SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.06810 · 2021

Understanding self-supervised Learning Dynamics without Contrastive Pairs

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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, 3 violated it and 1 has no contract verdict; 0 failures of our instrument; 4 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/2102.06810.json · badge: /api/ran/2102.06810.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
facebookresearch/luckmatters canonical (classifier label)
classifier basis: classifier_2025
2 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
lucidrains/byol-pytorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Accumulator Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/luckmatters/ssl/real-dataset/byol_trainer.py
pointer only (licence: NOASSERTION) · get_code("551a048173369c49")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

default Ran
ran, violated the contract we drafted
lucidrains/byol-pytorch/byol_pytorch/byol_pytorch.py
code served (permissive licence) · get_code("1c0f269ae9673b08")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

# The function `default` takes two parameters:
# - val: any value that might be None
# - def_val: a default value to return if val is None

# Test case 1: val is None, should return def_val
val_none = None
def_val_1 = 42

# Test case 2: val is not None, should return val
val_not_none = "some_value"
def_val_2 = "default_value"

# We'll use the first test case for ARGS
ARGS = {
    'val': val_none,
    'def_val': def_val_1
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
divisible_by Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/soft-moe-pytorch
pointer only · get_code("f912c209e9c899ca")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

exists Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from lucidrains/gradnorm-pytorch
pointer only · get_code("b7c3487f192e31b7")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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_orthonormal_matrix Ran
ran, honoured the contract we drafted
facebookresearch/luckmatters/ssl/real-dataset/byol_trainer.py
pointer only (licence: NOASSERTION) · get_code("418a6e830639c7e1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

BYOLTrainer Not yet run
unverified (harvested, no recorded run)
facebookresearch/luckmatters/ssl/real-dataset/byol_trainer.py
pointer only (licence: NOASSERTION) · get_code("a25c0f4514f8e550")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

_create_model_training_folder Not yet run
unverified (harvested, no recorded run)
facebookresearch/luckmatters/ssl/real-dataset/byol_trainer.py
pointer only (licence: NOASSERTION) · get_code("5b53f8127f8ee5f7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

check_valid Not yet run
unverified (harvested, no recorded run)
facebookresearch/luckmatters/ssl/real-dataset/byol_trainer.py
pointer only (licence: NOASSERTION) · get_code("34e6134013a7af6e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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.

weights_init Not yet run
unverified (harvested, no recorded run)
facebookresearch/luckmatters/ssl/real-dataset/byol_trainer.py
pointer only (licence: NOASSERTION) · get_code("f9ada57830668708")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/luckmatters (NOASSERTION). 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
exists 27 other papers
3 dated earlier, 24 later · 3 only as an assembly brick
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
2006.15055 (2020-06)
Object-Centric Learning with Slot Attention
2010.10241 (2020-10)
BYOL works even without batch statistics
and 24 more not named here
divisible_by 16 other papers
2 dated earlier, 14 later · 2 only as an assembly brick
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2010.10241 (2020-10)
BYOL works even without batch statistics
2304.09116 (2023-04)
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
and 13 more not named here
default 11 other papers
3 dated earlier, 8 later
2006.07733 (2020-06)
Bootstrap your own latent: A new approach to self-supervised Learning
2010.10241 (2020-10)
BYOL works even without batch statistics
2011.10043 (2020-11)
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
and 8 more not named here

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

While contrastive approaches of self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs) and maximizing views from different data points (negative pairs), recent \emph{non-contrastive} SSL (e.g., BYOL and SimSiam) show remarkable performance {\it without} negative pairs, with an extra learnable predictor and a stop-gradient operation. A fundamental question arises: why do these methods not collapse into trivial representations? We answer this question via a simple theoretical study and propose a novel approach, DirectPred, that \emph{directly} sets the linear predictor based on the statistics of its inputs, without gradient training. On ImageNet, it performs comparably with more complex two-layer non-linear predictors that employ BatchNorm and outperforms a linear predictor by $2.5\%$ in 300-epoch training (and $5\%$ in 60-epoch). DirectPred is motivated by our theoretical study of the nonlinear learning dynamics of non-contrastive SSL in simple linear networks. Our study yields conceptual insights into how non-contrastive SSL methods learn, how they avoid representational collapse, and how multiple factors, like predictor networks, stop-gradients, exponential moving averages, and weight decay all come into play. Our simple theory recapitulates the results of real-world ablation studies in both STL-10 and ImageNet. Code is released https://github.com/facebookresearch/luckmatters/tree/master/ssl.

For agents

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

get_harvested_code_for_paper("2102.06810")
get_code_for_paper("2102.06810")
have("2102.06810")

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

curl https://syntology.ai/api/ran/2102.06810.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.06810.svg)](https://syntology.ai/paper/2102.06810)

Connect an agent — have() is free.