SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.14673 · ICLR · 2025

Self-supervised contrastive learning performs non-linear system identification

Steffen Schneider, Tobias Schmidt, Rodrigo González Laiz

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 6 failures of our instrument; 0 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/2410.14673.json · badge: /api/ran/2410.14673.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
dynamical-inference/dcl canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
construct_invertible_mlp Ran
ran; our contract draft was wrong, not the code
dynamical-inference/dcl/dcl/models/mixing_mlp.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from dynamical-inference/ebc, is pointer only (licence: NONE) · get_code("372419c58793bc79")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from dynamical-inference/ebc, and GitHub detected no licence in that repository 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.

dot_similarity Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dynamical-inference/dcl/dcl/criterions/contrastive.py
code served (permissive licence) · get_code("355891358c72d589")
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. The image it ran in was not recorded. If your copy returns the same type 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
from torch import Tensor

torch.manual_seed(0)

# Create small tensors with distinct sizes for clarity
n = 2  # batch size
d = 4  # embedding dimension

# ref: shape (n, d) - reference samples
ref = torch.randn(n, d)

# pos: shape (n, d) - positive samples
pos = torch.randn(n, d)

# neg: shape (n, d) - negative samples
neg = torch.randn(n, d)

ARGS = {
    "ref": ref,
    "pos": pos,
    "neg": neg,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
euclidean_similarity Ran
ran; our contract draft was wrong, not the code
dynamical-inference/dcl/dcl/criterions/contrastive.py
code served (permissive licence) · get_code("a71babdd4607edf9")
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. The image it ran in was not recorded. If your copy returns the same type 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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# ref: (n, d) shape (2, 4)
# pos: (n, d) shape (2, 4)
# neg: (n, d) shape (2, 4)

ref = torch.randn(2, 4)
pos = torch.randn(2, 4)
neg = torch.randn(2, 4)

ARGS = {
    "ref": ref,
    "pos": pos,
    "neg": neg,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
flatten_dict Ran
ran; our contract draft was wrong, not the code
dynamical-inference/dcl/dcl/datajoint/sweep.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from dynamical-inference/ebc, is pointer only (licence: NONE) · get_code("f30ac4807ed6c8c5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from dynamical-inference/ebc, and GitHub detected no licence in that repository 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.

infonce Ran
ran; our contract draft was wrong, not the code
dynamical-inference/dcl/dcl/criterions/contrastive.py
code served (permissive licence) · get_code("83a611ce95a4a3e1")
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 torch
from torch import Tensor

torch.manual_seed(0)

# Create small tensors for pos_dist and neg_dist
# pos_dist: positive distances, shape (batch_size,) = (2,)
# neg_dist: negative distances, shape (batch_size, num_negatives) = (2, 4)

batch_size = 2
num_negatives = 4

pos_dist = torch.randn(batch_size)
neg_dist = torch.randn(batch_size, num_negatives)

ARGS = {
    "pos_dist": pos_dist,
    "neg_dist": neg_dist,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — 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
unflatten_dict Ran
ran; our contract draft was wrong, not the code
dynamical-inference/dcl/dcl/datajoint/sweep.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from dynamical-inference/ebc, is pointer only (licence: NONE) · get_code("20b0217aa68c7594")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from dynamical-inference/ebc, and GitHub detected no licence in that repository 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.

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, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 2 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
construct_invertible_mlp 1 other paper
1 later
2510.21706 (2025-10)
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
dot_similarity 1 other paper
1 later
2510.21706 (2025-10)
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
flatten_dict 1 other paper
1 later
2510.21706 (2025-10)
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
unflatten_dict 1 other paper
1 later
2510.21706 (2025-10)
Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions

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

Self-supervised learning (SSL) approaches have brought tremendous success across many tasks and domains. It has been argued that these successes can be attributed to a link between SSL and identifiable representation learning: Temporal structure and auxiliary variables ensure that latent representations are related to the true underlying generative factors of the data. Here, we deepen this connection and show that SSL can perform system identification in latent space. We propose dynamics contrastive learning, a framework to uncover linear, switching linear and non-linear dynamics under a non-linear observation model, give theoretical guarantees and validate them empirically. Code: github.com/dynamical-inference/dcl * Equal contribution.

For agents

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

get_harvested_code_for_paper("2410.14673")
get_code_for_paper("2410.14673")
have("2410.14673")

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

curl https://syntology.ai/api/ran/2410.14673.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.14673.svg)](https://syntology.ai/paper/2410.14673)

Connect an agent — have() is free.