Papers › MOMENT: A Family of Open Time-series Foundation Models

MOMENT: A Family of Open Time-series Foundation Models

6 Feb 2024arXiv:2402.03885archive 2025-07-28

Mononito Goswami, Konrad Szafer, Arjun Choudhry, Yifu Cai, Shuo Li, Artur Dubrawski

We introduce MOMENT, a family of open-source foundation models for general-purpose time series analysis. Pre-training large models on time series data is challenging due to (1) the absence of a large and cohesive public time series repository, and (2) diverse time series characteristics which make multi-dataset training onerous. Additionally, (3) experimental benchmarks to evaluate these models, especially in scenarios with limited resources, time, and supervision, are still in their nascent stages. To address these challenges, we compile a large and diverse collection of public time series, called the Time series Pile, and systematically tackle time series-specific challenges to unlock large-scale multi-dataset pre-training. Finally, we build on recent work to design a benchmark to evaluate time series foundation models on diverse tasks and datasets in limited supervision settings. Experiments on this benchmark demonstrate the effectiveness of our pre-trained models with minimal data and task-specific fine-tuning. Finally, we present several interesting empirical observations about large pre-trained time series models. Pre-trained models (AutonLab/MOMENT-1-large) and Time Series Pile (AutonLab/Timeseries-PILE) are available on Huggingface.

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 26 code samples: 25 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 26: 24 ran (of which 18 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 25 samples from 2 repositories, 23 ran (20 with no instrument failure; 3 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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.

moment-timeseries-foundation-model/moment mentioned on GitHubpytorchSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report
moment-timeseries-foundation-model/moment-research mentioned on GitHubjaxSyntology: 16 samples, 15 ran (3 instrument-failed) · 1 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

26 samples harvested: 24 ran (of which 18 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 4 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 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
19ran
2unverified

Licence: 1 of the 26 samples is 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. 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”. For 7 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.

