Papers › Chronos: Learning the Language of Time Series

Chronos: Learning the Language of Time Series

12 Mar 2024arXiv:2403.07815archive 2025-07-28

Abdul Fatir Ansari, Lorenzo Stella, Caner Turkmen, Xiyuan Zhang, Pedro Mercado, Huibin Shen, Oleksandr Shchur, Syama Sundar Rangapuram, Sebastian Pineda Arango, Shubham Kapoor, Jasper Zschiegner, Danielle C. Maddix, Hao Wang, Michael W. Mahoney, Kari Torkkola, Andrew Gordon Wilson, Michael Bohlke-Schneider, Yuyang Wang

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss. We pretrained Chronos models based on the T5 family (ranging from 20M to 710M parameters) on a large collection of publicly available datasets, complemented by a synthetic dataset that we generated via Gaussian processes to improve generalization. In a comprehensive benchmark consisting of 42 datasets, and comprising both classical local models and deep learning methods, we show that Chronos models: (a) significantly outperform other methods on datasets that were part of the training corpus; and (b) have comparable and occasionally superior zero-shot performance on new datasets, relative to methods that were trained specifically on them. Our results demonstrate that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks, positioning pretrained models as a viable tool to greatly simplify forecasting pipelines.

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 28 code samples harvested from 3 repositories linked to this paper: 23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 5 honoured, 1 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (6 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 19 samples from 2 repositories, 15 ran (13 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 23 samples that ran have no recorded date.

SalesforceAIResearch/uni2ts officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series (arXiv:2510.20273; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
amazon-science/chronos-forecasting officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 8 ran (2 instrument-failed) · 1 unverified report
ChernovAndrey/chronos-forecasting-wasserstein mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
mobile-sensing-and-ubicomp-laboratory/normwear mentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 13 ran (2 instrument-failed) · 4 unverified report
zechenli03/sensorllm mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ACL Anthology id 2025.emnlp-main.19 (that paper's own run record: 0 ran · 6 unverified); nothing checks that they implement this paper's method. report
etna-team/etna pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Time-Series Representation Learning via Temporal and Contextual Contrasting (arXiv:2106.14112; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); 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

28 samples harvested: 23 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 5 honoured, 1 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 5 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.

5ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
3ran; the contract check could not run
13ran
5unverified

Licence: 5 of the 28 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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”. “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.

