Papers › Don't Pay Attention to the Noise: Learning Self-supervised Representations of Light...

Don't Pay Attention to the Noise: Learning Self-supervised Representations of Light Curves with a Denoising Time Series Transformer

6 Jul 2022arXiv:2207.02777archive 2025-07-28

Mario Morvan, Nikolaos Nikolaou, Kai Hou Yip, Ingo Waldmann

Astrophysical light curves are particularly challenging data objects due to the intensity and variety of noise contaminating them. Yet, despite the astronomical volumes of light curves available, the majority of algorithms used to process them are still operating on a per-sample basis. To remedy this, we propose a simple Transformer model -- called Denoising Time Series Transformer (DTST) -- and show that it excels at removing the noise and outliers in datasets of time series when trained with a masked objective, even when no clean targets are available. Moreover, the use of self-attention enables rich and illustrative queries into the learned representations. We present experiments on real stellar light curves from the Transiting Exoplanet Space Satellite (TESS), showing advantages of our approach compared to traditional denoising techniques.

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 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 16 ran (12 with no instrument failure; 4 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.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mariomorvan/denoising-time-series-transformer officialmentioned in paperpytorchSyntology: 18 samples, 16 ran (4 instrument-failed) · 2 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.

Code Syntology ran Syntology

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
10ran
2unverified

Licence: 18 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mariomorvan/denoising-time-series-transformer. “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”. “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.

mariomorvan/denoising-time-series-transformer official repository 18 samples, 16 ran (4 instrument-failed) · 2 unverified
BatchNorm in 19 papers models/models.py ran · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · 42f0ae0ee495e5d7 · report fixture: signature input:Tensor/3/float · returned Tensor · level recorded 2026-09-22
FixedPosEmbedding models/models.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 043d857ed2708db5 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
IQRLoss models/models.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 7347e64e7d97d46a · report fixture: signature input:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LearnedPosEmbedding models/models.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 7c4b76725171d44c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
MaskedHuberLoss models/models.py ran · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · f4d0858dcf8f10e0 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
MaskedL1Loss models/models.py ran · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · ac251bc6c8ffdbfe · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
MaskedMSELoss models/models.py ran · metamorphic tier: invariant GPL-3.0 (copyleft) · pointer only · 3a7ede8147c5dd0e · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22
PosEmbedding models/models.py ran · metamorphic tier: invariant fingerprinted GPL-3.0 (copyleft) · pointer only · 150c70c525ad502d · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TransformerEncoder in 96 papers models/models.py ran GPL-3.0 (copyleft) · pointer only · e583815367c0ebbc · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned list · level recorded 2026-09-24
TransformerEncoderLayer in 90 papers models/models.py ran GPL-3.0 (copyleft) · pointer only · 82ac7fddfe86c023 · report fixture: signature src:Tensor/3/float · returned Tensor · level recorded 2026-09-24
detrend in 8 papers models/models.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · 1b6804b7cf69d1b7 · report fixture: signature x:Tensor/2/float, trend:Tensor/2/float · returned Tensor · level recorded 2026-09-22
estimate_noise models/models.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 4372f26d99b2b73d · report fixture: signature x:Tensor/2/float, dim:int/0/int, window_size:int/0/int, step:int/0/int, reduce:str/0/str, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
inverse_standardise_batch models/models.py ran · honoured contract fingerprinted GPL-3.0 (copyleft) · pointer only · ffb7ff09cfc9a52a · report fixture: signature x:Tensor/2/float, mu:Tensor/1/float, sigma:Tensor/1/float · returned Tensor · level recorded 2026-09-22
iqr models/models.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 9f5d0dc785c490d3 · report fixture: signature batch:Tensor/2/float, dim:int/0/int, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
naniqr models/models.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · ebed1f18f80743bc · report fixture: signature batch:Tensor/2/float, dim:int/0/int, reduction:str/0/str · returned Tensor · level recorded 2026-09-22
nanstd in 13 papers
census: 3 implementations from 8 papers, 2 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/models.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 1bfe235be7e974ba · report fixture: signature input:Tensor/2/float, dim:NoneType/0/?, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
LitImputer models/models.py unverified GPL-3.0 (copyleft) · pointer only · ab58a7f246202a08 · report
_MaskedLoss models/models.py unverified GPL-3.0 (copyleft) · pointer only · d02ec62220ae4d91 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Denoising Time Series Transformer (DTST) (graph method: Denoising Time Series Transformer (DTST)). 18 bricks; individually on a fixture: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. LitImputer entry · level 0 · unverified · ab58a7f246202a08
  2. IQRLoss loss · level 1 · ran · 7347e64e7d97d46a
  3. MaskedHuberLoss loss · level 1 · ran · f4d0858dcf8f10e0
  4. MaskedL1Loss loss · level 1 · ran · ac251bc6c8ffdbfe
  5. MaskedMSELoss loss · level 1 · ran · 3a7ede8147c5dd0e
  6. PosEmbedding model · level 1 · ran · 150c70c525ad502d
  7. TransformerEncoder model · level 1 · ran · e583815367c0ebbc
  8. TransformerEncoderLayer model · level 1 · ran · 82ac7fddfe86c023
  9. detrend helper · level 1 · ran · honoured contract · 1b6804b7cf69d1b7
  10. estimate_noise helper · level 1 · ran · our draft was wrong · 4372f26d99b2b73d
  11. inverse_standardise_batch helper · level 1 · ran · honoured contract · ffb7ff09cfc9a52a
  12. iqr helper · level 1 · ran · our draft was wrong · 9f5d0dc785c490d3
  13. naniqr helper · level 1 · ran · our draft was wrong · ebed1f18f80743bc
  14. _MaskedLoss helper · level 0 · unverified · d02ec62220ae4d91
  15. FixedPosEmbedding model · level 1 · ran · 043d857ed2708db5
  16. LearnedPosEmbedding model · level 1 · ran · 7c4b76725171d44c
  17. BatchNorm model · level 1 · ran · 42f0ae0ee495e5d7
  18. nanstd helper · level 1 · ran · our draft was wrong · 1bfe235be7e974ba

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="2207.02777") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DenoisingTime SeriesTime Series Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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