moment-timeseries-foundation-model/moment community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
ClassificationHead in 12 papers momentfm/models/moment.py ran MIT (permissive) · 8ef9dc7505c942b4 · report fixture: returned ClassificationHead · level recorded 2026-09-22
ForecastingHead momentfm/models/moment.py ran MIT (permissive) · 5943c7631d9d3474 · report fixture: signature x:Tensor/3/float, input_mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24
Masking in 8 papers momentfm/models/moment.py ran MIT (permissive) · 6d202f0efa0f3d3b · report fixture: returned Masking · level recorded 2026-09-22
PatchEmbedding in 25 papers momentfm/models/moment.py ran MIT (permissive) · e53222338698c548 · report fixture: returned PatchEmbedding · level recorded 2026-09-22
Patching momentfm/models/moment.py ran fingerprinted MIT (permissive) · 2d07ad712507deb1 · report fixture: returned Patching · level recorded 2026-09-22
PretrainHead momentfm/models/moment.py ran MIT (permissive) · 9245a921549e45e1 · report fixture: returned PretrainHead · level recorded 2026-09-22
TASKS momentfm/models/moment.py ran MIT (permissive) · 8d65b1c504d83fc0 · report fixture: returned TASKS · level recorded 2026-09-22
TimeseriesOutputs momentfm/models/moment.py ran MIT (permissive) · bf010e749e65008d · report fixture: returned TimeseriesOutputs · level recorded 2026-09-22
MOMENT momentfm/models/moment.py unverified MIT (permissive) · ead07ddaafd6a621 · report
moment-timeseries-foundation-model/moment-research community (archive-listed) 16 samples, 15 ran (3 instrument-failed) · 1 unverified
ClassificationHead in 12 papers moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · c1c9437626597115 · report fixture: returned ClassificationHead · level recorded 2026-09-22
ForecastingHead moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · 1ebce6b5c9313e8a · report fixture: returned ForecastingHead · level recorded 2026-09-22
Masking in 8 papers moment/models/moment.py ran MIT (permissive) · e8834f0cfa23f251 · report fixture: returned Masking · level recorded 2026-09-22
NamespaceWithDefaults moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · de1f59963de469c2 · report fixture: returned NamespaceWithDefaults · level recorded 2026-09-22
PatchEmbedding in 25 papers moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · d34a07561490ed88 · report fixture: returned PatchEmbedding · level recorded 2026-09-22
Patching moment/models/moment.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · edadd0bc7dbe0ed1 · report fixture: returned Patching · 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
moment/models/moment.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 9b8f485416c59a5e · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
PretrainHead moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · 852253d6801604d3 · report fixture: returned PretrainHead · level recorded 2026-09-22
RevIN in 13 papers moment/models/moment.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 62ae5753f3455e0a · report fixture: returned RevIN · level recorded 2026-09-22
TASKS moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · 4d08cfd1aa803db7 · report fixture: returned TASKS · level recorded 2026-09-22
TimeseriesOutputs moment/models/moment.py ran · metamorphic tier: deterministic MIT (permissive) · 1f565b96bd1e4975 · report fixture: returned TimeseriesOutputs · level recorded 2026-09-22
get_anomaly_criterion moment/models/moment.py ran · our draft was wrong MIT (permissive) · 94cc1bc7a7a6995e · report fixture: signature anomaly_criterion:str/0/str · returned MSELoss · level recorded 2026-09-22
get_huggingface_model_dimensions moment/models/moment.py ran · honoured contract MIT (permissive) · d2455b534e82e3a4 · report fixture: signature model_name:str/0/str · returned int · level recorded 2026-09-22
nanstd in 13 papers
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
moment/models/moment.py ran · our draft was wrong fingerprinted MIT (permissive) · 2dcb277b78902447 · report fixture: signature tensor:Tensor/2/float, dim:NoneType/0/?, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
nanvar moment/models/moment.py ran · our draft was wrong fingerprinted MIT (permissive) · 3dc94406bdfb6cc2 · report fixture: signature tensor:Tensor/2/float, dim:NoneType/0/?, keepdim:bool/0/bool · returned Tensor · level recorded 2026-09-22
MOMENT moment/models/moment.py unverified MIT (permissive) · a4560854408474a3 · 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.
freeze_parameters repository not located ran · our draft was wrong licence of this copy not recorded · 8828556cf3cc26a1 · report fixture: signature model:callable/0/? · returned SimpleModel · 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. 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 MOMENT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for MOMENT (graph method: MOMENT). 16 bricks; individually on a fixture: 15 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MOMENT entry · level 0 · unverified · a4560854408474a3
  2. ClassificationHead model · level 1 · ran · c1c9437626597115
  3. ForecastingHead model · level 1 · ran · 1ebce6b5c9313e8a
  4. Masking helper · level 1 · ran · e8834f0cfa23f251
  5. NamespaceWithDefaults helper · level 1 · ran · de1f59963de469c2
  6. PatchEmbedding helper · level 1 · ran · d34a07561490ed88
  7. Patching helper · level 1 · ran · edadd0bc7dbe0ed1
  8. PretrainHead model · level 1 · ran · 852253d6801604d3
  9. RevIN helper · level 1 · ran · 62ae5753f3455e0a
  10. TASKS helper · level 1 · ran · 4d08cfd1aa803db7
  11. TimeseriesOutputs helper · level 1 · ran · 1f565b96bd1e4975
  12. get_anomaly_criterion helper · level 1 · ran · our draft was wrong · 94cc1bc7a7a6995e
  13. get_huggingface_model_dimensions helper · level 1 · ran · honoured contract · d2455b534e82e3a4
  14. PositionalEmbedding helper · level 1 · ran · 9b8f485416c59a5e
  15. nanstd helper · level 1 · ran · our draft was wrong · 2dcb277b78902447
  16. nanvar helper · level 1 · ran · our draft was wrong · 3dc94406bdfb6cc2

harvested Assembly for MOMENT (graph method: MOMENT). 16 bricks; individually on a fixture: 15 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. MOMENT entry · level 0 · unverified · ead07ddaafd6a621
  2. ClassificationHead model · level 1 · ran · 8ef9dc7505c942b4
  3. ForecastingHead model · level 1 · ran · 5943c7631d9d3474
  4. Masking model · level 1 · ran · 6d202f0efa0f3d3b
  5. NamespaceWithDefaults helper · level 1 · ran · de1f59963de469c2
  6. PatchEmbedding model · level 1 · ran · e53222338698c548
  7. Patching model · level 1 · ran · 2d07ad712507deb1
  8. PretrainHead model · level 1 · ran · 9245a921549e45e1
  9. RevIN model · level 1 · ran · 62ae5753f3455e0a
  10. TASKS helper · level 1 · ran · 8d65b1c504d83fc0
  11. TimeseriesOutputs helper · level 1 · ran · bf010e749e65008d
  12. freeze_parameters helper · level 1 · ran · our draft was wrong · 8828556cf3cc26a1
  13. get_anomaly_criterion helper · level 1 · ran · our draft was wrong · 94cc1bc7a7a6995e
  14. PositionalEmbedding helper · level 1 · ran · 9b8f485416c59a5e
  15. nanstd helper · level 1 · ran · our draft was wrong · 2dcb277b78902447
  16. nanvar helper · level 1 · ran · our draft was wrong · 3dc94406bdfb6cc2

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="2402.03885") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Time 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