Papers › T-Rep: Representation Learning for Time Series using Time-Embeddings

T-Rep: Representation Learning for Time Series using Time-Embeddings

6 Oct 2023arXiv:2310.04486archive 2025-07-28

Archibald Fraikin, Adrien Bennetot, Stéphanie Allassonnière

Multivariate time series present challenges to standard machine learning techniques, as they are often unlabeled, high dimensional, noisy, and contain missing data. To address this, we propose T-Rep, a self-supervised method to learn time series representations at a timestep granularity. T-Rep learns vector embeddings of time alongside its feature extractor, to extract temporal features such as trend, periodicity, or distribution shifts from the signal. These time-embeddings are leveraged in pretext tasks, to incorporate smooth and fine-grained temporal dependencies in the representations, as well as reinforce robustness to missing data. We evaluate T-Rep on downstream classification, forecasting, and anomaly detection tasks. It is compared to existing self-supervised algorithms for time series, which it outperforms in all three tasks. We test T-Rep in missing data regimes, where it proves more resilient than its counterparts. Finally, we provide latent space visualisation experiments, highlighting the interpretability of the learned representations.

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 25 code samples: 24 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 25: 19 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 18 ran (9 with no instrument failure; 9 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

let-it-care/t-rep officialmentioned in papermentioned on GitHubpytorchSyntology: 24 samples, 18 ran (9 instrument-failed) · 6 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

25 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 10 where Syntology's instrument failed) · 6 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.

1ran · honoured contract
4ran · our draft was wrong
6ran; the contract check could not run
8ran
6unverified

Licence: 25 of the 25 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 let-it-care/t-rep. 1 sample is listed last, in a group without a repository. “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.

let-it-care/t-rep official repository 24 samples, 18 ran (9 instrument-failed) · 6 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 3, kind float, dtype float32
trep.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · e4d4c00eca81ac32 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DilatedConvEncoder in 8 papers trep.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · d00747ac84a3997a · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
GaussianPositionalEncoding trep.py ran · metamorphic tier: invariant licence not identified · pointer only · 8ec4af15819bfd4f · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LearnablePositionalEncodingBig trep.py ran · metamorphic tier: invariant licence not identified · pointer only · a18a1732e1ca752f · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LearnablePositionalEncodingSmall trep.py ran · metamorphic tier: invariant licence not identified · pointer only · 9f1774b017ada5c2 · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
T2vCos trep.py ran licence not identified · pointer only · f5ca3b07f6e82c2c · report fixture: signature tau:Tensor/2/float · returned Tensor · level recorded 2026-09-24
T2vSin trep.py ran licence not identified · pointer only · 059554668ba6727f · report fixture: signature tau:Tensor/2/float · returned Tensor · level recorded 2026-09-24
TembedCondPredHead trep.py ran · metamorphic tier: invariant licence not identified · pointer only · 070c5941256f46c5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_tembed_jsd_pairs trep.py ran · honoured contract licence not identified · pointer only · 93fd24844f87fff4 · report fixture: signature num_taus:int/0/int, n_pairs:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-22
get_tembed_pred_pairs trep.py ran · our draft was wrong licence not identified · pointer only · 34f54041ac94d24e · report fixture: signature max_range:int/0/int, max_dist:int/0/int, B:int/0/int, n_pairs:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-22
instance_contrastive_loss trep.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 9f8750cded333a83 · report fixture: signature h1:Tensor/3/float, h2:Tensor/3/float · returned Tensor · level recorded 2026-09-22
take_per_row trep.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 629a2d0ddc05f4b5 · report fixture: signature A:Tensor/2/float, indx:ndarray/1/int, num_elem:int/0/int · returned Tensor · level recorded 2026-09-22
tembed_cond_pred_loss trep.py ran; the contract check could not run (RAISES) licence not identified · pointer only · b9dc3c835ad04449 · report fixture: signature h1:Tensor/3/float, h2:Tensor/3/float, tau1:Tensor/3/float, tau2:Tensor/3/float, task_head:callable/0/?, max_time_dist:int/0/int · returned Tensor · level recorded 2026-09-24
tembed_jsd_pred_loss trep.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 132e68ed0b48e01b · report fixture: signature h1:Tensor/3/float, h2:Tensor/3/float, tau1:Tensor/3/float, tau2:Tensor/3/float, tembed_jsd_task_head:callable/0/? · returned Tensor · level recorded 2026-09-24
temporal_contrastive_loss in 5 papers trep.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 37fd464b5f0a503b · report fixture: signature h1:Tensor/3/float, h2:Tensor/3/float · returned Tensor · level recorded 2026-09-22
torch_kl trep.py ran · our draft was wrong fingerprinted licence not identified · pointer only · d63c90fd727c9544 · report fixture: signature a:Tensor/2/float, b:Tensor/2/float · returned Tensor · level recorded 2026-09-24
torch_pad_nan in 8 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
trep.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 98da2c25852e8ec3 · report fixture: signature arr:Tensor/2/float, left:int/0/int, right:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-22
torch_pad_with trep.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · c7b091c653c77e75 · report fixture: signature arr:Tensor/2/float, pad_val:float/0/float, left:int/0/int, right:int/0/int, dim:int/0/int · returned Tensor · level recorded 2026-09-22
LearnablePositionalEncodingHybrid trep.py unverified licence not identified · pointer only · 4f9901e390aa2913 · report
TRep trep.py unverified licence not identified · pointer only · daa518cc4409de18 · report
TSEncoder in 5 papers trep.py unverified licence not identified · pointer only · d0c784be860ebbec · report
TembedDivPredHead trep.py unverified licence not identified · pointer only · 99766445d665fe0f · report
hierarchical_contrastive_loss in 6 papers trep.py unverified licence not identified · pointer only · 7b7612a2384a5baf · report
save_checkpoint_callback train_eval.py unverified licence not identified · pointer only · d56075a227c8e82b · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
t2v in 6 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · e4bdfc21bb19cabb · report fixture: signature tau:Tensor/2/float, f:callable/0/?, out_features:int/0/int, w:Tensor/2/float, b:Tensor/1/float, w0:Tensor/2/float, b0:Tensor/1/float, arg:Tensor/0/float · returned Tensor · level recorded 2026-09-22

