Hans Briegel, Arunava Majumder, Marius Krumm, Paulin De Schoulepnikoff, Hendrik Poulsen Nautrup, Gorka Mu Ñoz-Gil, Florian Ürrutter
2 of 2 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, 0 violated it and 1 has no contract verdict; 0 failures 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/2602.06741.json · badge: /api/ran/2602.06741.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 |
|---|---|---|
| gorkamunoz/air | community Papers with Code archive |
2 ran · 0 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| VAIR | Ran ran on a synthesized input · constructed an object; no result was computed |
gorkamunoz/air/air/models.py pointer only (licence: NONE) · get_code("3ce18e274b37af46") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gorkamunoz/air 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. |
| reparametrize | Ran ran, honoured the contract we drafted |
gorkamunoz/air/air/models.py pointer only (licence: NONE) · get_code("926434dc272944d2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, gorkamunoz/air 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. |
Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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, 0 later) and 1 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 |
|---|---|---|---|
| reparametrize brick of this paper's assembly: helper |
10 other papers 10 dated earlier · 2 only as an assembly brick |
2105.14203 (2021-05) Understanding Instance-based Interpretability of Variational Auto-Encoders |
2111.02338 (2021-11) Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity 2210.13647 (2022-10) Temporally Disentangled Representation Learning and 7 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.
Learning interpretable representations with variational autoencoders (VAEs) is a major goal of representation learning. The main challenge lies in obtaining disentangled representations, where each latent dimension corresponds to a distinct generative factor. This difficulty is fundamentally tied to the inability to perform nonlinear independent component analysis. Here, we introduce the framework of action-induced representations (AIRs) which models representations of physical systems given experiments (or actions) that can be performed on them. We show that, in this framework, we can provably disentangle degrees of freedom w.r.t. their action dependence. We further introduce a variational AIR architecture (VAIR) that can extract AIRs and therefore achieve provable disentanglement where standard VAEs fail. Beyond state representation, VAIR also captures the action dependence of the underlying generative factors, directly linking experiments to the degrees of freedom they influence. Creating compressed representations of high-dimensional observations has become essential across a range of machine learning tasks, from improving computational efficiency in downstream pipelines (Rombach et al., 2022;Laskin et al., 2020), to enabling interpretable approaches that aim to uncover structure within the input data. In this context, variational autoencoders (VAEs) (Kingma & Welling, 2013) have emerged as a hallmark architecture for unsupervised representation learning. VAEs aim to compress input data into a low-dimensional latent space, creating a minimal representation of it. In cases where a dataset is characterized by few hidden variables, also known as factors of variation, VAEs are expected to extract these by encoding them in their latent space (Higgins et al., 2017). In physics, this
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2602.06741")
get_code_for_paper("2602.06741")
have("2602.06741")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2602.06741.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2602.06741)
Connect an agent — have() is free.