SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.12059 · 2019

Wasserstein Fair Classification

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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; 2 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/1907.12059.json · badge: /api/ran/1907.12059.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
deepmind/wasserstein_fairness canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
regression_loss_gradient Ran
ran on a synthesized input
deepmind/wasserstein_fairness/wasserstein_fairness/basic_costs.py
code served (permissive licence) · get_code("cf9a91119901cf28")
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

ARGS = {
    "x": np.array([
        [1.0, 2.0, 3.0],
        [4.0, 5.0, 6.0]
    ]),
    "y": np.array([0.0, 1.0]),
    "theta": np.array([0.1, 0.2, 0.3, 0.4])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
sinkhorn Ran
ran on a synthesized input
deepmind/wasserstein_fairness/wasserstein_fairness/optimal_transport.py
code served (permissive licence) · get_code("b2dcbd9e94bf9ac8")
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. 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 numpy as np

# Construct valid arguments for the sinkhorn function
N = 4

# cost: NxN strictly positive matrix
cost = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [2.0, 1.0, 4.0, 3.0],
    [3.0, 4.0, 1.0, 2.0],
    [4.0, 3.0, 2.0, 1.0]
], dtype=np.float64)

# lambda_: regulariser (positive scalar)
lambda_ = 0.5

# distn_a: input distribution a (vector of length N, sums to 1)
distn_a = np.array([0.25, 0.25, 0.25, 0.25], dtype=np.float64)

# distn_b: input distribution b (vector of length N, sums to 1)
distn_b = np.array([0.1, 0.2, 0.3, 0.4], dtype=np.float64)

# tolerance: stopping tolerance
tolerance = 1e-07

ARGS = {
    "cost": cost,
    "lambda_": lambda_,
    "distn_a": distn_a,
    "distn_b": distn_b,
    "tolerance": tolerance
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
wasserstein_coupling_on_the_real_line Ran
ran on a synthesized input
deepmind/wasserstein_fairness/wasserstein_fairness/optimal_transport.py
code served (permissive licence) · get_code("b50d587c566d6ce9")
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 csr_matrix. 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 numpy as np
import scipy.sparse as sparse

# Set random seed for reproducibility
np.random.seed(0)

# Create two small vectors of real numbers
x1 = np.array([1.5, 3.2, 2.8, 4.1])
x2 = np.array([2.1, 3.5, 1.9])

ARGS = {
    "x1": x1,
    "x2": x2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type csr_matrix — a csr_matrix output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a csr_matrix 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
regression_loss Not yet run
unverified (harvested, no recorded run)
deepmind/wasserstein_fairness/wasserstein_fairness/basic_costs.py
code served (permissive licence) · get_code("993e7548a1badb59")
How it ran

no invocation recorded.

wasserstein_two_loss_gradient Not yet run
unverified (harvested, no recorded run)
deepmind/wasserstein_fairness/wasserstein_fairness/basic_costs.py
code served (permissive licence) · get_code("1d316e869807fdff")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

We propose an approach to fair classification that enforces independence between the classifier outputs and sensitive information by minimizing Wasserstein-1 distances. The approach has desirable theoretical properties and is robust to specific choices of the threshold used to obtain class predictions from model outputs. We introduce different methods that enable hiding sensitive information at test time or have a simple and fast implementation. We show empirical performance against different fairness baselines on several benchmark fairness datasets.

For agents

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

get_harvested_code_for_paper("1907.12059")
get_code_for_paper("1907.12059")
have("1907.12059")

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

curl https://syntology.ai/api/ran/1907.12059.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.12059.svg)](https://syntology.ai/paper/1907.12059)

Connect an agent — have() is free.