Papers › UniTS: A Unified Multi-Task Time Series Model

UniTS: A Unified Multi-Task Time Series Model

29 Feb 2024arXiv:2403.00131archive 2025-07-28

ShangHua Gao, Teddy Koker, Owen Queen, Thomas Hartvigsen, Theodoros Tsiligkaridis, Marinka Zitnik

Although pre-trained transformers and reprogrammed text-based LLMs have shown strong performance on time series tasks, the best-performing architectures vary widely across tasks, with most models narrowly focused on specific areas, such as time series forecasting. Unifying predictive and generative time series tasks within a single model remains challenging. We introduce UniTS, a unified multi-task time series model that utilizes task tokenization to integrate predictive and generative tasks into a single framework. UniTS employs a modified transformer block to capture universal time series representations, enabling transferability from a heterogeneous, multi-domain pre-training dataset-characterized by diverse dynamic patterns, sampling rates, and temporal scales-to a wide range of downstream datasets with varied task specifications and data domains. Tested on 38 datasets across human activity sensors, healthcare, engineering, and finance, UniTS achieves superior performance compared to 12 forecasting models, 20 classification models, 18 anomaly detection models, and 16 imputation models, including adapted text-based LLMs. UniTS also demonstrates strong few-shot and prompt capabilities when applied to new domains and tasks. In single-task settings, UniTS outperforms competitive task-specialized time series models. Code and datasets are available at https://github.com/mims-harvard/UniTS.

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 28 code samples harvested from 2 repositories linked to this paper: 19 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 12 samples from 1 repository, 10 ran (10 with no instrument failure; 0 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mims-harvard/UniTS officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 9 ran (0 instrument-failed) · 7 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

