SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10312 · NeurIPS · 2020

Learning Certified Individually Fair Representations

Anian Ruoss, Mislav Balunović, Marc Fischer, Martin Vechev

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2002.10312.json · badge: /api/ran/2002.10312.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
eth-sri/lcifr canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Autoencoder Ran
ran on a synthesized input · constructed an object; no result was computed
eth-sri/lcifr/code/models/autoencoder.py
code served (permissive licence) · get_code("d7072fdb712894bb")
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, Autoencoder: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# The Autoencoder expects:
# - encoder_layers: a list of integers representing layer dimensions
# - decoder_layers: a list of integers representing layer dimensions
#
# The encoder_layers list is used as:
#   zip(encoder_layers[:-2], encoder_layers[1:-1])  # for ReLU layers
#   encoder_layers[-2], encoder_layers[-1]  # for final linear layer
#
# Similarly for decoder_layers
#
# So we need at least 3 elements in each list.
# Let's use distinct dimensions: 4 -> 3 -> 2 for encoder, 2 -> 3 -> 4 for decoder

encoder_layers = [4, 3, 2]  # input_dim=4, hidden=3, latent=2
decoder_layers = [2, 3, 4]  # latent=2, hidden=3, output_dim=4

ARGS = {
    'encoder_layers': encoder_layers,
    'decoder_layers': decoder_layers,
}
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 Autoencoder — 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 Autoencoder 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Fair representation learning provides an effective way of enforcing fairness constraints without compromising utility for downstream users. A desirable family of such fairness constraints, each requiring similar treatment for similar individuals, is known as individual fairness. In this work, we introduce the first method that enables data consumers to obtain certificates of individual fairness for existing and new data points. The key idea is to map similar individuals to close latent representations and leverage this latent proximity to certify individual fairness. That is, our method enables the data producer to learn and certify a representation where for a data point all similar individuals are at ℓ ∞ -distance at most ǫ, thus allowing data consumers to certify individual fairness by proving ǫ-robustness of their classifier. Our experimental evaluation on five real-world datasets and several fairness constraints demonstrates the expressivity and scalability of our approach. Key challenge A central challenge then is to enforce individual fairness in the setting described above. That is, to both learn an individually fair representation and to certify that individual fairness 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada.

For agents

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

get_harvested_code_for_paper("2002.10312")
get_code_for_paper("2002.10312")
have("2002.10312")

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

curl https://syntology.ai/api/ran/2002.10312.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.10312.svg)](https://syntology.ai/paper/2002.10312)

Connect an agent — have() is free.