SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.10941 · 2022

Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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, 1 violated it and 3 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2207.10941.json · badge: /api/ran/2207.10941.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
origamisl/rtnet canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
FunctionStatusWhere it lives
CORR Ran
ran, violated the contract we drafted
origamisl/rtnet/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
Cost_loss Ran
ran on a synthesized input
origamisl/rtnet/utils/tools.py
code served (permissive licence) · get_code("1f622a9699880bb7")
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 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 torch

torch.manual_seed(0)

# Analyze the function:
# - z_list: list of tensors
#   - Each z has shape (B, ...) where B is batch size
#   - z is reshaped to (B, group, -1) then permuted to (group, B, -1)
#   - After sim(), shape is (group, B, B)
#   - Then split by aug_num along dim 1, so B must be divisible by aug_num
# - group: integer for reshaping
# - aug_num: integer, default 4, B must be divisible by aug_num

# Let's construct valid tensors:
# B = 4 (divisible by aug_num=4)
# group = 2
# Each z tensor shape: (4, feature_dim) where feature_dim = group * something
# Let's say feature_dim = 2 * 6 = 12, so when reshaped to (4, 2, 6) it works

B = 4
group = 2
feature_dim = group * 6  # = 12
aug_num = 4

# Create z_list with valid tensors
z1 = torch.randn(B, feature_dim)
z2 = torch.randn(B, feature_dim)
z_list = [z1, z2]

ARGS = {
    "z_list": z_list,
    "group": group,
    "aug_num": aug_num,
}
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 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
loss_process Ran
ran on a synthesized input
origamisl/rtnet/utils/tools.py
code served (permissive licence) · get_code("1ac6e62f7be2df4e")
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 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create a simple criterion (loss function)
criterion = nn.MSELoss()

# Create a simple dataset stand-in with the required methods
class SimpleDataset:
    def inverse_transform(self, data):
        # Stand-in: just return the data as-is or with minimal transformation
        return data * 2.0
    
    def standard_transformer(self, data):
        # Stand-in: normalize the data
        return (data - data.mean()) / (data.std() + 1e-8)

dataset = SimpleDataset()

# Create prediction and true tensors
# pred shape: (2, 4) - batch size 2, 4 output dimensions
# true shape: (2, 4) - batch size 2, 4 target dimensions
pred = torch.randn(2, 4)
true = torch.randn(2, 4)

ARGS = {
    'pred': pred,
    'true': true,
    'criterion': criterion,
    'flag': 0,
    'dataset': dataset
}
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 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
sim Ran
ran on a synthesized input
origamisl/rtnet/utils/tools.py
code served (permissive licence) · get_code("31a45e2deaa0cbea")
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, 3, 3) 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 for testing
# The function expects z to support:
# - matmul with transpose (so 3D tensor)
# - sum operation
# - sqrt operation
# - division
# Shape: (batch=2, seq=3, dim=4)
z = torch.randn(2, 3, 4)

ARGS = {
    "z": z
}
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, 3, 3) — shape (2, 3, 3) 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)
origamisl/rtnet/utils/metrics.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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)
origamisl/rtnet/utils/metrics.py
pointer only (licence: Apache-2.0); 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 (Apache-2.0), 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 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
RSE 18 other papers
2 dated earlier, 16 later
2202.01381 (2022-02)
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
2203.05167 (2022-03)
TiSAT: Time Series Anomaly Transformer
2305.18803 (2023-05)
Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
and 15 more not named here
MAE 17 other papers
2 dated earlier, 15 later
2202.01381 (2022-02)
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
2203.05167 (2022-03)
TiSAT: Time Series Anomaly Transformer
2305.18803 (2023-05)
Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
and 14 more not named here
CORR 13 other papers
2 dated earlier, 11 later
2202.01381 (2022-02)
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
2203.05167 (2022-03)
TiSAT: Time Series Anomaly Transformer
2305.18803 (2023-05)
Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors
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 2026-11-21.

Repositories linked to this paper

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

Abstract

How to handle time features shall be the core question of any time series forecasting model. Ironically, it is often ignored or misunderstood by deep-learning based models, even those baselines which are state-of-the-art. This behavior makes their inefficient, untenable and unstable. In this paper, we rigorously analyze three prevalent but deficient/unfounded deep time series forecasting mechanisms or methods from the view of time series properties, including normalization methods, multivariate forecasting and input sequence length. Corresponding corollaries and solutions are given on both empirical and theoretical basis. We thereby propose a novel time series forecasting network, i.e. RTNet, on the basis of aforementioned analysis. It is general enough to be combined with both supervised and self-supervised forecasting format. Thanks to the core idea of respecting time series properties, no matter in which forecasting format, RTNet shows obviously superior forecasting performances compared with dozens of other SOTA time series forecasting baselines in three real-world benchmark datasets. By and large, it even occupies less time complexity and memory usage while acquiring better forecasting accuracy. The source code is available at https://github.com/OrigamiSL/RTNet.

For agents

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

get_harvested_code_for_paper("2207.10941")
get_code_for_paper("2207.10941")
have("2207.10941")

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

curl https://syntology.ai/api/ran/2207.10941.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.10941.svg)](https://syntology.ai/paper/2207.10941)

Connect an agent — have() is free.