SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1608.06019 · 2016

Domain Separation Networks

arXiv · PDF · Open in the Atlas

Code that ran

10 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 6 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/1608.06019.json · badge: /api/ran/1608.06019.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
WinChua/CDRTR community (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
better-chao/DSN reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
AmirHussein96/Simplified-DSN reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
buildVoca Ran
ran on a synthesized input
WinChua/CDRTR/CDRTR/preprocess/utils.py
code served (permissive licence) · get_code("8fba778a6f75c85d")
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 JSON file with sample Amazon review data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.json')
temp_filename = temp_file.name

# Write sample JSON data in Amazon review format
sample_reviews = [
    {
        "asin": "B00002243X",
        "helpful": [4, 4],
        "overall": 5.0,
        "reviewText": "This product is amazing! I love it so much.",
        "reviewTime": "08 17, 2011",
        "reviewerID": "A3F73SC1LY51OO",
        "reviewerName": "Alan Montgomery",
        "summary": "Great product",
        "unixReviewTime": 1313539200
    },
    {
        "asin": "B00003456Y",
        "helpful": [2, 3],
        "overall": 3.0,
        "reviewText": "Not bad, but could be better. It's okay though.",
        "reviewTime": "09 20, 2012",
        "reviewerID": "B4G84TD2MZ62PP",
        "reviewerName": "Bob Smith",
        "summary": "Decent product",
        "unixReviewTime": 1348108800
    },
    {
        "asin": "B00002243X",
        "helpful": [1, 2],
        "overall": 2.0,
        "reviewText": "Disappointing! Doesn't work as advertised.",
        "reviewTime": "10 15, 2013",
        "reviewerID": "C5H95UE3NA73QQ",
        "reviewerName": "Carol Jones",
        "summary": "Not recommended",
        "unixReviewTime": 1381776000
    }
]

for review in sample_reviews:
    temp_file.write(json.dumps(review) + '\n')

temp_file.close()

ARGS = {
    "filename": temp_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 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
calc_losses Ran
ran; our contract draft was wrong, not the code
better-chao/DSN/model.py
pointer only (licence: NONE) · get_code("6fd1a214765e72ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, better-chao/DSN 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.

clean_str Ran
ran; our contract draft was wrong, not the code
WinChua/CDRTR/CDRTR/preprocess/utils.py
code served (permissive licence) · get_code("3a61a354e5a70023")
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

def clean_str(string):
    """
    Tokenization/string cleaning for all datasets except for SST.
    Original taken from
    https://github.com/yoonkim/CNN_sentence/blob/master/process_data.py
    """
    string = re.sub("[^A-Za-z0-9(),!?\\'\\`]", ' ', string)
    string = re.sub("\\'s", " 's", string)
    string = re.sub("\\'ve", " 've", string)
    string = re.sub("n\\'t", " n't", string)
    string = re.sub("\\'re", " 're", string)
    string = re.sub("\\'d", " 'd", string)
    string = re.sub("\\'ll", " 'll", string)
    string = re.sub(',', ' , ', string)
    string = re.sub('!', ' ! ', string)
    string = re.sub('\\(', ' \\( ', string)
    string = re.sub('\\)', ' \\) ', string)
    string = re.sub('\\?', ' \\? ', string)
    string = re.sub('\\s{2,}', ' ', string)
    return string.strip().lower()

ARGS = {
    'string': "Hello, world! This is a test. It's amazing (don't you think?)"
}
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
compose_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AmirHussein96/Simplified-DSN/create_mnistm.py
pointer only (licence: NONE) · get_code("ff78cef5d3488545")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AmirHussein96/Simplified-DSN 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.

create_mnistm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
better-chao/DSN/create_mnistm.py
pointer only (licence: NONE) · get_code("7cb4d00956da097a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, better-chao/DSN 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.

difference_loss Ran
ran; our contract draft was wrong, not the code
better-chao/DSN/model.py
pointer only (licence: NONE) · get_code("77ccceb98cdee6c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, better-chao/DSN 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.

logitRegression Ran
ran on a synthesized input
WinChua/CDRTR/CDRTR/core/LinearModel/LR.py
code served (permissive licence) · get_code("5a45998cae0b9c38")
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 EagerTensor, ndim 2, dtype family float, shape (2, 1) 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 tensorflow as tf
import numpy as np

# Create a small input tensor for logistic regression
# Shape: (batch_size=2, input_dim=4)
input_data = tf.constant([[1.0, 2.0, 3.0, 4.0],
                          [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

