SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.04486 · ICLR · 2024

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

Stéphanie Allassonnière, Archibald Fraikin, Adrien Bennetot

arXiv · PDF · Open in the Atlas

Code that ran

19 of 25 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; 1 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 10 failures of our instrument; 6 no recorded run), 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/2310.04486.json · badge: /api/ran/2310.04486.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
Let-it-Care/T-Rep canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
let-it-care/t-rep marked official in Papers with Code
Papers with Code archive
18 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
ConvBlock Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("e4d4c00eca81ac32")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

DilatedConvEncoder Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("d00747ac84a3997a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

GaussianPositionalEncoding Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("8ec4af15819bfd4f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

LearnablePositionalEncodingBig Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("a18a1732e1ca752f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

LearnablePositionalEncodingSmall Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("9f1774b017ada5c2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

T2vCos Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("f5ca3b07f6e82c2c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

T2vSin Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("059554668ba6727f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

TembedCondPredHead Ran
ran on a synthesized input
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("070c5941256f46c5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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_tembed_jsd_pairs Ran
ran, honoured the contract we drafted
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("93fd24844f87fff4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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_tembed_pred_pairs Ran
ran; our contract draft was wrong, not the code
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("34f54041ac94d24e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

instance_contrastive_loss Ran
ran; our contract draft was wrong, not the code
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("9f8750cded333a83")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

t2v Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from ojus1/Time2Vec-PyTorch
pointer only · get_code("e4bdfc21bb19cabb")
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.

take_per_row Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("629a2d0ddc05f4b5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

tembed_cond_pred_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("b9dc3c835ad04449")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

tembed_jsd_pred_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("132e68ed0b48e01b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

temporal_contrastive_loss Ran
ran; our contract draft was wrong, not the code
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("37fd464b5f0a503b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

torch_kl Ran
ran; our contract draft was wrong, not the code
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("d63c90fd727c9544")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

torch_pad_nan Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("98da2c25852e8ec3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

torch_pad_with Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("c7b091c653c77e75")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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.

LearnablePositionalEncodingHybrid Not yet run
unverified (harvested, no recorded run)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("4f9901e390aa2913")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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. No invocation recorded.

TRep Not yet run
unverified (harvested, no recorded run)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("daa518cc4409de18")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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. No invocation recorded.

TSEncoder Not yet run
unverified (harvested, no recorded run)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("d0c784be860ebbec")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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. No invocation recorded.

TembedDivPredHead Not yet run
unverified (harvested, no recorded run)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("99766445d665fe0f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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. No invocation recorded.

hierarchical_contrastive_loss Not yet run
unverified (harvested, no recorded run)
let-it-care/t-rep/trep.py
pointer only (licence: NOASSERTION) · get_code("7b7612a2384a5baf")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, let-it-care/t-rep (NOASSERTION). 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. No invocation recorded.

save_checkpoint_callback Not yet run
unverified (harvested, no recorded run)
Let-it-Care/T-Rep/train_eval.py
pointer only (licence: NOASSERTION) · get_code("d56075a227c8e82b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, Let-it-Care/T-Rep (NOASSERTION). 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. No invocation recorded.

Also present in other papers' code

Of 25 samples lifted from this paper's linked repositories, 25 carry a function identity and 0 do not. Of the 25 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 3 the same month, 2 later) and 21 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
ConvBlock
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 1 the same month, 2 later · 1 only as an assembly brick
2309.13378 (2023-09)
Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment
2310.14017 (2023-10)
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
2601.07550 (2026-01)
TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
and 1 more not named here
DilatedConvEncoder
brick of this paper's assembly: helper
3 other papers
1 the same month, 2 later · 1 only as an assembly brick
2310.14017 (2023-10)
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
2601.07550 (2026-01)
TFEC: Multivariate Time-Series Clustering via Temporal-Frequency Enhanced Contrastive Learning
2606.13277 (2026-06)
ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization
t2v
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1907.05321 (2019-07)
Time2Vec: Learning a Vector Representation of Time
take_per_row
brick of this paper's assembly: helper
1 other paper
1 the same month
2310.14017 (2023-10)
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

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

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.

For agents

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

get_harvested_code_for_paper("2310.04486")
get_code_for_paper("2310.04486")
have("2310.04486")

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

curl https://syntology.ai/api/ran/2310.04486.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.04486.svg)](https://syntology.ai/paper/2310.04486)

Connect an agent — have() is free.