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

19ran
9unverified

Licence: 0 of the 28 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

mims-harvard/UniTS official repository 16 samples, 9 ran (0 instrument-failed) · 7 unverified
CrossAttention in 85 papers models/UniTS.py ran · metamorphic tier: invariant MIT (permissive) · ef2961b050617953 · report fixture: signature x:Tensor/3/float, query:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DynamicLinear models/UniTS.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · d81cf82caf0a3c14 · report fixture: signature x:Tensor/2/float, out_features:int/0/int · returned Tensor · level recorded 2026-09-22
GateLayer models/UniTS.py ran · metamorphic tier: invariant MIT (permissive) · 18d0036b2989c343 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
LearnablePositionalEmbedding models/UniTS.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · a7720e5f169c2b3d · report fixture: signature x:Tensor/3/float, offset:int/0/int · returned Tensor · level recorded 2026-09-22
PatchEmbedding in 25 papers models/UniTS.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · acc8fc941a65797e · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-22
SeqAttBlock models/UniTS.py ran · metamorphic tier: invariant MIT (permissive) · dda0e56e79965b1b · report fixture: signature x:Tensor/4/float, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
SeqAttention models/UniTS.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 454a1cd3d3329ede · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
VarAttBlock models/UniTS.py ran · metamorphic tier: invariant MIT (permissive) · 35326016e90c28ac · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
VarAttention models/UniTS.py ran · metamorphic tier: invariant MIT (permissive) · 03d429ddb106034b · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
CLSHead models/UniTS.py unverified MIT (permissive) · d1b2155e7ac7b6df · report
DynamicLinearMlp models/UniTS.py unverified MIT (permissive) · be28d50c76414fa6 · report
ForecastHead models/UniTS.py unverified MIT (permissive) · bfe2418bb89918c9 · report
MLPBlock in 17 papers models/UniTS.py unverified MIT (permissive) · 9707fb7077958a62 · report
Model in 227 papers models/UniTS.py unverified MIT (permissive) · 1a32039eae4bf633 · report
calculate_unfold_output_length models/UniTS.py unverified MIT (permissive) · ea42266bafc13587 · report
thuml/Time-Series-Library found in paper text by Syntology 12 samples, 10 ran (0 instrument-failed) · 2 unverified
DFT_series_decomp models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · 2ab8882fbb385d83 · report fixture: returned DFT_series_decomp · level recorded 2026-09-22
DataEmbedding_wo_pos in 5 papers models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · 6a02f6d3ac9d4ea7 · report fixture: returned DataEmbedding_wo_pos · level recorded 2026-09-22
FixedEmbedding in 6 papers models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · 921d4aae41f22f16 · report fixture: returned FixedEmbedding · level recorded 2026-09-22
MultiScaleSeasonMixing models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · 125e0c04535acce1 · report fixture: returned MultiScaleSeasonMixing · level recorded 2026-09-22
Normalize in 154 papers models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · d85e5a2fd0a672ba · report fixture: returned Normalize · level recorded 2026-09-22
PastDecomposableMixing models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · 4a082cb4e49aff69 · report fixture: returned PastDecomposableMixing · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
models/TimeMixer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 5da1d16a64cf53ce · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
TemporalEmbedding in 7 papers models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · f42ba6fda711db0d · report fixture: returned TemporalEmbedding · level recorded 2026-09-22
TimeFeatureEmbedding models/TimeMixer.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 98a0817e251d19c7 · report fixture: returned TimeFeatureEmbedding · level recorded 2026-09-22
TokenEmbedding in 11 papers models/TimeMixer.py ran · metamorphic tier: deterministic MIT (permissive) · 588a4a8475ed63a0 · report fixture: returned TokenEmbedding · level recorded 2026-09-22
Model in 227 papers models/TimeMixer.py unverified MIT (permissive) · b1d72a6f113503e9 · report
MultiScaleTrendMixing models/TimeMixer.py unverified MIT (permissive) · ad047f96a9f8d71f · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for UNITS (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for UNITS (graph method: UNITS). 14 bricks; individually on a fixture: 12 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Model entry · level 0 · unverified · b1d72a6f113503e9
  2. DataEmbedding_wo_pos helper · level 1 · ran · 6a02f6d3ac9d4ea7
  3. Normalize helper · level 1 · ran · d85e5a2fd0a672ba
  4. PastDecomposableMixing helper · level 1 · ran · 4a082cb4e49aff69
  5. series_decomp helper · level 1 · ran · eb14ea186bdfc6fe
  6. PositionalEmbedding helper · level 1 · ran · 5da1d16a64cf53ce
  7. TemporalEmbedding helper · level 1 · ran · f42ba6fda711db0d
  8. TimeFeatureEmbedding helper · level 1 · ran · 98a0817e251d19c7
  9. TokenEmbedding helper · level 1 · ran · 588a4a8475ed63a0
  10. DFT_series_decomp helper · level 1 · ran · 2ab8882fbb385d83
  11. MultiScaleSeasonMixing helper · level 1 · ran · 125e0c04535acce1
  12. MultiScaleTrendMixing helper · level 0 · unverified · ad047f96a9f8d71f
  13. moving_avg helper · level 1 · ran · 262d9b037b804057
  14. FixedEmbedding helper · level 1 · ran · 921d4aae41f22f16

harvested Assembly for UNITS (graph method: UNITS). 16 bricks; individually on a fixture: 9 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; 0 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. Model entry · level 0 · unverified · 1a32039eae4bf633
  2. BasicBlock model · level 0 · unverified · d3cc5ae17d330bdd
  3. CLSHead model · level 0 · unverified · d1b2155e7ac7b6df
  4. DynamicLinear model · level 1 · ran · d81cf82caf0a3c14
  5. ForecastHead model · level 0 · unverified · bfe2418bb89918c9
  6. LearnablePositionalEmbedding model · level 1 · ran · a7720e5f169c2b3d
  7. PatchEmbedding data_transform · level 1 · ran · acc8fc941a65797e
  8. calculate_unfold_output_length helper · level 0 · unverified · ea42266bafc13587
  9. DynamicLinearMlp helper · level 0 · unverified · be28d50c76414fa6
  10. MLPBlock model · level 0 · unverified · 9707fb7077958a62
  11. SeqAttBlock model · level 1 · ran · dda0e56e79965b1b
  12. VarAttBlock model · level 1 · ran · 35326016e90c28ac
  13. CrossAttention model · level 1 · ran · ef2961b050617953
  14. GateLayer helper · level 1 · ran · 18d0036b2989c343
  15. SeqAttention helper · level 1 · ran · 454a1cd3d3329ede
  16. VarAttention helper · level 1 · ran · 03d429ddb106034b

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="2403.00131") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Anomaly DetectionImputationTime SeriesTime Series Forecastingmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Time Series Forecasting ETTh1 (336) Multivariate UniTS-ST MAE 0.422 #9 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate UniTS-ST MSE 0.405 #9 of 72 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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