SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.11939 · NeurIPS · 2023

One Fits All: Power General Time Series Analysis by Pretrained LM

Tian Zhou, Xue Wang, Peisong Niu, Sun Liang, Jin Rong

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2302.11939.json · badge: /api/ran/2302.11939.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
liaoyuhua/GPT-TS community
Papers with Code archive
5 ran · 1 no recorded run
damo-di-ml/one_fits_all alias (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
damo-di-ml/neurips2023-one-fits-all community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input · constructed an object; no result was computed
liaoyuhua/GPT-TS/src/model.py
pointer only (licence: NONE) · get_code("283abdbdd3b3be9d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liaoyuhua/GPT-TS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

CausalSelfAttention Ran
ran on a synthesized input · constructed an object; no result was computed
liaoyuhua/GPT-TS/src/model.py
pointer only (licence: NONE) · get_code("ad66bcf4514af931")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liaoyuhua/GPT-TS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

FlattenHead Ran
ran on a synthesized input · constructed an object; no result was computed
liaoyuhua/GPT-TS/src/model.py
pointer only (licence: NONE) · get_code("22bc376d349bfa99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liaoyuhua/GPT-TS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GPT4TS Ran
ran on a synthesized input · constructed an object; no result was computed
damo-di-ml/one_fits_all/Long-term_Forecasting/models/GPT4TS.py
pointer only (licence: NONE) · get_code("f7b3ba88e01c955b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, damo-di-ml/one_fits_all when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

PoolingHead Ran
ran on a synthesized input · constructed an object; no result was computed
liaoyuhua/GPT-TS/src/model.py
pointer only (licence: NONE) · get_code("8218db7b8802c1ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liaoyuhua/GPT-TS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RevIN Ran
ran on a synthesized input · constructed an object; no result was computed
liaoyuhua/GPT-TS/src/model.py
pointer only (licence: NONE) · get_code("15bf8037c337e5d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liaoyuhua/GPT-TS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GPT2TS Not yet run
unverified (harvested, no recorded run)
liaoyuhua/GPT-TS/src/model.py
pointer only (licence: NONE) · get_code("f5ab1a373dfe173b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, liaoyuhua/GPT-TS when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

gpt4ts Not yet run
unverified (harvested, no recorded run)
damo-di-ml/neurips2023-one-fits-all/Classification/src/models/gpt4ts.py
pointer only (licence: NONE) · get_code("784ad185e9363327")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, damo-di-ml/neurips2023-one-fits-all when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
FlattenHead
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2310.04948 (2023-10)
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
PoolingHead
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2310.04948 (2023-10)
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series analysis. Unlike NLP and CV where a unified model can be used to perform different tasks, specially designed approach still dominates in each time series analysis task such as classification, anomaly detection, forecasting, and few-shot learning. The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from billions of tokens, for time series analysis. Specifically, we refrain from altering the self-attention and feedforward layers of the residual blocks in the pre-trained language or image model. This model, known as the Frozen Pretrained Transformer (FPT), is evaluated through fine-tuning on all major types of tasks involving time series. Our results demonstrate that pre-trained models on natural language or images can lead to a comparable or state-of-the-art performance in all main time series analysis tasks, as illustrated in Figure 1. We also found both theoretically and empirically that the self-attention module behaviors similarly to principle component analysis (PCA), an observation that helps explains how transformer bridges the domain gap and a crucial step towards understanding the universality of a pre-trained transformer. The code is publicly available at https://github.com/DAMO-DI-ML/One_Fits_All.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.11939")
get_code_for_paper("2302.11939")
have("2302.11939")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.11939.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.11939.svg)](https://syntology.ai/paper/2302.11939)

Connect an agent — have() is free.