Alexander Ivanov, Ivan Mikheev, Ivan Kirillov, Kirill Chernyshev, Andrey Shutkin, Denis Parkhomenko, Kandinsky Lab, Kirill Malakhov, Ilia Vasiliev, Ilia Trushkin, Valeriya Kobenko, David Chikovani, and 3 more
1 of 2 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; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2608.05798.json · badge: /api/ran/2608.05798.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 |
|---|---|---|
| kandinskylab/kvae | canonical (classifier label) classifier basis: census |
1 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_activation_with_kwargs | Ran ran; our contract draft was wrong, not the code |
kandinskylab/kvae/kvae/layers/common.py code served (permissive licence) · get_code("370d1d8404d6280a") How it ranRan 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 SiLU. 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.
|
| get_normalization | Not yet run unverified (harvested, no recorded run) |
kandinskylab/kvae/kvae/layers/norm.py code served (permissive licence) · get_code("f2d28f519435983f") How it ranno invocation 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, 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 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.
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 2026-11-21.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -two causal video tokenizers for 4x16x16 and 4x8x8 compression; KVAE-2D, an image model, compressing input by factor of 8 with 32 channels. We demonstrate that reconstruction (PSNR, LPIPS, PESQ, etc.) and generation results on objective (Frechet Distance, CLIP score, CLAP score, etc.) and subjective (side-by-side evaluation) metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio. Considering difficulty of development, we share with community training details, model selection method and ablation on design choices. The code is publicly available at https://github.com/kandinskylab/kvae and https://github.com/kandinskylab/kvae-audio. 1 worked on video tokenization 2 worked on image tokenization 3 worked on audio tokenization 4 worked on diffusbility estimation .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2608.05798")
get_code_for_paper("2608.05798")
have("2608.05798")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2608.05798.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2608.05798)
Connect an agent — have() is free.