SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.00620 · 2026

Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference

Ruichu Cai, Yuming Liu, Themis Palpanas, Zijian Li, Lujia Pan, Shifeng Xie, Keli Zhang, Juntao Fang, Shengbin Nie, Yuhui Ling

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; 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/2602.00620.json · badge: /api/ran/2602.00620.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
fangjuntao/TIC-FM canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
default Ran
ran, violated the contract we drafted
fangjuntao/TIC-FM/src/TIC/model/rope.py
pointer only (licence: NONE); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fangjuntao/TIC-FM 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.

exists Ran
ran, violated the contract we drafted
fangjuntao/TIC-FM/src/TIC/model/rope.py
pointer only (licence: NONE); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fangjuntao/TIC-FM 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.

sdpa_with_flattened_batch Ran
ran; our contract draft was wrong, not the code
fangjuntao/TIC-FM/src/TIC/model/attention.py
pointer only (licence: NONE); the stored copy get_code serves, from fangjuntao/ChorusTIC, is pointer only (licence: NONE) · get_code("fa8166d67efadbad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fangjuntao/TIC-FM 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.

broadcat Not yet run
unverified (harvested, no recorded run)
fangjuntao/TIC-FM/src/TIC/model/rope.py
pointer only (licence: NONE) · get_code("7980b84775918f4a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fangjuntao/TIC-FM 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.

encode_with_TSEncoder Not yet run
unverified (harvested, no recorded run)
fangjuntao/TIC-FM/src/TIC/model/TSEncoder_adapter_icl.py
pointer only (licence: NONE) · get_code("de9762a52d7ba4bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, fangjuntao/TIC-FM 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 3 later) and 1 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
exists 486 other papers
468 dated earlier, 7 the same month, 9 later, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
159 dated earlier, 2 the same month, 1 later, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
broadcat 4 other papers
4 dated earlier
2212.10554 (2022-12)
A Length-Extrapolatable Transformer
2402.04324 (2024-02)
ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation
2504.13181 (2025-04)
Perception Encoder: The best visual embeddings are not at the output of the network
and 1 more not named here
sdpa_with_flattened_batch 2 other papers
2 later
2606.07345 (2026-06)
TABSWIFT: An Efficient Tabular Foundation Model with Row-Wise Attention
2608.24033 (2026-08)
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning

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

The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice violates the training-free premise of zero-shot deployment and introduces evaluation bias due to classifierdependent training choices. To address this issue, we propose TIC-FM, an in-context learning framework that treats the labeled training set as context and predicts labels for all test instances in a single forward pass, without parameter updates. TIC-FM pairs a time series encoder and a lightweight projection adapter with a splitmasked latent memory Transformer. We further provide theoretical justification that in-context inference can subsume trained classifiers and can emulate gradient-based classifier training within a single forward pass. Experiments on 128 UCR datasets show strong accuracy, with consistent gains in the extreme low-label situation, highlighting training-free transfer for time series classification.The source code is publicly available at https://github.com/fangjuntao/TIC-FM.

For agents

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

get_harvested_code_for_paper("2602.00620")
get_code_for_paper("2602.00620")
have("2602.00620")

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

curl https://syntology.ai/api/ran/2602.00620.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.00620.svg)](https://syntology.ai/paper/2602.00620)

Connect an agent — have() is free.