SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.09729 · 2022

It's Raw! Audio Generation with State-Space Models

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); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2202.09729.json · badge: /api/ran/2202.09729.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
copy not recorded community
not in the paper's declared repositories
3 ran · 0 no recorded run
rf5/simple-sashimi reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
necrashter/SaShiMi-796 reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
albertfgu/diffwave-sashimi reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from jeonsworld/ViT-pytorch
pointer only · get_code("0f786c407fb1ee4c")
How it ran

The 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.

Activation Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from raminmh/liquid-s4
pointer only · get_code("89b10a8b26bbb7ed")
How it ran

The 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.

calc_diffusion_step_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rf5/simple-sashimi/sashimi/model.py
pointer only (licence: NONE) · get_code("163666f807c3a9bd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rf5/simple-sashimi 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.

get_initializer Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from ag1988/dss
pointer only · get_code("f3449af8fae1d130")
How it ran

The 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.

naive_cauchy_kernel Ran
ran; our contract draft was wrong, not the code
necrashter/SaShiMi-796/S4/cauchy.py
code served (permissive licence) · get_code("5aa881c74c73bcb8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, ndim 2, 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

torch.manual_seed(0)

# Based on the function body:
# - g.unsqueeze(1) suggests g has shape that can be unsqueezed at dim 1
# - Lambda is used as the second operand in subtraction with g.unsqueeze(1)
# - a0, a1, b0, b1 are multiplied and divided by denominator, then summed over dim=-1
# - The pattern suggests: g has shape (N,), Lambda has shape (M,)
# - After g.unsqueeze(1), it becomes (N, 1), and denominator becomes (N, M)
# - a0, b0, a1, b1 should broadcast with denominator and sum over last dim
# - So a0, a1, b0, b1 should have shape (..., M) where M matches Lambda's size

N = 2  # batch size
M = 4  # feature dimension

# g: shape (N,) - will be unsqueezed to (N, 1)
g = torch.randn(N)

# Lambda: shape (M,) - represents poles or eigenvalues
Lambda = torch.randn(M)

# a0, a1, b0, b1: shape (N, M) to broadcast with denominator (N, M)
a0 = torch.randn(N, M)
a1 = torch.randn(N, M)
b0 = torch.randn(N, M)
b1 = torch.randn(N, M)

ARGS = {
    'a0': a0,
    'a1': a1,
    'b0': b0,
    'b1': b1,
    'g': g,
    'Lambda': Lambda
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 2, 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
sampling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
albertfgu/diffwave-sashimi/generate.py
code served (permissive licence) · get_code("8765bfcc420abc33")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import torch.nn as nn

torch.manual_seed(0)

class StandInNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(10, 10)
    
    def forward(self, inputs, mel_spec=None):
        x, diffusion_steps = inputs
        batch_size, channels, length = x.shape
        # Return tensor with same shape as x
        return torch.randn(batch_size, channels, length)

net = StandInNet()

size = (2, 1, 8)  # (batch_size=2, channels=1, length=8)

T = 5
Alpha = torch.linspace(0.99, 0.95, T)
Alpha_bar = torch.cumprod(Alpha, dim=0)
Sigma = torch.sqrt((1 - Alpha) * (1 - torch.cat([torch.tensor([1.0]), Alpha_bar[:-1]])) / (1 - Alpha_bar))

diffusion_hyperparams = {
    'T': T,
    'Alpha': Alpha,
    'Alpha_bar': Alpha_bar,
    'Sigma': Sigma
}

condition = torch.randn(2, 3, 6)  # Some conditioning tensor

ARGS = {
    'net': net,
    'size': size,
    'diffusion_hyperparams': diffusion_hyperparams,
    'condition': condition
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py could not observe it (call:AssertionError)
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

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 (4 with at least one paper dated earlier, 1 the same month, 3 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
swish 206 other papers
92 dated earlier, 2 the same month, 108 later, 4 same year, order not determinable · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
Activation 15 other papers
4 dated earlier, 11 later · 2 only as an assembly brick
1312.5602 (2013-12)
Playing Atari with Deep Reinforcement Learning
2008.07669 (2020-08)
HiPPO: Recurrent Memory with Optimal Polynomial Projections
2009.09761 (2020-09)
DiffWave: A Versatile Diffusion Model for Audio Synthesis
and 12 more not named here
get_initializer 10 other papers
2 dated earlier, 8 later · 1 only as an assembly brick
2008.07669 (2020-08)
HiPPO: Recurrent Memory with Optimal Polynomial Projections
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2203.14343 (2022-03)
Diagonal State Spaces are as Effective as Structured State Spaces
and 7 more not named here
calc_diffusion_step_embedding 1 other paper
1 dated earlier
2009.09761 (2020-09)
DiffWave: A Versatile Diffusion Model for Audio Synthesis

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

Developing architectures suitable for modeling raw audio is a challenging problem due to the high sampling rates of audio waveforms. Standard sequence modeling approaches like RNNs and CNNs have previously been tailored to fit the demands of audio, but the resultant architectures make undesirable computational tradeoffs and struggle to model waveforms effectively. We propose SaShiMi, a new multi-scale architecture for waveform modeling built around the recently introduced S4 model for long sequence modeling. We identify that S4 can be unstable during autoregressive generation, and provide a simple improvement to its parameterization by drawing connections to Hurwitz matrices. SaShiMi yields state-of-the-art performance for unconditional waveform generation in the autoregressive setting. Additionally, SaShiMi improves non-autoregressive generation performance when used as the backbone architecture for a diffusion model. Compared to prior architectures in the autoregressive generation setting, SaShiMi generates piano and speech waveforms which humans find more musical and coherent respectively, e.g. 2x better mean opinion scores than WaveNet on an unconditional speech generation task. On a music generation task, SaShiMi outperforms WaveNet on density estimation and speed at both training and inference even when using 3x fewer parameters. Code can be found at https://github.com/HazyResearch/state-spaces and samples at https://hazyresearch.stanford.edu/sashimi-examples.

For agents

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

get_harvested_code_for_paper("2202.09729")
get_code_for_paper("2202.09729")
have("2202.09729")

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

curl https://syntology.ai/api/ran/2202.09729.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.09729.svg)](https://syntology.ai/paper/2202.09729)

Connect an agent — have() is free.