ARGS = {
    "ipt": input_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (2, 1) — shape (2, 1) 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
mnist_to_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AmirHussein96/Simplified-DSN/create_mnistm.py
pointer only (licence: NONE) · get_code("fe1dbd8806085fe2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AmirHussein96/Simplified-DSN 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.

padding Ran
ran on a synthesized input
WinChua/CDRTR/CDRTR/utils.py
code served (permissive licence) · get_code("805af20b689e601f")
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 int; 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

torch.manual_seed(0)

# Build valid arguments for the padding function
sentc = [1, 2, 3, 4, 5]  # A list of integers
size = 10  # Target size for padding
pad = 0  # Padding value (same type as list elements)

ARGS = {
    'sentc': sentc,
    'size': size,
    'pad': pad
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — 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
recordTime Ran
ran on a synthesized input
WinChua/CDRTR/CDRTR/utils.py
code served (permissive licence) · get_code("69cebf606530314b")
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 logging
import functools
import time

# Configure logging to see debug output
logging.basicConfig(level=logging.DEBUG)

# Define a simple function to decorate
def sample_function(x, y=10):
    """A simple function that will be decorated with recordTime"""
    time.sleep(0.01)  # Simulate some work
    return x + y

# Apply the decorator
def recordTime(func):
    logger = logging.getLogger(__name__)

    @functools.wraps(func)
    def innerWrapper(*args, **kwargs):
        logger.debug('calling  func: %s, args: %s, kwargs: %s', func.__name__, ' '.join(str(a) for a in args), ' '.join(('{k}={v}'.format(k=k, v=v) for k, v in kwargs.items())))
        start = time.time()
        result = func(*args, **kwargs)
        end = time.time()
        logger.debug('call end func: %s, it cost %f s', func.__name__, end - start)
        return result
    return innerWrapper

decorated_func = recordTime(sample_function)

ARGS = {
    'func': sample_function
}
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 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
create_mnistm Not yet run
unverified (harvested, no recorded run)
AmirHussein96/Simplified-DSN/create_mnistm.py
pointer only (licence: NONE) · get_code("7c7eaa1486a49223")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, AmirHussein96/Simplified-DSN 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.

generateColdUser Not yet run
unverified (harvested, no recorded run)
WinChua/CDRTR/CDRTR/preprocess/cold.py
code served (permissive licence) · get_code("9304c4038bf8917c")
How it ran

no invocation recorded.

mergeUserItem Not yet run
unverified (harvested, no recorded run)
WinChua/CDRTR/CDRTR/preprocess/sentiOutputMergeUserItem.py
code served (permissive licence) · get_code("a6024e8116aa1f9a")
How it ran

no invocation recorded.

pkload Not yet run
unverified (harvested, no recorded run)
WinChua/CDRTR/CDRTR/utils.py
code served (permissive licence) · get_code("396cd1afb3640ed8")
How it ran

no invocation recorded.

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
clean_str 9 other papers
2 dated earlier, 7 later
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1510.03820 (2015-10)
A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classification
1703.03130 (2017-03)
A Structured Self-attentive Sentence Embedding
and 6 more not named here

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

The cost of large scale data collection and annotation often makes the application of machine learning algorithms to new tasks or datasets prohibitively expensive. One approach circumventing this cost is training models on synthetic data where annotations are provided automatically. Despite their appeal, such models often fail to generalize from synthetic to real images, necessitating domain adaptation algorithms to manipulate these models before they can be successfully applied. Existing approaches focus either on mapping representations from one domain to the other, or on learning to extract features that are invariant to the domain from which they were extracted. However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain. We suggest that explicitly modeling what is unique to each domain can improve a model's ability to extract domain-invariant features. Inspired by work on private-shared component analysis, we explicitly learn to extract image representations that are partitioned into two subspaces: one component which is private to each domain and one which is shared across domains. Our model is trained not only to perform the task we care about in the source domain, but also to use the partitioned representation to reconstruct the images from both domains. Our novel architecture results in a model that outperforms the state-of-the-art on a range of unsupervised domain adaptation scenarios and additionally produces visualizations of the private and shared representations enabling interpretation of the domain adaptation process.

For agents

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

get_harvested_code_for_paper("1608.06019")
get_code_for_paper("1608.06019")
have("1608.06019")

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

curl https://syntology.ai/api/ran/1608.06019.json

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

[![Syntology run record](https://syntology.ai/api/ran/1608.06019.svg)](https://syntology.ai/paper/1608.06019)

Connect an agent — have() is free.