SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.03325 · ICML · 2024

Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations

Sang Xie, Helen Qu, M Jee, G Jernigan, Le Guillou, K.-T Lim, Muñoz Arancibia

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 0 have no contract verdict; 5 failures of our instrument; 1 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/2402.03325.json · badge: /api/ran/2402.03325.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
helenqu/connect-later canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
convert_to_pandas_period Ran
ran; our contract draft was wrong, not the code
helenqu/connect-later/connect_later/dataset_preprocess_raw.py
pointer only (licence: NONE) · get_code("3f40eee76eaed297")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, helenqu/connect-later 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.

normalize_all Ran
ran; our contract draft was wrong, not the code
helenqu/connect-later/connect_later/dataset_preprocess_raw.py
pointer only (licence: NONE) · get_code("59c3d5e2ae6e0a8d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, helenqu/connect-later 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.

normalize_by_channel Ran
ran; our contract draft was wrong, not the code
helenqu/connect-later/connect_later/dataset_preprocess_raw.py
pointer only (licence: NONE) · get_code("5f393d809299394f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, helenqu/connect-later 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.

prepare_model_input Ran
ran; our contract draft was wrong, not the code
helenqu/connect-later/connect_later/pretrain.py
pointer only (licence: NONE) · get_code("447e52d440681920")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, helenqu/connect-later 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.

setup_model_config Ran
ran; our contract draft was wrong, not the code
helenqu/connect-later/connect_later/pretrain.py
pointer only (licence: NONE) · get_code("d9beb42690d42263")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, helenqu/connect-later 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.

get_dataset Not yet run
unverified (harvested, no recorded run)
helenqu/connect-later/connect_later/pretrain.py
pointer only (licence: NONE) · get_code("8339f116bb89252e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, helenqu/connect-later 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
normalize_all 1 other paper
1 later
2412.02527 (2024-12)
The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data The Multimodal Universe Collaboration
normalize_by_channel 1 other paper
1 later
2412.02527 (2024-12)
The Multimodal Universe: Enabling Large-Scale Machine Learning with 100 TB of Astronomical Scientific Data The Multimodal Universe Collaboration

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

Models trained on a labeled source domain often generalize poorly when deployed on an outof-distribution (OOD) target domain. In the domain adaptation setting where unlabeled target data is available, self-supervised pretraining (e.g., contrastive learning or masked autoencoding) is a promising method to mitigate this performance drop. Pretraining depends on generic data augmentations (e.g., cropping or masking) to learn representations that generalize across domains, which may not work for all distribution shifts. In this paper, we show on real-world tasks that standard fine-tuning after pretraining does not consistently improve OOD error over simply training from scratch on labeled source data. To better leverage pretraining for distribution shifts, we propose the Connect Later framework, which fine-tunes the model with targeted augmentations designed with knowledge of the shift. Intuitively, pretraining learns good representations within the source and target domains, while fine-tuning with targeted augmentations improves generalization across domains. Connect Later achieves state-of-the-art OOD accuracy while maintaining comparable or better in-distribution accuracy on 4 real-world tasks in wildlife identification (IWILDCAM-WILDS), tumor detection (CAMELYON17-WILDS), and astronomy (ASTROCLASSIFICATION, REDSHIFTS).

For agents

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

get_harvested_code_for_paper("2402.03325")
get_code_for_paper("2402.03325")
have("2402.03325")

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

curl https://syntology.ai/api/ran/2402.03325.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.03325.svg)](https://syntology.ai/paper/2402.03325)

Connect an agent — have() is free.