SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.23663 · 2026

Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning

Zheng Chen, Yasuko Matsubara, Yasushi Sakurai, Kohei Obata, Taichi Murayama

arXiv · PDF · Open in the Atlas

Code that ran

15 of 19 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; 5 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2602.23663.json · badge: /api/ran/2602.23663.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
KoheiObata/MoST canonical (classifier label)
classifier basis: census
15 ran · 4 no recorded run
FunctionStatusWhere it lives
cal_metrics Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/tasks/forecasting.py
pointer only (licence: NONE) · get_code("a4750195b8805692")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

contrastive_loss Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/models/losses.py
pointer only (licence: NONE) · get_code("af74d156c2e5a696")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

ex_range Ran
ran, honoured the contract we drafted
KoheiObata/MoST/models/losses.py
pointer only (licence: NONE) · get_code("de6d260fcaa1a258")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

fit_knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KoheiObata/MoST/tasks/_eval_protocols.py
pointer only (licence: NONE) · get_code("befe203f4fa96ee5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

fit_svm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KoheiObata/MoST/tasks/_eval_protocols.py
pointer only (licence: NONE) · get_code("fbbc32593fb6aa88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

genInvCov Ran
ran, honoured the contract we drafted
KoheiObata/MoST/datasets/generate.py
pointer only (licence: NONE) · get_code("2af7d33ef64535ef")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

genInvCov_rectangle Ran
ran, honoured the contract we drafted
KoheiObata/MoST/datasets/generate.py
pointer only (licence: NONE) · get_code("12cee97a6422f609")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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_area Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/utils_tensor.py
pointer only (licence: NONE) · get_code("b0e4a2bfe8a035f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

instance_loss Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/models/losses.py
pointer only (licence: NONE) · get_code("088d29a95cbc6a8b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

load_google_data Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/utils_tensor.py
pointer only (licence: NONE) · get_code("c3f8106c7e9ea78f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

nan_to_zero Ran
ran, honoured the contract we drafted
KoheiObata/MoST/tasks/forecasting.py
pointer only (licence: NONE) · get_code("006e96babc62edf9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

nonlinear_trend Ran
ran, honoured the contract we drafted
KoheiObata/MoST/datasets/generate.py
pointer only (licence: NONE) · get_code("89ca6450d1c2cfde")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

pad_nan_to_target Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/utils.py
pointer only (licence: NONE) · get_code("5254eb44ce12370e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

pkl_load Ran
ran; our contract draft was wrong, not the code
KoheiObata/MoST/utils.py
pointer only (licence: NONE) · get_code("645d1fdb1dc0e80c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

torch_pad_nan Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KoheiObata/MoST/utils.py
pointer only (licence: NONE) · get_code("79783deb10f33397")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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.

eval_classification Not yet run
unverified (harvested, no recorded run)
KoheiObata/MoST/tasks/classification.py
pointer only (licence: NONE) · get_code("0839a317b7309e63")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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. No invocation recorded.

fit_lr Not yet run
unverified (harvested, no recorded run)
KoheiObata/MoST/tasks/_eval_protocols.py
pointer only (licence: NONE) · get_code("2309c20a08ac1773")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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. No invocation recorded.

generate_pred_samples Not yet run
unverified (harvested, no recorded run)
KoheiObata/MoST/tasks/forecasting.py
pointer only (licence: NONE) · get_code("63e193a1a856ae88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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. No invocation recorded.

time_features Not yet run
unverified (harvested, no recorded run)
KoheiObata/MoST/utils_tensor.py
pointer only (licence: NONE) · get_code("081ecd2bf3fa858a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KoheiObata/MoST 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. No invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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
pad_nan_to_target 7 other papers
7 dated earlier · 1 only as an assembly brick
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2202.01575 (2022-02)
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
2310.04486 (2023-10)
T-Rep: Representation Learning for Time Series using Time-Embeddings
and 4 more not named here
pkl_load 6 other papers
6 dated earlier
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2202.01575 (2022-02)
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
2311.11235 (2023-11)
Unraveling the "Anomaly" in Time Series Anomaly Detection: A Self-supervised Tri-domain Solution
and 3 more not named here
torch_pad_nan 6 other papers
6 dated earlier
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2202.01575 (2022-02)
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
2310.14017 (2023-10)
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
and 3 more not named here
cal_metrics 2 other papers
2 dated earlier
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2202.01575 (2022-02)
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
fit_knn 2 other papers
2 dated earlier
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2310.14017 (2023-10)
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
fit_lr 2 other papers
2 dated earlier
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2310.14017 (2023-10)
Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series
generate_pred_samples 2 other papers
2 dated earlier
2106.10466 (2021-06)
TS2Vec: Towards Universal Representation of Time Series
2202.01575 (2022-02)
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

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

Multi-mode tensor time series (TTS) can be found in many domains, such as search engines and environmental monitoring systems. Learning representations of a TTS benefits various applications, but it is also challenging since the complexities inherent in the tensor hinder the realization of rich representations. In this paper, we propose a novel representation learning method designed specifically for TTS, namely MoST. Specifically, MoST uses a tensor slicing approach to reduce the complexity of the TTS structure and learns representations that can be disentangled into individual non-temporal modes. Each representation captures mode-specific features, which are the relationship between variables within the same mode, and mode-invariant features, which are in common in representations of different modes. We employ a contrastive learning framework to learn parameters; the loss function comprises two parts intended to learn representation in a mode-specific way and mode-invariant way, effectively exploiting disentangled representations as augmentations. Extensive experiments on real-world datasets show that MoST consistently outperforms the state-of-the-art methods in terms of classification and forecasting accuracy. Code is available at https://github.com/KoheiObata/MoST.

For agents

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

get_harvested_code_for_paper("2602.23663")
get_code_for_paper("2602.23663")
have("2602.23663")

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

curl https://syntology.ai/api/ran/2602.23663.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.23663.svg)](https://syntology.ai/paper/2602.23663)

Connect an agent — have() is free.