FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines Article Swipe

PDF

Prashant Shenoy ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2512.01038

Foundation models (FMs) have opened new avenues for machine learning applications due to their ability to adapt to new and unseen tasks with minimal or no further training. Time-series foundation models (TSFMs) -- FMs trained on time-series data -- have shown strong performance on classification, regression, and imputation tasks. Recent pipelines combine TSFMs with task-specific encoders, decoders, and adapters to improve performance; however, assembling such pipelines typically requires ad hoc, model-specific implementations that hinder modularity and reproducibility. We introduce FMTK, an open-source, lightweight and extensible toolkit for constructing and fine-tuning TSFM pipelines via standardized backbone and component abstractions. FMTK enables flexible composition across models and tasks, achieving correctness and performance with an average of seven lines of code. https://github.com/umassos/FMTK

Related Topics

Truth And Reconciliation Commission Of Canada

Concepts

No concepts available.

Metadata

Type: preprint
Landing Page: http://arxiv.org/abs/2512.01038
PDF: https://arxiv.org/pdf/2512.01038
OA Status: green
OpenAlex ID: https://openalex.org/W4416958109

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416958109

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2512.01038

Digital Object Identifier
Title: FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines

Work title
Type: preprint

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-11-30

Full publication date if available
Authors: Prashant Shenoy

List of authors in order
Landing page: https://arxiv.org/abs/2512.01038

Publisher landing page
PDF URL: https://arxiv.org/pdf/2512.01038

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2512.01038

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416958109
doi	https://doi.org/10.48550/arxiv.2512.01038
ids.doi	https://doi.org/10.48550/arxiv.2512.01038
ids.openalex	https://openalex.org/W4416958109
fwci
type	preprint
title	FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language
locations[0].id	pmh:oai:arXiv.org:2512.01038
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2512.01038
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2512.01038
locations[1].id	doi:10.48550/arxiv.2512.01038
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2512.01038
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5032939724
authorships[0].author.orcid	https://orcid.org/0000-0002-5435-1901
authorships[0].author.display_name	Prashant Shenoy
authorships[0].author_position	middle
authorships[0].raw_author_name	Shenoy, Prashant
authorships[0].is_corresponding	True
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2512.01038
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-12-03T00:00:00
display_name	FMTK: A Modular Toolkit for Composable Time Series Foundation Model Pipelines
has_fulltext	False
is_retracted	False
updated_date	2025-12-03T23:12:59.920255
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2512.01038
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2512.01038
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2512.01038
primary_location.id	pmh:oai:arXiv.org:2512.01038
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2512.01038
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2512.01038
publication_date	2025-11-30
publication_year	2025
referenced_works_count	0
abstract_inverted_index.--	32, 38
abstract_inverted_index.We	77
abstract_inverted_index.ad	68
abstract_inverted_index.an	80, 111
abstract_inverted_index.no	25
abstract_inverted_index.of	113, 116
abstract_inverted_index.on	35, 43
abstract_inverted_index.or	24
abstract_inverted_index.to	12, 15, 17, 59
abstract_inverted_index.FMs	33
abstract_inverted_index.and	19, 46, 57, 75, 83, 88, 95, 104, 108
abstract_inverted_index.due	11
abstract_inverted_index.for	7, 86
abstract_inverted_index.new	5, 18
abstract_inverted_index.via	92
abstract_inverted_index.FMTK	98
abstract_inverted_index.TSFM	90
abstract_inverted_index.data	37
abstract_inverted_index.have	3, 39
abstract_inverted_index.hoc,	69
abstract_inverted_index.such	64
abstract_inverted_index.that	72
abstract_inverted_index.with	22, 53, 110
abstract_inverted_index.(FMs)	2
abstract_inverted_index.FMTK,	79
abstract_inverted_index.TSFMs	52
abstract_inverted_index.adapt	16
abstract_inverted_index.code.	117
abstract_inverted_index.lines	115
abstract_inverted_index.seven	114
abstract_inverted_index.shown	40
abstract_inverted_index.tasks	21
abstract_inverted_index.their	13
abstract_inverted_index.Recent	49
abstract_inverted_index.across	102
abstract_inverted_index.hinder	73
abstract_inverted_index.models	1, 30, 103
abstract_inverted_index.opened	4
abstract_inverted_index.strong	41
abstract_inverted_index.tasks,	105
abstract_inverted_index.tasks.	48
abstract_inverted_index.unseen	20
abstract_inverted_index.(TSFMs)	31
abstract_inverted_index.ability	14
abstract_inverted_index.avenues	6
abstract_inverted_index.average	112
abstract_inverted_index.combine	51
abstract_inverted_index.enables	99
abstract_inverted_index.further	26
abstract_inverted_index.improve	60
abstract_inverted_index.machine	8
abstract_inverted_index.minimal	23
abstract_inverted_index.toolkit	85
abstract_inverted_index.trained	34
abstract_inverted_index.adapters	58
abstract_inverted_index.backbone	94
abstract_inverted_index.flexible	100
abstract_inverted_index.however,	62
abstract_inverted_index.learning	9
abstract_inverted_index.requires	67
abstract_inverted_index.achieving	106
abstract_inverted_index.component	96
abstract_inverted_index.decoders,	56
abstract_inverted_index.encoders,	55
abstract_inverted_index.introduce	78
abstract_inverted_index.pipelines	50, 65, 91
abstract_inverted_index.training.	27
abstract_inverted_index.typically	66
abstract_inverted_index.Foundation	0
abstract_inverted_index.assembling	63
abstract_inverted_index.extensible	84
abstract_inverted_index.foundation	29
abstract_inverted_index.imputation	47
abstract_inverted_index.modularity	74
abstract_inverted_index.Time-series	28
abstract_inverted_index.composition	101
abstract_inverted_index.correctness	107
abstract_inverted_index.fine-tuning	89
abstract_inverted_index.lightweight	82
abstract_inverted_index.performance	42, 109
abstract_inverted_index.regression,	45
abstract_inverted_index.time-series	36
abstract_inverted_index.applications	10
abstract_inverted_index.constructing	87
abstract_inverted_index.open-source,	81
abstract_inverted_index.performance;	61
abstract_inverted_index.standardized	93
abstract_inverted_index.abstractions.	97
abstract_inverted_index.task-specific	54
abstract_inverted_index.model-specific	70
abstract_inverted_index.classification,	44
abstract_inverted_index.implementations	71
abstract_inverted_index.reproducibility.	76
abstract_inverted_index.https://github.com/umassos/FMTK	118
cited_by_percentile_year
corresponding_author_ids	https://openalex.org/A5032939724
countries_distinct_count	0
institutions_distinct_count	1
citation_normalized_percentile