SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.04442 · 2024

TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 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/2410.04442.json · badge: /api/ran/2410.04442.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
hank0626/timebridge canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
CORR Ran
ran, violated the contract we drafted
hank0626/timebridge/utils/metrics.py
code served (permissive licence) · get_code("03d63d172032b256")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float32, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small numpy arrays for pred and true
# CORR expects 2D arrays where it computes correlation across the first dimension
# Using distinct sizes: batch=2, features=4
np.random.seed(0)
pred = np.random.randn(2, 4).astype(np.float32)
true = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "pred": pred,
    "true": true
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float32, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
PeriodNorm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hank0626/timebridge/layers/Transformer_EncDec.py
code served (permissive licence) · get_code("825425c76db1d77d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 12) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a 3D tensor input: (batch=2, channels=4, time_steps=12)
# The function expects either 3D or 4D tensors
# For 3D input, it will unsqueeze to add a dimension
x_3d = torch.randn(2, 4, 12)

# Alternative: create a 4D tensor: (batch=2, channels=4, n=3, time_steps=12)
x_4d = torch.randn(2, 4, 3, 12)

# period_len parameter - must be smaller than time dimension for valid indexing
period_len = 6

ARGS = {
    'x': x_3d,
    'period_len': period_len
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 12) — shape (2, 4, 12) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
denormalization Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hank0626/timebridge/layers/Embed.py
code served (permissive licence) · get_code("ebab5ccedc5c9abe")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - x: tensor with shape (B, D, L) - used with .shape and indexing
# - mean: tensor with shape (B, D_mean, L_mean) - used with .shape[-1] and indexing
# - std: tensor with shape (B, D_std, L_std) - used with indexing

# The function expects:
# B (batch size) = 2
# D (feature dimension) = 4
# L (sequence length) = 5
# mean.shape[-1] should be checked (1 or L)
# mean and std should have compatible shapes for indexing [:, :D, ...]

B = 2
D = 4
L = 5

# Create x tensor: (B, D, L)
x = torch.randn(B, D, L)

# Create mean tensor: (B, D, L) with last dimension = L (not 1 for typical case)
mean = torch.randn(B, D, L)

# Create std tensor: (B, D, L)
std = torch.randn(B, D, L)

# Make std and mean positive (since they're used as multipliers for denormalization)
std = torch.abs(std) + 0.1
mean = torch.randn(B, D, L)

ARGS = {
    "x": x,
    "mean": mean,
    "std": std
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 5) — shape (2, 4, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
divide_no_nan Ran
ran, honoured the contract we drafted
hank0626/timebridge/utils/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from seungyoon-Choi/CoSPOT, is pointer only (licence: NONE) · get_code("bdc787c888ab83a2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from seungyoon-Choi/CoSPOT, and GitHub detected no licence in that repository 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.

get_phi_psi Ran
ran; our contract draft was wrong, not the code
hank0626/timebridge/layers/utils.py
code served (permissive licence) · get_code("f32036738135c8a8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from functools import partial

# Construct valid arguments for get_phi_psi
ARGS = {
    'k': 3,
    'base': 'legendre'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sympy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
legendreDer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hank0626/timebridge/layers/utils.py
code served (permissive licence) · get_code("4ef26472da51e3aa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from scipy.special import eval_legendre

# The function legendreDer takes two parameters:
# k: an integer representing the order
# x: a value or array on which to evaluate the Legendre polynomials

# Looking at the function:
# - k is used in range(k-1, -1, -2) so it should be an integer
# - x is passed to eval_legendre which accepts scalars or arrays
# - The function iterates through odd/even indices based on k

# Create small test values
k = 5  # integer order
x = np.array([0.0, 0.5, -0.5, 1.0])  # small array of evaluation points

ARGS = {
    "k": k,
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalization Ran
ran, honoured the contract we drafted
hank0626/timebridge/layers/Embed.py
code served (permissive licence) · get_code("7ae3eba84feb6b9e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small tensor with shape (batch=2, features=4)
x = torch.randn(2, 4)

# Test case 1: with mean and std provided
mean_provided = torch.randn(2, 1)
std_provided = torch.randn(2, 1).abs() + 0.1  # ensure positive

ARGS = {
    "x": x,
    "mean": mean_provided,
    "std": std_provided
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
phi_ Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
hank0626/timebridge/layers/utils.py
code served (permissive licence) · get_code("a54c8c5c47c6a8b8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (4,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# phi_ takes phi_c (polynomial coefficients), x (input array), and bounds lb, ub
# It creates a Polynomial from phi_c, evaluates it at x, and masks values outside [lb, ub]

