Papers › SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings

SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings

14 Jun 2024arXiv:2406.10354archive 2025-07-28

Barbora Barancikova, Zhuoyue Huang, Cristopher Salvi

Score-based diffusion models have recently emerged as state-of-the-art generative models for a variety of data modalities. Nonetheless, it remains unclear how to adapt these models to generate long multivariate time series. Viewing a time series as the discretization of an underlying continuous process, we introduce SigDiffusion, a novel diffusion model operating on log-signature embeddings of the data. The forward and backward processes gradually perturb and denoise log-signatures preserving their algebraic structure. To recover a signal from its log-signature, we provide new closed-form inversion formulae expressing the coefficients obtained by expanding the signal in a given basis (e.g. Fourier or orthogonal polynomials) as explicit polynomial functions of the log-signature. Finally, we show that combining SigDiffusion with these inversion formulae results in highly realistic time series generation, competitive with the current state-of-the-art on various datasets of synthetic and real-world examples.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 41 code samples harvested from 3 repositories linked to this paper: 28 ran (of which 5 constructed an object rather than computing a result; 21 with no instrument failure: 8 honoured, 1 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 32 samples from 2 repositories, 23 ran (16 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Barb0ra/SigDiffusions officialmentioned on GitHubjaxSyntology: 9 samples, 5 ran (0 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

41 samples harvested: 28 ran (of which 5 constructed an object rather than computing a result; 21 with no instrument failure: 8 honoured, 1 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
1ran; the contract check could not run
12ran
13unverified

