SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.13792 · 2024

Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning

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 (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 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/2410.13792.json · badge: /api/ran/2410.13792.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
azencot-group/gatlm canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
decor_time Ran
ran; our contract draft was wrong, not the code
azencot-group/gatlm/FEDformer/layers/AutoCorrelation.py
code served (permissive licence) · get_code("c4d0804ed8acef6e")
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 function. 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 time
import torch
import torch.nn as nn

def decor_time(func):
    def func2(*args, **kw):
        now = time.time()
        y = func(*args, **kw)
        t = time.time() - now
        print('call <{}>, time={}'.format(func.__name__, t))
        return y
    return func2

# Create a simple test function to decorate
@decor_time
def sample_function(x, y):
    """A simple function that does some work"""
    result = x + y
    time.sleep(0.001)  # Small delay to ensure measurable time
    return result

# Define ARGS mapping every parameter of decor_time to a value
ARGS = {
    'func': sample_function
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
get_frequency_modes Ran
ran, honoured the contract we drafted
azencot-group/gatlm/FEDformer/layers/FourierCorrelation.py
code served (permissive licence) · get_code("592ea8b254b006db")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

np.random.seed(0)

ARGS = {
    'seq_len': 128,
    'modes': 64,
    'mode_select_method': 'random'
}
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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
get_settings Ran
ran; our contract draft was wrong, not the code
azencot-group/gatlm/utils.py
code served (permissive licence) · get_code("01de8080b8d66e5e")
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 str. 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 torch
import numpy as np

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.task_id = "task_001"
        self.model = "transformer"
        self.mode_select = "time_series"
        self.modes = 8
        self.data = "electricity"
        self.features = "M"
        self.seq_len = 96
        self.label_len = 48
        self.pred_len = 24
        self.d_model = 512
        self.n_heads = 8
        self.e_layers = 2
        self.d_layers = 1
        self.d_ff = 2048
        self.factor = 3
        self.embed = "timeF"
        self.distil = True
        self.des = "experiment"

ARGS = {
    'args': Args(),
    'ii': 0
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
intrinsic_dimension Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
azencot-group/gatlm/intrinsic_dimension.py
code served (permissive licence) · get_code("958b0dcff51cb7c5")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from scipy.spatial.distance import pdist, squareform

torch.manual_seed(0)

# Create a small dataset of points
# Shape: (n_points, n_dimensions)
# Using 8 points in 4-dimensional space
X_cpu = np.random.randn(8, 4).astype(np.float32)

# For GPU version, convert to torch tensor (CPU tensor, since sandbox has no CUDA)
X_gpu = torch.tensor(X_cpu, dtype=torch.float32)

ARGS = {
    'X': X_cpu,
    'verbose': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn, torch — 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
intrinsic_dimension_cpu Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
azencot-group/gatlm/intrinsic_dimension.py
code served (permissive licence) · get_code("667c82d1e6846bea")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import torch

torch.manual_seed(0)

# Create a small set of random points in 3D space
# We need enough points so that the distance matrix operations work
# The function computes pairwise distances and looks at nearest neighbors
np.random.seed(0)
n_points = 10
n_features = 3

# Create random points in feature space
X = np.random.randn(n_points, n_features).astype(np.float64)

ARGS = {
    "X": X,
    "verbose": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
torch_knn Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
azencot-group/gatlm/caml.py
code served (permissive licence) · get_code("8944eec10f3ba5ad")
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, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim 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)

# Create a small input tensor with shape (2, 4) - 2 data points, 4 dimensions
X = torch.randn(2, 4, dtype=torch.float32)

# Number of nearest neighbors
K = 1

ARGS = {
    "X": X,
    "K": K,
}
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 tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
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
intrinsic_dimension_gpu Not yet run
unverified (harvested, no recorded run)
azencot-group/gatlm/intrinsic_dimension.py
code served (permissive licence) · get_code("0b07b88a5336fd5a")
How it ran

no invocation recorded.

sample_neighbors Not yet run
unverified (harvested, no recorded run)
azencot-group/gatlm/utils.py
code served (permissive licence) · get_code("348d1d4dc8440301")
How it ran

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 (2 with at least one paper dated earlier, 1 the same month, 1 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
get_frequency_modes 27 other papers
17 dated earlier, 2 the same month, 8 later · 1 only as an assembly brick
2201.12740 (2022-01)
FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
2304.09184 (2023-04)
Frequency Enhanced Hybrid Attention Network for Sequential Recommendation
2305.13036 (2023-05)
Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting
and 24 more not named here
decor_time 3 other papers
3 dated earlier
2205.08897 (2022-05)
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting
2310.14838 (2023-10)
Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
2311.01933 (2023-11)
ForecastPFN: Synthetically-Trained Zero-Shot 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

Transformer models have consistently achieved remarkable results in various domains such as natural language processing and computer vision. However, despite ongoing research efforts to better understand these models, the field still lacks a comprehensive understanding. This is particularly true for deep time series forecasting methods, where analysis and understanding work is relatively limited. Time series data, unlike image and text information, can be more challenging to interpret and analyze. To address this, we approach the problem from a manifold learning perspective, assuming that the latent representations of time series forecasting models lie next to a low-dimensional manifold. In our study, we focus on analyzing the geometric features of these latent data manifolds, including intrinsic dimension and principal curvatures. Our findings reveal that deep transformer models exhibit similar geometric behavior across layers, and these geometric features are correlated with model performance. Additionally, we observe that untrained models initially have different structures, but they rapidly converge during training. By leveraging our geometric analysis and differentiable tools, we can potentially design new and improved deep forecasting neural networks. This approach complements existing analysis studies and contributes to a better understanding of transformer models in the context of time series forecasting. Code is released at https://github.com/azencot-group/GATLM.

For agents

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

get_harvested_code_for_paper("2410.13792")
get_code_for_paper("2410.13792")
have("2410.13792")

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

curl https://syntology.ai/api/ran/2410.13792.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.13792.svg)](https://syntology.ai/paper/2410.13792)

Connect an agent — have() is free.