
from torch import nn

torch.manual_seed(0)

# Create a stand-in data manager class that has frequent_vocab_size attribute
class DataManager:
    def __init__(self, vocab_size):
        self.frequent_vocab_size = vocab_size

# Create instances
dm = DataManager(vocab_size=10)
d_model = 4
max_length = 8
pad_idx = 0
learned_pos_embed = True

# Optional: create a small wordvec tensor (pretrained embeddings)
# Shape: (vocab_size, embedding_dim)
wordvec = None

ARGS = {
    "dm": dm,
    "d_model": d_model,
    "max_length": max_length,
    "pad_idx": pad_idx,
    "learned_pos_embed": learned_pos_embed,
    "wordvec": wordvec
}
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 EmbeddingLayer — 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 EmbeddingLayer 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
Encoder Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("ac16887aad3c401d")
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, Encoder: 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
import math

torch.manual_seed(0)

# Set up parameters for Encoder
num_layers = 2
d_model = 4
vocab_size = 10
h = 2  # number of heads, must divide d_model
dropout = 0.1

# Create input tensor: (batch_size, seq_len, d_model)
batch_size = 2
seq_len = 3
x = torch.randn(batch_size, seq_len, d_model)

# Create attention mask: (batch_size, 1, seq_len, seq_len) or compatible shape
# mask should be True where we want to mask (set to -inf in scaled_attention)
# For this example, we'll create a simple causal mask (no masking)
mask = torch.zeros(batch_size, 1, seq_len, seq_len, dtype=torch.bool)

ARGS = {
    "num_layers": num_layers,
    "d_model": d_model,
    "vocab_size": vocab_size,
    "h": h,
    "dropout": dropout,
}
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 Encoder — 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 Encoder 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
EncoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("fe38343a20d6cec6")
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, EncoderLayer: 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)

# EncoderLayer parameters:
# - d_model: embedding dimension
# - h: number of attention heads
# - dropout: dropout rate

ARGS = {
    "d_model": 8,
    "h": 2,
    "dropout": 0.1,
}
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 EncoderLayer — 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 EncoderLayer 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
Generator Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("31ab6deda5fe5457")
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, Generator: 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)

ARGS = {
    'd_model': 8,
    'vocab_size': 16
}
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 Generator — 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 Generator 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
Hyp Ran
ran on a synthesized input · constructed an object; no result was computed
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("9f75aa33a1ccdc32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

LayerNorm Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("244df97d092c7e06")
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, LayerNorm: 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)

ARGS = {
    "embedding_dim": 64,
    "eps": 1e-06
}
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 LayerNorm — 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 LayerNorm 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
Linear Ran
ran; our contract draft was wrong, not the code · constructed an object; no result was computed
this paper's copy was not recorded; identical code first harvested from marvinchung/hw5-textstyletransfer
pointer only; the stored copy get_code serves, from marvinchung/hw5-textstyletransfer, is pointer only (licence: NONE) · get_code("01f0f6d4a6e475b1")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

MultiHeadAttention Ran
ran on a synthesized input
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("b9a5bb409e08cbc8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, 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
from torch import nn

INIT_ARGS = {
    'd_model': 4,
    'h': 2,
    'dropout': 0.1
}

# Construct input tensors for forward pass
batch_size = 2
seq_len = 3
d_model = INIT_ARGS['d_model']

query = torch.randn(batch_size, seq_len, d_model)
key = torch.randn(batch_size, seq_len, d_model)
value = torch.randn(batch_size, seq_len, d_model)
mask = torch.zeros(batch_size, 1, seq_len, seq_len).bool()  # No masking

ARGS = {
    'query': query,
    'key': key,
    'value': value,
    'mask': mask
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
PolyNorm Ran
ran on a synthesized input · constructed an object; no result was computed
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("e2b9062d0b945f4b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

PositionwiseFeedForward Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("94350806140c9d40")
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, PositionwiseFeedForward: 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)

ARGS = {
    "d_model": 8,
    "dropout": 0.1,
}
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 PositionwiseFeedForward — 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 PositionwiseFeedForward 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
SublayerConnection Ran
ran on a synthesized input · constructed an object; no result was computed
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("3e2638d464cbc25c")
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, SublayerConnection: 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)

# Create a simple sublayer module that takes layer-normed input and processes it
class SimpleSublayer(nn.Module):
    def __init__(self, d_model):
        super(SimpleSublayer, self).__init__()
        self.linear = nn.Linear(d_model, d_model)
    
    def forward(self, x):
        # x shape: (batch, seq_len, d_model)
        return self.linear(x)

