SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.08320 · 2021

Self-Supervised Learning with Kernel Dependence Maximization

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 (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 0 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/2106.08320.json · badge: /api/ran/2106.08320.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
deepmind/ssl_hsic canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_prob Ran
ran on a synthesized input
deepmind/ssl_hsic/ssl_hsic/kernels.py
code served (permissive licence) · get_code("bf31cca50c4f8a4b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (5,) 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 mpmath
import numpy as np

# Construct arguments for compute_prob
n = 3
x_range = np.array([0.5, 1.0, 1.5, 2.0, 2.5])

ARGS = {
    "n": n,
    "x_range": x_range
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
mpmath, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (5,) — shape (5,) 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
get_label_weights Ran
ran on a synthesized input
deepmind/ssl_hsic/ssl_hsic/kernels.py
code served (permissive licence) · get_code("26fe2e60e0128a1d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 jax.numpy as jnp

def get_label_weights(batch: int) -> tuple:
    """Returns the positive and negative weights of the label kernel matrix."""
    w_pos_base = jnp.atleast_2d(1.0)
    w_neg_base = jnp.atleast_2d(0.0)
    w_mean = (w_pos_base + w_neg_base * (batch - 1)) / batch
    w_pos_base -= w_mean
    w_neg_base -= w_mean
    w_mean = (w_pos_base + w_neg_base * (batch - 1)) / batch
    w_pos = w_pos_base - w_mean
    w_neg = w_neg_base - w_mean
    return (w_pos[0, 0], w_neg[0, 0])

ARGS = {
    "batch": 8
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
pairwise_distance_square Ran
ran on a synthesized input
deepmind/ssl_hsic/ssl_hsic/kernels.py
code served (permissive licence) · get_code("4820794f76936b41")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ArrayImpl, ndim 2, dtype family float, shape (2, 3) 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 jax.numpy as jnp

# Create small test tensors for x and y
x = jnp.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
])

y = jnp.array([
    [0.5, 1.5, 2.5, 3.5],
    [4.5, 5.5, 6.5, 7.5],
    [9.0, 10.0, 11.0, 12.0]
])

maximum = 10000000000.0

ARGS = {
    'x': x,
    'y': y,
    'maximum': maximum
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
all_gather Not yet run
unverified (harvested, no recorded run)
deepmind/ssl_hsic/ssl_hsic/helpers.py
code served (permissive licence) · get_code("0688ca3fb68dd609")
How it ran

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

We approach self-supervised learning of image representations from a statistical dependence perspective, proposing Self-Supervised Learning with the Hilbert-Schmidt Independence Criterion (SSL-HSIC). SSL-HSIC maximizes dependence between representations of transformations of an image and the image identity, while minimizing the kernelized variance of those representations. This framework yields a new understanding of InfoNCE, a variational lower bound on the mutual information (MI) between different transformations. While the MI itself is known to have pathologies which can result in learning meaningless representations, its bound is much better behaved: we show that it implicitly approximates SSL-HSIC (with a slightly different regularizer). Our approach also gives us insight into BYOL, a negative-free SSL method, since SSL-HSIC similarly learns local neighborhoods of samples. SSL-HSIC allows us to directly optimize statistical dependence in time linear in the batch size, without restrictive data assumptions or indirect mutual information estimators. Trained with or without a target network, SSL-HSIC matches the current state-of-the-art for standard linear evaluation on ImageNet, semi-supervised learning and transfer to other classification and vision tasks such as semantic segmentation, depth estimation and object recognition. Code is available at https://github.com/deepmind/ssl_hsic .

For agents

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

get_harvested_code_for_paper("2106.08320")
get_code_for_paper("2106.08320")
have("2106.08320")

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

curl https://syntology.ai/api/ran/2106.08320.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.08320.svg)](https://syntology.ai/paper/2106.08320)

Connect an agent — have() is free.