Licence: 11 of the 41 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Barb0ra/SigDiffusions official repository 9 samples, 5 ran (0 instrument-failed) · 4 unverified
AdaLayerNorm in 7 papers model.py ran no licence file found · pointer only · 66ba3dc1453ebfa8 · report fixture: returned AdaLayerNorm · level recorded 2026-09-22
AttentionBlock in 69 papers model.py ran no licence file found · pointer only · b57c91105cf43bfd · report fixture: returned AttentionBlock · level recorded 2026-09-22
LearnablePositionalEncoding in 7 papers model.py ran fingerprinted no licence file found · pointer only · 89e0fe61f90c79f6 · report fixture: returned LearnablePositionalEncoding · level recorded 2026-09-22
LinearAttentionBlock model.py ran no licence file found · pointer only · 7fd03ae35f8f8af7 · report fixture: returned LinearAttentionBlock · level recorded 2026-09-22
SinusoidalPosEmb in 18 papers
census: 6 implementations from 6 papers, 3 distinct outputs on one shared input
model.py ran fingerprinted no licence file found · pointer only · 44eddf4f037504f8 · report fixture: returned SinusoidalPosEmb · level recorded 2026-09-22
AbstractAttentionBlock model.py unverified no licence file found · pointer only · a0f03fe49bb607f0 · report
FeedForwardBlock in 7 papers model.py unverified no licence file found · pointer only · cd1df37cc84912df · report
Transformer in 173 papers model.py unverified no licence file found · pointer only · 535cf740696d6f5e · report
TransformerLayer in 34 papers model.py unverified no licence file found · pointer only · 9605b4044e0b00ed · report
Y-debug-sys/Diffusion-TS found in paper text by Syntology 14 samples, 8 ran (3 instrument-failed) · 6 unverified
AdaLayerNorm in 7 papers Models/interpretable_diffusion/gaussian_diffusion.py ran · metamorphic tier: invariant MIT (permissive) · 17df8b9f4c6833b9 · report fixture: signature x:Tensor/3/float, timestep:Tensor/1/float, label_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LearnablePositionalEncoding in 7 papers Models/interpretable_diffusion/gaussian_diffusion.py ran MIT (permissive) · d0d1a8d43d381f8c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SinusoidalPosEmb in 18 papers
census: 6 implementations from 6 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float32
Models/interpretable_diffusion/gaussian_diffusion.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e527f57c18083096 · report fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-22
cond_fn Models/interpretable_diffusion/gaussian_diffusion.py ran · our draft was wrong MIT (permissive) · 11d182d075e866b3 · report fixture: signature x:Tensor/2/float, t:Tensor/1/int, classifier:callable/0/?, y:Tensor/1/int, classifier_scale:float/0/float · returned Tensor · level recorded 2026-09-22
default in 430 papers Models/interpretable_diffusion/gaussian_diffusion.py ran · our draft was wrong fingerprinted MIT (permissive) · fc87ca21003c5c48 · report fixture: signature val:str/0/str, d:str/0/str · returned str · level recorded 2026-09-22
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input
Models/interpretable_diffusion/gaussian_diffusion.py ran · violated contract MIT (permissive) · e4db616479dcb90a · report fixture: signature x:NoneType/0/? · returned bool · level recorded 2026-09-22
extract in 149 papers
census: 9 implementations from 12 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
Models/interpretable_diffusion/gaussian_diffusion.py ran · our draft was wrong MIT (permissive) · 7d62068d1d024522 · report fixture: signature a:Tensor/2/float, t:Tensor/2/int, x_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
Models/interpretable_diffusion/gaussian_diffusion.py ran · honoured contract MIT (permissive) · d6b55d231d2542c0 · report fixture: signature t:Tensor/2/float, args:tuple/1/empty, kwargs:dict/0/? · returned Tensor · level recorded 2026-09-22
Decoder in 210 papers Models/interpretable_diffusion/gaussian_diffusion.py unverified MIT (permissive) · 3b43c4c4d7b69a9d · report
DecoderBlock in 30 papers Models/interpretable_diffusion/gaussian_diffusion.py unverified MIT (permissive) · 463007d5004378ce · report
Diffusion_TS Models/interpretable_diffusion/gaussian_diffusion.py unverified MIT (permissive) · 0cc30159869c886b · report
Encoder in 278 papers Models/interpretable_diffusion/gaussian_diffusion.py unverified MIT (permissive) · 97d5065144c647f5 · report
EncoderBlock in 23 papers Models/interpretable_diffusion/gaussian_diffusion.py unverified MIT (permissive) · f167bbb63f7b5ffd · report
Transformer in 173 papers Models/interpretable_diffusion/gaussian_diffusion.py unverified MIT (permissive) · 2df3968af29cdc9f · report
lim0606/ddo found in paper text by Syntology 18 samples, 15 ran (4 instrument-failed) · 3 unverified
c_p lib/ggp.py ran · honoured contract fingerprinted MIT (permissive) · 34afa7744b295787 · report fixture: signature p:float/0/float · returned float64 · level recorded 2026-09-24
design_lowpass_filter_dct lib/models/aliasfree_dct.py ran MIT (permissive) · dad41c4c6f5ef82f · report fixture: signature numtaps:int/0/int, cutoff:float/0/float, width:float/0/float, fs:float/0/float, radial:bool/0/bool, EPS:float/0/float · returned Tensor · level recorded 2026-09-24
format_time in 140 papers dnnlib/util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 053fc534bc6bb989 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-25
format_time_brief in 69 papers dnnlib/util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 77f4aa0649e7f404 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-25
get_batch in 82 papers lib/models/contconv.py ran · honoured contract MIT (permissive) · 63c721392992855f · report fixture: signature batch_size:int/0/int, num_points:int/0/int · returned Tensor · level recorded 2026-09-24
get_coords in 5 papers lib/models/contconv.py ran · honoured contract fingerprinted MIT (permissive) · 577031d9c370f7c7 · report fixture: signature batch_size:int/0/int, height:int/0/int · returned Tensor · level recorded 2026-09-24
get_mgrid in 16 papers gano.py ran · honoured contract fingerprinted MIT (permissive) · 53cb98760ce45cd1 · report fixture: signature dim:int/0/int, img_height:int/0/int · returned Tensor · level recorded 2026-09-24
get_mgrid in 16 papers lib/models/contconv.py ran · honoured contract fingerprinted MIT (permissive) · 6e0529bf4b8f6ec9 · report fixture: signature img_height:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-24
group_norm in 17 papers lib/models/fourier.py ran MIT (permissive) · 06ccdd7ca6235c7b · report fixture: signature x:Tensor/3/float, ref_freq:Tensor/3/float, num_groups:int/0/int, dim:int/0/int, EPS:float/0/float · returned Tensor · level recorded 2026-09-24
image_to_xv gano.py ran · our draft was wrong fingerprinted MIT (permissive) · 5b7f7ef74742d726 · report fixture: signature x:Tensor/4/float, v:Tensor/4/float · returned tuple · level recorded 2026-09-24
low_discrepancy_rand lib/diffusion.py ran · honoured contract MIT (permissive) · 5967738153293c90 · report fixture: signature batch_size:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-24
low_discrepancy_randint lib/diffusion.py ran MIT (permissive) · 7a9a3c30c002f635 · report fixture: signature batch_size:int/0/int, k:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-24
sech lib/diffusion.py ran · honoured contract fingerprinted MIT (permissive) · 41ed864df9f2723f · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
u_p lib/ggp.py ran fingerprinted MIT (permissive) · 074bb7829ad247e9 · report fixture: signature x:Tensor/1/float, p:float/0/float, EPS:float/0/float · returned Tensor · level recorded 2026-09-24
xv_to_image gano.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · dc0158b1ae43506a · report fixture: signature x:Tensor/3/float, v:Tensor/3/float · returned tuple · level recorded 2026-09-24
ask_yes_no in 70 papers dnnlib/util.py unverified MIT (permissive) · 9d31d2c4cd16bb2d · report
euler_maruyama_method lib/sdes.py unverified MIT (permissive) · be66681c78a85f62 · report
g_p lib/ggp.py unverified MIT (permissive) · 98798568c7d9b962 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for SigDiffusion (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for SigDiffusion (graph method: SigDiffusion). 9 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 5 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. Transformer entry · level 0 · unverified · 535cf740696d6f5e
  2. LearnablePositionalEncoding data_transform · level 1 · ran · 89e0fe61f90c79f6
  3. TransformerLayer model · level 0 · unverified · 9605b4044e0b00ed
  4. AbstractAttentionBlock helper · level 0 · unverified · a0f03fe49bb607f0
  5. AttentionBlock model · level 1 · ran · b57c91105cf43bfd
  6. FeedForwardBlock model · level 0 · unverified · cd1df37cc84912df
  7. LinearAttentionBlock model · level 1 · ran · 7fd03ae35f8f8af7
  8. AdaLayerNorm helper · level 1 · ran · 66ba3dc1453ebfa8
  9. SinusoidalPosEmb helper · level 1 · ran · 44eddf4f037504f8