# Create polynomial coefficients (small array)
phi_c = np.array([1.0, 2.0, 0.5])

# Create input array with values in and out of bounds
x = np.array([0.2, 0.5, 0.8, 1.5])

# Define bounds
lb = 0.0
ub = 1.0

ARGS = {
    "phi_c": phi_c,
    "x": x,
    "lb": lb,
    "ub": ub,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
MAE Not yet run
unverified (harvested, no recorded run)
hank0626/timebridge/utils/metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from shangzongjiang/Ada-MSHyper, is pointer only (licence: NONE) · get_code("75f44993b096bf76")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shangzongjiang/Ada-MSHyper, and GitHub detected no licence in that repository 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.

RSE Not yet run
unverified (harvested, no recorded run)
hank0626/timebridge/utils/metrics.py
pointer only (licence: MIT); the stored copy get_code serves, from shangzongjiang/Ada-MSHyper, is pointer only (licence: NONE) · get_code("b40a11875ebd0cd2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from shangzongjiang/Ada-MSHyper, and GitHub detected no licence in that repository 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 5 the same month, 7 later) and 3 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
phi_ 24 other papers
16 dated earlier, 3 the same month, 5 later · 1 only as an assembly brick
2201.12740 (2022-01)
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
2205.08897 (2022-05)
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
2304.05206 (2023-04)
The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting
and 21 more not named here
get_phi_psi 23 other papers
15 dated earlier, 3 the same month, 5 later · 1 only as an assembly brick
2201.12740 (2022-01)
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
2205.08897 (2022-05)
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
2305.13036 (2023-05)
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting
and 20 more not named here
legendreDer 23 other papers
15 dated earlier, 3 the same month, 5 later · 1 only as an assembly brick
2201.12740 (2022-01)
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
2205.08897 (2022-05)
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
2305.13036 (2023-05)
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting
and 20 more not named here
RSE 18 other papers
13 dated earlier, 1 the same month, 4 later
2202.01381 (2022-02)
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
2203.05167 (2022-03)
TiSAT: Time Series Anomaly Transformer
2207.10941 (2022-07)
Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
and 15 more not named here
MAE 17 other papers
11 dated earlier, 1 the same month, 5 later
2202.01381 (2022-02)
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
2203.05167 (2022-03)
TiSAT: Time Series Anomaly Transformer
2207.10941 (2022-07)
Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
and 14 more not named here
divide_no_nan 14 other papers
7 dated earlier, 7 later
2401.09093 (2024-01)
RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks
2402.04852 (2024-02)
Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learning
2403.01493 (2024-03)
ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis
and 11 more not named here
CORR 13 other papers
9 dated earlier, 4 later
2202.01381 (2022-02)
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
2203.05167 (2022-03)
TiSAT: Time Series Anomaly Transformer
2207.10941 (2022-07)
Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
and 10 more not named here

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

Non-stationarity poses significant challenges for multivariate time series forecasting due to the inherent short-term fluctuations and long-term trends that can lead to spurious regressions or obscure essential long-term relationships. Most existing methods either eliminate or retain non-stationarity without adequately addressing its distinct impacts on short-term and long-term modeling. Eliminating non-stationarity is essential for avoiding spurious regressions and capturing local dependencies in short-term modeling, while preserving it is crucial for revealing long-term cointegration across variates. In this paper, we propose TimeBridge, a novel framework designed to bridge the gap between non-stationarity and dependency modeling in long-term time series forecasting. By segmenting input series into smaller patches, TimeBridge applies Integrated Attention to mitigate short-term non-stationarity and capture stable dependencies within each variate, while Cointegrated Attention preserves non-stationarity to model long-term cointegration across variates. Extensive experiments show that TimeBridge consistently achieves state-of-the-art performance in both short-term and long-term forecasting. Additionally, TimeBridge demonstrates exceptional performance in financial forecasting on the CSI 500 and S&P 500 indices, further validating its robustness and effectiveness. Code is available at https://github.com/Hank0626/TimeBridge.

For agents

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

get_harvested_code_for_paper("2410.04442")
get_code_for_paper("2410.04442")
have("2410.04442")

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

curl https://syntology.ai/api/ran/2410.04442.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.04442.svg)](https://syntology.ai/paper/2410.04442)

Connect an agent — have() is free.