SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1703.07015 · 2017

Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 6 failures of our instrument; 0 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/1703.07015.json · badge: /api/ran/1703.07015.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
laiguokun/LSTNet canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
quocanuit/lstnet-solar-gen community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
flaviagiammarino/lstnet-tensorflow community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
create_scaler Ran
ran; our contract draft was wrong, not the code
quocanuit/lstnet-solar-gen/predict.py
code served (permissive licence) · get_code("5fb6852b1a1af7f2")
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 MinMaxScaler. 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
from sklearn.preprocessing import MinMaxScaler

torch.manual_seed(0)

# Create a small numpy array with shape (batch_size, features)
# The function will reshape it to (-1, num_features)
data = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0],
], dtype=np.float32)

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MinMaxScaler — a MinMaxScaler output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinMaxScaler 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
format_datetime Ran
ran; our contract draft was wrong, not the code
quocanuit/lstnet-solar-gen/API/solar-app/solar_app.py
code served (permissive licence) · get_code("a559cf5116ae4a2f")
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.

from datetime import datetime

# Create a datetime object
dt = datetime(2024, 1, 15, 14, 30, 45)

# Define arguments dict
ARGS = {
    'dt': dt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
generate_report Ran
ran; our contract draft was wrong, not the code
quocanuit/lstnet-solar-gen/data_preprocessing.py
code served (permissive licence) · get_code("c186a224ff408cda")
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 dict. 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 pandas as pd
import numpy as np

# Create a sample DataFrame with datetime index
dates = pd.date_range('2023-01-01', periods=100, freq='D')
df = pd.DataFrame({
    'feature1': np.random.randn(100),
    'feature2': np.random.randn(100),
    'feature3': np.random.randn(100),
    'target_col': np.random.randn(100)
}, index=dates)

# Add some missing values
df.loc[df.index[5], 'feature1'] = np.nan
df.loc[df.index[10], 'feature2'] = np.nan

# Create X and y arrays
X = np.random.randn(95, 3)
y = np.random.randn(95)

# Define parameters
features = ['feature1', 'feature2', 'feature3']
target = 'target_col'
window = 7
horizon = 1
data_type = 'time_series'

ARGS = {
    'df': df,
    'X': X,
    'y': y,
    'features': features,
    'target': target,
    'window': window,
    'horizon': horizon,
    'data_type': data_type
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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_training_sequences Ran
ran; our contract draft was wrong, not the code
flaviagiammarino/lstnet-tensorflow/lstnet_tensorflow/utils.py
code served (permissive licence) · get_code("f7970af5000a7b6f")
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. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-26T21:51:12Z. 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

# Create a simple time series with shape (n_samples=10, n_targets=3)
# This represents 10 time steps of 3 different time series
y = np.array([
    [1.0, 2.0, 3.0],
    [1.5, 2.5, 3.5],
    [2.0, 3.0, 4.0],
    [2.5, 3.5, 4.5],
    [3.0, 4.0, 5.0],
    [3.5, 4.5, 5.5],
    [4.0, 5.0, 6.0],
    [4.5, 5.5, 6.5],
    [5.0, 6.0, 7.0],
    [5.5, 6.5, 7.5],
], dtype=np.float32)

# Set n_lookback to 2 (use 2 past time steps as input)
n_lookback = 2

ARGS = {
    "y": y,
    "n_lookback": n_lookback,
}
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 tuple — a tuple output has no array shape of its own; none is stated
Environment
image syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
kernel_regularizer Ran
ran; our contract draft was wrong, not the code
flaviagiammarino/lstnet-tensorflow/lstnet_tensorflow/model.py
code served (permissive licence) · get_code("e1c6f9447ee6d80c")
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 L2. 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 tensorflow as tf

ARGS = {
    'regularizer': 'L2',
    'regularization_factor': 0.01
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type L2 — a L2 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a L2 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
normal_std Ran
ran, honoured the contract we drafted
laiguokun/LSTNet/utils.py
code served (permissive licence) · get_code("1ef18a710e2babf6")
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

def normal_std(x):
    return x.std() * np.sqrt((len(x) - 1.0) / len(x))

# The function takes a single parameter 'x' which needs:
# - .std() method (numpy array or similar)
# - len() support
# - numeric operations (* and numpy.sqrt)

x = np.array([1.0, 2.0, 3.0, 4.0, 5.0])

ARGS = {
    "x": x
}
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 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
process_best_params Ran
ran; our contract draft was wrong, not the code
quocanuit/lstnet-solar-gen/hyperparameter_tuning.py
code served (permissive licence) · get_code("2e470dc1796859fc")
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 dict. 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)

# Construct the 'best' dictionary with various parameter types
best = {
    'hidRNN': 128.5,  # Will be converted to int
    'hidCNN': 64.7,   # Will be converted to int
    'hidSkip': 32.2,  # Will be converted to int
    'CNN_kernel': 3.9,  # Will be converted to int
    'highway_window': 7.1,  # Will be converted to int
    'skip': 0,  # Index into space['skip']
    'batch_size': 1,  # Index into space['batch_size']
    'dropout': 0.5,  # Float value, kept as-is
    'lr': 0.001,  # Float value, kept as-is
    'some_other_param': 'test_value'  # Generic parameter, kept as-is
}

# Construct the 'space' dictionary with indexed selections
space = {
    'skip': [1, 2, 3, 4],  # List of skip values; best['skip']=0 selects space['skip'][0]=1
    'batch_size': [16, 32, 64, 128]  # List of batch sizes; best['batch_size']=1 selects space['batch_size'][1]=32
}

ARGS = {
    'best': best,
    'space': space
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 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
normal_std 2 other papers
2 later
2104.14917 (2021-04)
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution
2202.08408 (2022-02)
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs

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

Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. Temporal data arise in these real-world applications often involves a mixture of long-term and short-term patterns, for which traditional approaches such as Autoregressive models and Gaussian Process may fail. In this paper, we proposed a novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge. LSTNet uses the Convolution Neural Network (CNN) and the Recurrent Neural Network (RNN) to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends. Furthermore, we leverage traditional autoregressive model to tackle the scale insensitive problem of the neural network model. In our evaluation on real-world data with complex mixtures of repetitive patterns, LSTNet achieved significant performance improvements over that of several state-of-the-art baseline methods. All the data and experiment codes are available online.

For agents

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

get_harvested_code_for_paper("1703.07015")
get_code_for_paper("1703.07015")
have("1703.07015")

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

curl https://syntology.ai/api/ran/1703.07015.json

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

[![Syntology run record](https://syntology.ai/api/ran/1703.07015.svg)](https://syntology.ai/paper/1703.07015)

Connect an agent — have() is free.