Pascal Vincent, Li Jing, Yann Lecun, Yuandong Tian
5 of 5 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, 1 violated it and 3 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; 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/2110.09348.json · badge: /api/ran/2110.09348.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.
| Repository | Role | Ran |
|---|---|---|
| facebookresearch/directclr | canonical (classifier label) classifier basis: classifier_2025 |
4 ran · 0 no recorded run |
| copy not recorded | community not in the paper's declared repositories |
1 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| GaussianBlur | Ran ran on a synthesized input |
facebookresearch/directclr/directclr/utils.py pointer only (licence: NOASSERTION) · get_code("5cb188100f283607") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/directclr (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. |
| Solarization | Ran ran on a synthesized input |
facebookresearch/directclr/directclr/utils.py pointer only (licence: NOASSERTION) · get_code("278b169f0382b00f") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/directclr (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. |
| Transform | Ran ran on a synthesized input |
facebookresearch/directclr/directclr/utils.py pointer only (licence: NOASSERTION) · get_code("b7848967558711a1") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/directclr (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. |
| exclude_bias_and_norm | Ran ran, violated the contract we drafted |
this paper's copy was not recorded; identical code first harvested from facebookresearch/vicreg pointer only · get_code("28c640db8f721c0d") How it ranThe 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. |
| singular | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
facebookresearch/directclr/spectrum.py pointer only (licence: NOASSERTION) · get_code("564d5f8da88a4568") How it ranThe body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/directclr (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. |
Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| exclude_bias_and_norm | 7 other papers 1 dated earlier, 6 later |
2105.04906 (2021-05) VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning |
2112.09164 (2021-12) High Fidelity Visualization of What Your Self-Supervised Representation Knows About 2211.10831 (2022-11) Joint Embedding Predictive Architectures Focus on Slow Features and 4 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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from different views of the same image. Various methods have been proposed to solve the collapsing problem where all embedding vectors collapse to a trivial constant solution. Among these methods, contrastive learning prevents collapse via negative sample pairs. It has been shown that non-contrastive methods suffer from a lesser collapse problem of a different nature: dimensional collapse, whereby the embedding vectors end up spanning a lower-dimensional subspace instead of the entire available embedding space. Here, we show that dimensional collapse also happens in contrastive learning. In this paper, we shed light on the dynamics at play in contrastive learning that leads to dimensional collapse. Inspired by our theory, we propose a novel contrastive learning method, called DirectCLR, which directly optimizes the representation space without relying on an explicit trainable projector. Experiments show that DirectCLR outperforms SimCLR with a trainable linear projector on ImageNet.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2110.09348")
get_code_for_paper("2110.09348")
have("2110.09348")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2110.09348.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2110.09348)
Connect an agent — have() is free.