amazon-science/chronos-forecasting official repository 9 samples, 8 ran (2 instrument-failed) · 1 unverified
from_list_of_tensors src/chronos/chronos2/preprocess.py ran · our draft was wrong Apache-2.0 (permissive) · df6b398cd625b6ca · report fixture: signature data:list/1/Tensor, prediction_length:int/0/int · returned list · level recorded 2026-09-24
from_tensor src/chronos/chronos2/preprocess.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 320651b2368cae7e · report fixture: signature data:Tensor/3/float, prediction_length:int/0/int · returned list · level recorded 2026-09-24
infer_freq_from_df src/chronos/df_utils.py ran Apache-2.0 (permissive) · 6f9f1492b3e8c060 · report fixture: signature df:DataFrame/0/?, id_column:str/0/str, timestamp_column:str/0/str · returned str · level recorded 2026-09-24
interpolate_quantiles src/chronos/utils.py ran Apache-2.0 (permissive) · 6570164cb0997c3c · report fixture: signature query_quantile_levels:list/1/float, original_quantile_levels:list/1/float, original_values:Tensor/2/float · returned Tensor · level recorded 2026-09-24
left_pad_and_cat_2D src/chronos/chronos2/dataset.py ran · honoured contract Apache-2.0 (permissive) · be1b4be52aeb0521 · report fixture: signature tensors:list/1/Tensor · returned Tensor · level recorded 2026-09-24
left_pad_and_stack_1D src/chronos/utils.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 29cf01d44829ae99 · report fixture: signature tensors:list/1/Tensor · returned Tensor · level recorded 2026-09-25
make_future_df src/chronos/df_utils.py ran Apache-2.0 (permissive) · 01e3ac35c7607e05 · report fixture: signature df:DataFrame/0/?, prediction_length:int/0/int, freq:NoneType/0/?, id_column:str/0/str, timestamp_column:str/0/str · returned DataFrame · level recorded 2026-09-24
normalize_df src/chronos/df_utils.py ran Apache-2.0 (permissive) · cb5df9cb2cc3d661 · report fixture: signature df:DataFrame/0/?, id_column:str/0/str, timestamp_column:str/0/str, order:ndarray/1/<U1 · returned DataFrame · level recorded 2026-09-24
weighted_quantile in 5 papers src/chronos/utils.py unverified Apache-2.0 (permissive) · 1a9eb49448571307 · report
ChernovAndrey/chronos-forecasting-wasserstein community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
check_nan in 6 papers scripts/preprocessing_training_data/zero_shot_datasets.py ran · honoured contract Apache-2.0 (permissive) · 3963a392d702ebd5 · report fixture: signature df:DataFrame/0/? · returned tuple · level recorded 2026-09-22
extract_target_from_extra_datasets scripts/preprocessing_training_data/zero_shot_datasets.py ran · honoured contract Apache-2.0 (permissive) · 7bcb6ba4a8212388 · report fixture: signature ds:MockDataset/0/? · returned ndarray · level recorded 2026-09-22
mobile-sensing-and-ubicomp-laboratory/normwear community (archive-listed) 17 samples, 13 ran (2 instrument-failed) · 4 unverified
adjust_learning_rate in 125 papers modules/lr_sched.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · bd3578806ecf5ac2 · report fixture: signature optimizer:SGD/0/?, epoch:int/0/int, args:Args/0/? · returned float · level recorded, date not recorded
butter_bandpass_filter in 8 papers modules/signal_preprocess.py ran Apache-2.0 (permissive) · 98c7e5db66c62dee · report fixture: signature data:ndarray/1/float, lowcut:float/0/float, highcut:float/0/float, fs:float/0/float, order:int/0/int · returned ndarray · level recorded 2026-09-24
cwt_ricker modules/normwear.py ran Apache-2.0 (permissive) · b96b8312d8a5918f · report fixture: signature x:Tensor/2/float, lowest_scale:float/0/float, largest_scale:float/0/float, step:float/0/float, wavelet_len:int/0/int · returned Tensor · level recorded 2026-09-24
extract_stat_features downstream_pipeline/model_apis.py ran Apache-2.0 (permissive) · 3328b1e2a64383ba · report fixture: signature ts:ndarray/1/float, sampling_rate:int/0/int · returned list · level recorded 2026-09-24
freeze_model in 12 papers downstream_pipeline/model_apis.py ran Apache-2.0 (permissive) · 7350d8fc12462db1 · report fixture: signature model:callable/0/? · returned SimpleModel · level recorded 2026-09-24
get_1d_sincos_pos_embed_from_grid in 75 papers
census: 8 implementations from 17 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 1, kind float, dtype float32
modules/layers.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) here; the stored copy is pointer only · 5c8ea92d43ead77d · report fixture: signature embed_dim:int/0/int, pos:ndarray/1/float · returned ndarray · level recorded 2026-09-22
get_2d_sincos_pos_embed_flexible in 6 papers modules/layers.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 68fc090d0a502993 · report fixture: signature embed_dim:int/0/int, grid_size:tuple/1/int, cls_token:bool/0/bool · returned ndarray · level recorded 2026-09-24
impute modules/signal_preprocess.py ran fingerprinted Apache-2.0 (permissive) · 12a7b65c0afc67bd · report fixture: signature ts:ndarray/1/float, sr:int/0/int, tr:int/0/int · returned ndarray · level recorded 2026-09-24
parse_tuple in 34 papers downstream_pipeline/main_finetune.py ran Apache-2.0 (permissive) · 13fd40ad9b57200f · report fixture: signature arg_str:str/0/str · returned tuple · level recorded 2026-09-24
ricker_wavelet modules/normwear.py ran Apache-2.0 (permissive) · 8341801558fc0c56 · report fixture: signature points:int/0/int, scale:Tensor/0/float · returned Tensor · level recorded 2026-09-24
rolling_window in 16 papers modules/signal_preprocess.py ran fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 895ca4b776fb6d6d · report fixture: signature a:ndarray/2/float, window:int/0/int · returned ndarray · level recorded 2026-09-25
str2bool in 533 papers downstream_pipeline/main_finetune.py ran · violated contract Apache-2.0 (permissive) · 7c508037b40522af · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
unfreeze_model downstream_pipeline/model_apis.py ran Apache-2.0 (permissive) · c06c4fafc2597d4c · report fixture: signature model:callable/0/? · returned SimpleModel · level recorded 2026-09-24
cwt_wrap modules/normwear.py unverified Apache-2.0 (permissive) · 20465878e703999d · report
get_2d_sincos_pos_embed_from_grid in 140 papers modules/layers.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 2884deadbb637c3e · report
spec_cwt main_model.py unverified Apache-2.0 (permissive) · f2ab8ea7178a9e19 · report
wt main_model.py unverified Apache-2.0 (permissive) · ea3c205b7dee4a25 · report

Tasks

Gaussian ProcessesLanguage ModelingLanguage ModellingQuantizationTime Series

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdafactorAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5

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