SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2208.02810 · NeurIPS · 2022

Analyzing Data-Centric Properties for Graph Contrastive Learning

Danai Koutra, Mark Heimann, Ekdeep Singh Lubana, Jayaraman Thiagarajan, Puja Trivedi

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 3 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/2208.02810.json · badge: /api/ran/2208.02810.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
pujacomputes/datapropsgraphssl canonical (classifier label)
classifier basis: classifier_2025
5 ran · 3 no recorded run
FunctionStatusWhere it lives
attach_motif Ran
ran; our contract draft was wrong, not the code
pujacomputes/datapropsgraphssl/datagen/create_dataset.py
pointer only (licence: NONE) · get_code("5021b9765af13b73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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.

compute_sep Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pujacomputes/datapropsgraphssl/examples/compute_invariance_sep.py
pointer only (licence: NONE) · get_code("5bdaecd839af62f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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_host_cands Ran
ran; our contract draft was wrong, not the code
pujacomputes/datapropsgraphssl/datagen/create_dataset.py
pointer only (licence: NONE) · get_code("89a4d235cfbcb6be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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.

pairwise_cos Ran
ran, honoured the contract we drafted
pujacomputes/datapropsgraphssl/examples/compute_invariance_sep.py
pointer only (licence: NONE) · get_code("938830ef2b180441")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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.

random_ba Ran
ran, honoured the contract we drafted
pujacomputes/datapropsgraphssl/datagen/create_dataset.py
pointer only (licence: NONE) · get_code("c5c43465c498efee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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.

add_to_list Not yet run
unverified (harvested, no recorded run)
pujacomputes/datapropsgraphssl/datagen/create_dataset.py
pointer only (licence: NONE) · get_code("6fe9689ed3b012d4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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.

make_class_dataset Not yet run
unverified (harvested, no recorded run)
pujacomputes/datapropsgraphssl/datagen/create_dataset.py
pointer only (licence: NONE) · get_code("b79b228917c3479a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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.

random_tree Not yet run
unverified (harvested, no recorded run)
pujacomputes/datapropsgraphssl/datagen/create_dataset.py
pointer only (licence: NONE) · get_code("32861c24d95bf2ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pujacomputes/datapropsgraphssl 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to taskirrelevant semantics, separability of classes in some latent space, and recoverability of labels from augmented samples. However, given their discrete, non-Euclidean nature, graph datasets and graph SSL methods are unlikely to satisfy these properties. This raises the question: how do graph SSL methods, such as contrastive learning (CL), work well? To systematically probe this question, we perform a generalization analysis for CL when using generic graph augmentations (GGAs), with a focus on data-centric properties. Our analysis yields formal insights into the limitations of GGAs and the necessity of task-relevant augmentations. As we empirically show, GGAs do not induce task-relevant invariances on common benchmark datasets, leading to only marginal gains over naive, untrained baselines. Our theory motivates a synthetic data generation process that enables control over task-relevant information and boasts pre-defined optimal augmentations. This flexible benchmark helps us identify yet unrecognized limitations in advanced augmentation techniques (e.g., automated methods). Overall, our work rigorously contextualizes, both empirically and theoretically, the effects of data-centric properties on augmentation strategies and learning paradigms for graph SSL.

For agents

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

get_harvested_code_for_paper("2208.02810")
get_code_for_paper("2208.02810")
have("2208.02810")

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

curl https://syntology.ai/api/ran/2208.02810.json

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

[![Syntology run record](https://syntology.ai/api/ran/2208.02810.svg)](https://syntology.ai/paper/2208.02810)

Connect an agent — have() is free.