SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.09458 · 2018

Invariant Representations without Adversarial Training

arXiv · PDF · Open in the Atlas

Code that ran

3 of 10 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 3 have no contract verdict; 0 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/1805.09458.json · badge: /api/ran/1805.09458.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
dcmoyer/inv-rep community (classifier label)
classifier basis not recorded on the link
3 ran · 7 no recorded run
FunctionStatusWhere it lives
check_args Ran
ran on a synthesized input
dcmoyer/inv-rep/src/adv.py
code served (permissive licence) · get_code("59018abfb0f04c99")
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 Args. 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 os
import tempfile

class Args:
    def __init__(self):
        self.experiment_name = "test_experiment"
        self.latent_and_label_data_path = "/tmp/latent_data.pkl"
        self.eval_output = tempfile.mktemp(suffix=".json")
        self.exp_override = False
        self.dim_z = 32
        self.baseline = False
        self.n_hidden = 64

ARGS = {
    'args': Args()
}
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 Args — a Args output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Args 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
check_args Ran
ran on a synthesized input
dcmoyer/inv-rep/src/run_navib.py
code served (permissive licence) · get_code("f01f20d39b2db43c")
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 os
import tempfile
from argparse import Namespace

# Create a temporary directory for the experiment
temp_dir = tempfile.mkdtemp()
param_save_path = os.path.join(temp_dir, 'experiment_params')

ARGS = {
    'args': Namespace(
        experiment_name='test_experiment',
        param_save_path=param_save_path,
        exp_override=False,
        data_path='/tmp/test_data',
        dim_z=8,
        n_hidden_xz=64,
        n_hidden_zy=64,
        learn_rate=0.001,
        num_epochs=10,
        batch_size=32
    )
}
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
log_loss Ran
ran on a synthesized input
dcmoyer/inv-rep/src/error_utils.py
code served (permissive licence) · get_code("3fec486caf59026e")
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 (6,) 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

# log_loss takes two parameters: c and c_hat
# Both are used with numpy operations (np.clip, np.log, etc.)
# They should be numpy arrays or array-like objects
# c is used as binary labels (0 or 1)
# c_hat is used as predicted probabilities (should be between 0 and 1)

# Create small numpy arrays for testing
np.random.seed(0)

# Binary labels (0 or 1)
c = np.array([0, 1, 1, 0, 1, 1])

# Predicted probabilities (values between 0 and 1)
c_hat = np.array([0.1, 0.9, 0.8, 0.2, 0.7, 0.95])

ARGS = {
    "c": c,
    "c_hat": c_hat
}
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 (6,) — shape (6,) 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
all_pairs_gaussian_kl Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/kl_tools.py
code served (permissive licence) · get_code("f45a869d12b5eed2")
How it ran

no invocation recorded.

feed_forward_discriminator_logit Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/ffd.py
code served (permissive licence) · get_code("be19c83df71a65aa")
How it ran

no invocation recorded.

kl_conditional_and_marg Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/kl_tools.py
code served (permissive licence) · get_code("ff789371daf7a231")
How it ran

no invocation recorded.

maybe_download_adult Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/uci_data.py
code served (permissive licence) · get_code("3d9d8f91ab38b9e0")
How it ran

no invocation recorded.

maybe_download_german Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/uci_data.py
code served (permissive licence) · get_code("d0491147dc7c71a8")
How it ran

no invocation recorded.

zero_one_abs Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/error_utils.py
code served (permissive licence) · get_code("54f5546aa78a4241")
How it ran

no invocation recorded.

zero_one_thold Not yet run
unverified (harvested, no recorded run)
dcmoyer/inv-rep/src/error_utils.py
code served (permissive licence) · get_code("3d9dcc2e0abd24a0")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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.

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

Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance to arbitrary nuisance factors yet remain useful for other tasks is challenging. Existing approaches cast the trade-off between task performance and invariance in an adversarial way, using an iterative minimax optimization. We show that adversarial training is unnecessary and sometimes counter-productive; we instead cast invariant representation learning as a single information-theoretic objective that can be directly optimized. We demonstrate that this approach matches or exceeds performance of state-of-the-art adversarial approaches for learning fair representations and for generative modeling with controllable transformations.

For agents

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

get_harvested_code_for_paper("1805.09458")
get_code_for_paper("1805.09458")
have("1805.09458")

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

curl https://syntology.ai/api/ran/1805.09458.json

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

[![Syntology run record](https://syntology.ai/api/ran/1805.09458.svg)](https://syntology.ai/paper/1805.09458)

Connect an agent — have() is free.