SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.04933 · NeurIPS · 2022

Energy-Based Contrastive Learning of Visual Representations

Jong Ye, Beomsu Kim

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 7 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/2202.04933.json · badge: /api/ran/2202.04933.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
1202kbs/ebclr canonical (classifier label)
classifier basis: classifier_2025
12 ran · 2 no recorded run
FunctionStatusWhere it lives
Buffer Ran
ran on a synthesized input · constructed an object; no result was computed
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("6ac1e9429f4fe7fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

GaussianBlur Ran
ran on a synthesized input · constructed an object; no result was computed
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("d4ea33d3221533f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

MSGLD Ran
ran on a synthesized input
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("1445124b9a9a3222")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

SimCLR_Loss Ran
ran on a synthesized input
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("7dae9e689051c347")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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_lr_schedule Ran
ran; our contract draft was wrong, not the code
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("9917282e521dbb6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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_optimizer Ran
ran; our contract draft was wrong, not the code
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("04f4732de0a195ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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_t Ran
ran; our contract draft was wrong, not the code
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("971f12d0a863e889")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

load_ckpt Ran
ran, honoured the contract we drafted
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("fdcbd4afb30b8c3f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

logsumexp Ran
ran; our contract draft was wrong, not the code
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("a5d7c8bbd5782ef5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

shuffled_idx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("507b89409e45c9af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

similarity_f Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("5f603a9f2e80d384")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

transform_data Ran
ran; our contract draft was wrong, not the code
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("a93280fc29bbdbef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

EBCLR Not yet run
unverified (harvested, no recorded run)
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("aad3c0e761fa8f19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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.

save_ckpt Not yet run
unverified (harvested, no recorded run)
1202kbs/ebclr/libs/ebclr.py
pointer only (licence: NONE) · get_code("dd7d00639441fd9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, 1202kbs/ebclr 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 14 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

Contrastive learning is a method of learning visual representations by training Deep Neural Networks (DNNs) to increase the similarity between representations of positive pairs (transformations of the same image) and reduce the similarity between representations of negative pairs (transformations of different images). Here we explore Energy-Based Contrastive Learning (EBCLR) that leverages the power of generative learning by combining contrastive learning with Energy-Based Models (EBMs). EBCLR can be theoretically interpreted as learning the joint distribution of positive pairs, and it shows promising results on small and medium-scale datasets such as MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. Specifically, we find EBCLR demonstrates from ×4 up to ×20 acceleration compared to SimCLR and MoCo v2 in terms of training epochs. Furthermore, in contrast to SimCLR, we observe EBCLR achieves nearly the same performance with 254 negative pairs (batch size 128) and 30 negative pairs (batch size 16) per positive pair, demonstrating the robustness of EBCLR to small numbers of negative pairs. Hence, EBCLR provides a novel avenue for improving contrastive learning methods that usually require large datasets with a significant number of negative pairs per iteration to achieve reasonable performance on downstream tasks.

For agents

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

get_harvested_code_for_paper("2202.04933")
get_code_for_paper("2202.04933")
have("2202.04933")

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

curl https://syntology.ai/api/ran/2202.04933.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.04933.svg)](https://syntology.ai/paper/2202.04933)

Connect an agent — have() is free.