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 T-Rep (graph method: T-Rep). 30 bricks; individually on a fixture: 24 ran (of which 1 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 2 violated, 9 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. TRep entry · level 0 · unverified · daa518cc4409de18
  2. TSEncoder model · level 0 · unverified · d0c784be860ebbec
  3. TembedCondPredHead helper · level 1 · ran · 070c5941256f46c5
  4. TembedDivPredHead helper · level 0 · unverified · 99766445d665fe0f
  5. centerize_vary_length_series helper · level 0 · unverified · a0b6f98fa3e2d24e
  6. hierarchical_contrastive_loss loss · level 0 · unverified · 7b7612a2384a5baf
  7. split_with_nan helper · level 1 · ran · our draft was wrong · 271f7134c2ce540e
  8. take_per_row helper · level 1 · ran; the contract check could not run (RAISES) · 629a2d0ddc05f4b5
  9. torch_pad_nan helper · level 1 · ran; the contract check could not run (RAISES) · 98da2c25852e8ec3
  10. torch_pad_with helper · level 1 · ran; the contract check could not run (RAISES) · c7b091c653c77e75
  11. DilatedConvEncoder helper · level 1 · ran · d00747ac84a3997a
  12. generate_binomial_mask helper · level 1 · ran · violated contract · fd10054ec4772b80
  13. generate_continuous_mask helper · level 1 · ran · violated contract · acda587a1d1be3bf
  14. instance_contrastive_loss loss · level 1 · ran · our draft was wrong · 9f8750cded333a83
  15. tembed_cond_pred_loss loss · level 1 · ran; the contract check could not run (RAISES) · b9dc3c835ad04449
  16. tembed_jsd_pred_loss loss · level 1 · ran; the contract check could not run (RAISES) · 132e68ed0b48e01b
  17. temporal_contrastive_loss loss · level 1 · ran · our draft was wrong · 37fd464b5f0a503b
  18. pad_nan_to_target helper · level 1 · ran · our draft was wrong · 5254eb44ce12370e
  19. ConvBlock helper · level 1 · ran · e4d4c00eca81ac32
  20. get_tembed_pred_pairs helper · level 1 · ran · our draft was wrong · 34f54041ac94d24e
  21. get_tembed_jsd_pairs helper · level 1 · ran · honoured contract · 93fd24844f87fff4
  22. torch_kl helper · level 1 · ran · our draft was wrong · d63c90fd727c9544
  23. SamePadConv helper · level 1 · ran · 1a2ed22e016a22d5
  24. GaussianPositionalEncoding model · level 1 · ran · 8ec4af15819bfd4f
  25. LearnablePositionalEncodingBig model · level 1 · ran · a18a1732e1ca752f
  26. LearnablePositionalEncodingHybrid model · level 0 · unverified · 4f9901e390aa2913
  27. LearnablePositionalEncodingSmall model · level 1 · ran · 9f1774b017ada5c2
  28. T2vCos model · level 1 · ran · f5ca3b07f6e82c2c
  29. T2vSin model · level 1 · ran · 059554668ba6727f
  30. t2v helper · level 1 · ran; the contract check could not run (RAISES) · e4bdfc21bb19cabb

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="2310.04486") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Anomaly DetectionRepresentation LearningTime Series

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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