SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10002 · ECCV · 2022

Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain

Volker Fischer, Chaithanya Mummadi, Piyapat Saranrittichai, Claudia Blaiotta, Mauricio Munoz

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2207.10002.json · badge: /api/ran/2207.10002.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
boschresearch/sourcegen marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
boschresearch/sourcegen/sourcegen/models/sourcegen/models.py
pointer only (licence: AGPL-3.0) · get_code("cdbc5f096210f439")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, boschresearch/sourcegen, is not in the permissive set Syntology serves inline. 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.

compute_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
boschresearch/sourcegen/sourcegen/models/sourcegen/models.py
pointer only (licence: AGPL-3.0) · get_code("3a05a13349f6cd51")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, boschresearch/sourcegen, is not in the permissive set Syntology serves inline. 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.

get_factor_pair_association Ran
ran, honoured the contract we drafted
boschresearch/sourcegen/sourcegen/models/sourcegen/models.py
pointer only (licence: AGPL-3.0) · get_code("1ed691aec2c75a36")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, boschresearch/sourcegen, is not in the permissive set Syntology serves inline. 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.

SourceGenModel Not yet run
unverified (harvested, no recorded run)
boschresearch/sourcegen/sourcegen/models/sourcegen/models.py
pointer only (licence: AGPL-3.0) · get_code("f9a8291a9bd2d32c")
How it ran

The body of this sample is withheld: AGPL-3.0, as GitHub detects it on this paper's repository, boschresearch/sourcegen, is not in the permissive set Syntology serves inline. 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Shortcut learning occurs when a deep neural network overly relies on spurious correlations in the training dataset in order to solve downstream tasks. Prior works have shown how this impairs the compositional generalization capability of deep learning models. To address this problem, we propose a novel approach to mitigate shortcut learning in uncontrolled target domains. Our approach extends the training set with an additional dataset (the source domain), which is specifically designed to facilitate learning independent representations of basic visual factors. We benchmark our idea on synthetic target domains where we explicitly control shortcut opportunities as well as real-world target domains. Furthermore, we analyze the effect of different specifications of the source domain and the network architecture on compositional generalization. Our main finding is that leveraging data from a source domain is an effective way to mitigate shortcut learning. By promoting independence across different factors of variation in the learned representations, networks can learn to consider only predictive factors and ignore potential shortcut factors during inference.

For agents

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

get_harvested_code_for_paper("2207.10002")
get_code_for_paper("2207.10002")
have("2207.10002")

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

curl https://syntology.ai/api/ran/2207.10002.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.10002.svg)](https://syntology.ai/paper/2207.10002)

Connect an agent — have() is free.