# Build arguments
d_model = 4
dropout = 0.1
sublayer = SimpleSublayer(d_model)

ARGS = {
    'd_model': d_model,
    'dropout': dropout
}
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 SublayerConnection — 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 SublayerConnection 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
advcance_ens_beam Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("7a943e0929e23b36")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

scaled_attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from marvinchung/hw5-textstyletransfer
pointer only; the stored copy get_code serves, from marvinchung/hw5-textstyletransfer, is pointer only (licence: NONE) · get_code("97bd0c0f69d68e77")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

select_active_enc_info Ran
ran; our contract draft was wrong, not the code
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("ca8292bfcf4d9b5a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

select_active_enc_mask Ran
ran; our contract draft was wrong, not the code
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("a97450c4460623c1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

Decoder Not yet run
unverified (harvested, no recorded run)
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("dbea3ea139953d0c")
How it ran

no invocation recorded.

Decoder Not yet run
unverified (harvested, no recorded run)
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("7a121f5925381565")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

Encoder Not yet run
unverified (harvested, no recorded run)
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("4e9d07e2d5cbf009")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

HiddenDecoder Not yet run
unverified (harvested, no recorded run)
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("159a44511500802f")
How it ran

no invocation recorded.

LengthPredictor Not yet run
unverified (harvested, no recorded run)
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("6d9d8f5da460708b")
How it ran

no invocation recorded.

StyleTransformer Not yet run
unverified (harvested, no recorded run)
thu-coai/NAST/styletransformer/transformer.py
code served (permissive licence) · get_code("e73587b60482cbcc")
How it ran

no invocation recorded.

Transformer Not yet run
unverified (harvested, no recorded run)
cindyxinyiwang/TextStyleTransfer/src/transformer.py
pointer only (licence: NONE) · get_code("30cf69b3b879a328")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cindyxinyiwang/TextStyleTransfer 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.

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 (3 with at least one paper dated earlier, 0 the same month, 12 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
Linear
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later · 1 only as an assembly brick
1905.05621 (2019-05)
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
2203.02135 (2022-03)
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
and 1 more not named here
Embedding
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 1 only as an assembly brick
1905.05621 (2019-05)
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
2203.02135 (2022-03)
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
scaled_attention
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later · 1 only as an assembly brick
1905.05621 (2019-05)
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
2203.02135 (2022-03)
Continual Few-shot Relation Learning via Embedding Space Regularization and Data Augmentation
Decoder
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
DecoderLayer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
Encoder
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
EncoderLayer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
Generator
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
LayerNorm
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
MultiHeadAttention
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
PositionwiseFeedForward
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer
SublayerConnection
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2106.02210 (2021-06)
NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer

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

We present a deep generative model for unsupervised text style transfer that unifies previously proposed non-generative techniques. Our probabilistic approach models non-parallel data from two domains as a partially observed parallel corpus. By hypothesizing a parallel latent sequence that generates each observed sequence, our model learns to transform sequences from one domain to another in a completely unsupervised fashion. In contrast with traditional generative sequence models (e.g. the HMM), our model makes few assumptions about the data it generates: it uses a recurrent language model as a prior and an encoder-decoder as a transduction distribution. While computation of marginal data likelihood is intractable in this model class, we show that amortized variational inference admits a practical surrogate. Further, by drawing connections between our variational objective and other recent unsupervised style transfer and machine translation techniques, we show how our probabilistic view can unify some known non-generative objectives such as backtranslation and adversarial loss. Finally, we demonstrate the effectiveness of our method on a wide range of unsupervised style transfer tasks, including sentiment transfer, formality transfer, word decipherment, author imitation, and related language translation. Across all style transfer tasks, our approach yields substantial gains over state-of-the-art non-generative baselines, including the state-of-the-art unsupervised machine translation techniques that our approach generalizes. Further, we conduct experiments on a standard unsupervised machine translation task and find that our unified approach matches the current state-of-the-art. 1 * Equal Contribution. 1 Code and data are available at https://github.com/cindyxinyiwang/deep-latent-sequence-model. 2 Notably, some tasks we evaluate on do change content to some degree, such as sentiment transfer, but for conciseness we use the term "style transfer" nonetheless.

For agents

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

get_harvested_code_for_paper("2002.03912")
get_code_for_paper("2002.03912")
have("2002.03912")

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

curl https://syntology.ai/api/ran/2002.03912.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.03912.svg)](https://syntology.ai/paper/2002.03912)

Connect an agent — have() is free.