harvested Assembly for SigDiffusion (graph method: SigDiffusion). 23 bricks; individually on a fixture: 17 ran (of which 7 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Diffusion_TS entry · level 0 · unverified · 0cc30159869c886b
  2. Transformer model · level 0 · unverified · 2df3968af29cdc9f
  3. cond_fn helper · level 1 · ran · our draft was wrong · 11d182d075e866b3
  4. cosine_beta_schedule scheduler · level 1 · ran · honoured contract · 05e94467a0de94a4
  5. default helper · level 1 · ran · our draft was wrong · fc87ca21003c5c48
  6. extract helper · level 1 · ran · our draft was wrong · 7d62068d1d024522
  7. identity helper · level 1 · ran · honoured contract · d6b55d231d2542c0
  8. linear_beta_schedule scheduler · level 1 · ran · honoured contract · 482723f534770483
  9. Conv_MLP helper · level 1 · ran · 32defcc2b620d0aa
  10. Decoder helper · level 0 · unverified · 3b43c4c4d7b69a9d
  11. Encoder helper · level 0 · unverified · 97d5065144c647f5
  12. LearnablePositionalEncoding helper · level 1 · ran · d0d1a8d43d381f8c
  13. exists helper · level 1 · ran · violated contract · e4db616479dcb90a
  14. Transpose helper · level 1 · ran · dde0210f6a5d551c
  15. DecoderBlock helper · level 0 · unverified · 463007d5004378ce
  16. EncoderBlock helper · level 0 · unverified · f167bbb63f7b5ffd
  17. AdaLayerNorm helper · level 1 · ran · 17df8b9f4c6833b9
  18. CrossAttention helper · level 1 · ran · 70413232706855f0
  19. FourierLayer helper · level 1 · ran · edf24dca081f9e86
  20. FullAttention helper · level 1 · ran · ffd74a96f021eabd
  21. GELU2 helper · level 1 · ran · d552eac1f22192a9
  22. TrendBlock helper · level 1 · ran · b97fade1356fcd8b
  23. SinusoidalPosEmb helper · level 1 · ran · e527f57c18083096

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.10354") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Time SeriesTime Series Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections