Papers › TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis

TOTEM: TOkenized Time Series EMbeddings for General Time Series Analysis

26 Feb 2024arXiv:2402.16412archive 2025-07-28

Sabera Talukder, Yisong Yue, Georgia Gkioxari

This work studies the problem of time series analysis with generalist (or foundation) models, which are models trained across many data domains. Drawing inspiration from the widespread success of large language models, we consider the simple strategy of discretely tokenizing time series data drawn from a myriad of datasets via self-supervision, then using the fixed tokenization to solve a variety of tasks across many data domains. Canonically, time series models are either trained on a single dataset or built in a task-specific manner (e.g., a forecasting-only model), where many use patches of time as inputs to the model. As such, performant generalist, discrete representation time series models explored across many tasks are of value. Our method, TOkenized Time Series EMbeddings (TOTEM), produces such generalist time series models with minimal or no fine-tuning while exhibiting strong zero-shot performance. We evaluate TOTEM extensively over nearly 500 experiments on three commonly-studied time series tasks with real-world data: imputation (17 baselines, 12 datasets), anomaly detection (19 baselines, 25 datasets), and forecasting (14 baselines, 12 datasets). We conclude that TOTEM matches or outperforms existing state-of-the-art models in both the canonical specialist setting (i.e., training one model on one domain) as well as the generalist setting (i.e., training a single model on many domains), which demonstrates the efficacy of tokenization for general time series analysis. The open-source implementation is available here: https://github.com/SaberaTalukder/TOTEM; a video summary is available here: https://www.youtube.com/watch?v=OqrCpdb6MJk.

PaperPDFCodeCode Syntology ran

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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (9 with no instrument failure; 2 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

saberatalukder/totem officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 11 ran (2 instrument-failed) · 2 unverified report
WenjieDu/PyPOTS pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (arXiv:2012.07436; that paper's own run record: 62 ran (of which 53 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified), Multi-Time Attention Networks for Irregularly Sampled Time Series (arXiv:2101.10318; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified) and 5 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
9ran
2unverified

Licence: 13 of the 13 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 saberatalukder/totem. “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.

saberatalukder/totem official repository 13 samples, 11 ran (2 instrument-failed) · 2 unverified
codes2time forecasting/extract_forecasting_data.py ran no licence file found · pointer only · 55dfde0d12235653 · report fixture: signature code_ids:Tensor/3/int, codebook:Tensor/2/float, compression_factor:int/0/int, vqvae_decoder:callable/0/?, revin_layer:callable/0/? · returned tuple · level recorded 2026-09-24
codes2timerevin anomaly_detection/detect_anomaly.py ran no licence file found · pointer only · cb77fdb4a1e324c7 · report fixture: signature code_ids:Tensor/3/int, codebook:Tensor/2/float, compression_factor:int/0/int, vqvae_decoder:callable/0/? · returned Tensor · level recorded 2026-09-24
create_datloaders anomaly_detection/detect_anomaly.py ran no licence file found · pointer only · 762b2be39fdadf5a · report fixture: signature batchsize:int/0/int, dataset:str/0/str, base_path:str/0/str, labels_path:str/0/str · returned tuple · level recorded 2026-09-24
create_datloaders anomaly_detection/train_vqvae.py ran no licence file found · pointer only · b5c7d28a17f662a4 · report fixture: signature batchsize:int/0/int, dataset:str/0/str, base_path:str/0/str · returned tuple · level recorded 2026-09-24
create_time_series_dataloader forecasting/generalist_eval.py ran no licence file found · pointer only · 1a119a859ec7ea04 · report fixture: signature datapath:str/0/str, batchsize:int/0/int · returned dict · level recorded 2026-09-24
get_params in 53 papers forecasting/generalist_eval.py ran · our draft was wrong no licence file found · pointer only · 96092138a8882ebc · report fixture: signature data_type:str/0/str, data_path:str/0/str · returned dict · level recorded 2026-09-24
load_and_flatten anomaly_detection/combine_datasets.py ran · our draft was wrong no licence file found · pointer only · af1552f9da41a7cc · report fixture: signature folder:str/0/str, args:Args/0/? · returned tuple · level recorded 2026-09-24
load_and_flatten anomaly_detection/combine_labels.py ran no licence file found · pointer only · 7302b9f7263f76d0 · report fixture: signature folder:str/0/str, args:Args/0/?, num_sensor:int/0/int · returned ndarray · level recorded 2026-09-24
revintime2codes anomaly_detection/detect_anomaly.py ran no licence file found · pointer only · 67b566e76ba373ba · report fixture: signature revin_data:Tensor/3/float, compression_factor:int/0/int, vqvae_encoder:callable/0/?, vqvae_quantizer:callable/0/? · returned tuple · level recorded 2026-09-24
save_data anomaly_detection/save_chunked_data.py ran no licence file found · pointer only · 92447a783743bb61 · report fixture: signature data_set:list/1/tuple, args:Args/0/?, save_labels:bool/0/bool · returned tuple · level recorded 2026-09-24
time2codes forecasting/extract_forecasting_data.py ran no licence file found · pointer only · 99487b1b03cba02c · report fixture: signature revin_data:Tensor/3/float, compression_factor:int/0/int, vqvae_encoder:callable/0/?, vqvae_quantizer:callable/0/? · returned tuple · level recorded 2026-09-24
inference in 65 papers forecasting/generalist_eval.py unverified no licence file found · pointer only · 7b15d87455a71d97 · report
train_model in 103 papers anomaly_detection/train_vqvae.py unverified no licence file found · pointer only · b299340c6f48dc63 · report

Tasks

Anomaly DetectionImputationTime SeriesTime Series Analysis

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