SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.10093 · 2024

LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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; 6 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 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/2405.10093.json · badge: /api/ran/2405.10093.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
stijnverdenius/lat-pfn canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
V_denormalize Ran
ran, honoured the contract we drafted
stijnverdenius/lat-pfn/util/config_util.py
pointer only (licence: CC-BY-4.0) · get_code("bb43c29130d4c0c8")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

V_normalize Ran
ran, honoured the contract we drafted
stijnverdenius/lat-pfn/util/config_util.py
pointer only (licence: CC-BY-4.0) · get_code("49789c26ba814b17")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

add_attention_hook Ran
ran; our contract draft was wrong, not the code
stijnverdenius/lat-pfn/util/metrics.py
pointer only (licence: CC-BY-4.0) · get_code("a5be36f76effc4c7")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

causal_expanded_mask Ran
ran, honoured the contract we drafted
stijnverdenius/lat-pfn/model/base_pfn.py
pointer only (licence: CC-BY-4.0) · get_code("eb1d613c4a721aab")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

diagonal_mask Ran
ran, honoured the contract we drafted
stijnverdenius/lat-pfn/model/base_pfn.py
pointer only (licence: CC-BY-4.0) · get_code("019d7b7f3ec8da25")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

expand_diagonal Ran
ran, honoured the contract we drafted
stijnverdenius/lat-pfn/model/base_pfn.py
pointer only (licence: CC-BY-4.0) · get_code("f3d2c5acfad15121")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

fig2img Ran
ran, honoured the contract we drafted
stijnverdenius/lat-pfn/util/metrics.py
pointer only (licence: CC-BY-4.0) · get_code("0c10ac60c21bd3ce")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

init_method_normal Ran
ran; our contract draft was wrong, not the code
stijnverdenius/lat-pfn/model/mup_imp/mup_custom.py
pointer only (licence: CC-BY-4.0) · get_code("bc31f24735c30432")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

initialize_loader Ran
ran; our contract draft was wrong, not the code
stijnverdenius/lat-pfn/evaluation/real_eval.py
pointer only (licence: CC-BY-4.0) · get_code("55930a3f1525056f")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

mup_multi_head_attention_forward Ran
ran on a synthesized input
stijnverdenius/lat-pfn/model/mup_imp/mup_custom.py
pointer only (licence: CC-BY-4.0) · get_code("0f7ead92423c5cbc")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

dictify Not yet run
unverified (harvested, no recorded run)
stijnverdenius/lat-pfn/util/config_util.py
pointer only (licence: CC-BY-4.0) · get_code("17d9f42249274807")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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.

plot Not yet run
unverified (harvested, no recorded run)
stijnverdenius/lat-pfn/util/metrics.py
pointer only (licence: CC-BY-4.0) · get_code("8ea068c039e9397f")
How it ran

The body of this sample is withheld: CC-BY-4.0, as GitHub detects it on this paper's repository, stijnverdenius/lat-pfn, is not in the permissive set Syntology serves inline. 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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.

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

We introduce LatentTimePFN (LaT-PFN), a foundational Time Series model with a strong embedding space that enables zero-shot forecasting. To achieve this, we perform in-context learning in latent space utilizing a novel integration of the Prior-data Fitted Networks (PFN) and Joint Embedding Predictive Architecture (JEPA) frameworks. We leverage the JEPA framework to create a prediction-optimized latent representation of the underlying stochastic process that generates time series and combines it with contextual learning, using a PFN. Furthermore, we improve on preceding works by utilizing related time series as a context and introducing a normalized abstract time axis. This reduces training time and increases the versatility of the model by allowing any time granularity and forecast horizon. We show that this results in superior zero-shot predictions compared to established baselines. We also demonstrate our latent space produces informative embeddings of both individual time steps and fixed-length summaries of entire series. Finally, we observe the emergence of multi-step patch embeddings without explicit training, suggesting the model actively learns discrete tokens that encode local structures in the data, analogous to vision transformers.

For agents

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

get_harvested_code_for_paper("2405.10093")
get_code_for_paper("2405.10093")
have("2405.10093")

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

curl https://syntology.ai/api/ran/2405.10093.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.10093.svg)](https://syntology.ai/paper/2405.10093)

Connect an agent — have() is free.