SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.03028 · 2023

Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 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, 0 violated it and 3 have no contract verdict; 0 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/2301.03028.json · badge: /api/ran/2301.03028.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
paddlepaddle/paddlespatial canonical (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
build_deepwalk_corpus Ran
ran on a synthesized input
paddlepaddle/paddlespatial/paddlespatial/modelzoo/road_representation/DeepWalk.py
code served (permissive licence) · get_code("52b0d84daf3b51eb")
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 2, 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 random
import networkx as nx
from logging import getLogger

class MockGraph:
    def __init__(self):
        self.graph = nx.Graph()
        self.graph.add_edges_from([(0, 1), (1, 2), (2, 3), (0, 2)])
    
    def nodes(self):
        return self.graph.nodes()
    
    def random_walk(self, path_length, rand=None, alpha=0, start=None):
        """Generate a random walk starting from the given node."""
        walk = [start]
        current = start
        for _ in range(path_length - 1):
            neighbors = list(self.graph.neighbors(current))
            if not neighbors:
                break
            # With probability alpha, restart from random node
            if alpha > 0 and rand.random() < alpha:
                current = rand.choice(list(self.graph.nodes()))
            else:
                current = rand.choice(neighbors)
            walk.append(current)
        return walk

G = MockGraph()
num_paths = 2
path_length = 3
alpha = 0.1
rand = random.Random(42)

ARGS = {
    'G': G,
    'num_paths': num_paths,
    'path_length': path_length,
    'alpha': alpha,
    'rand': rand
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, 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_dataset Ran
ran on a synthesized input
paddlepaddle/paddlespatial/paddlespatial/modelzoo/road_representation/util.py
code served (permissive licence) · get_code("6ceeb8c4a0f9c09d")
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 MockBaseRoadRepDataset. 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 unittest.mock import MagicMock

torch.manual_seed(0)

class MockConfig(dict):
    """Mock configuration object that behaves like a dict"""
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
    
    def __getitem__(self, key):
        return super().__getitem__(key)
    
    def __setitem__(self, key, value):
        return super().__setitem__(key, value)

class MockBaseRoadRepDataset:
    """Mock dataset for road representation models"""
    def __init__(self, config):
        self.config = config
        self.data = torch.randn(2, 4)
    
    def __len__(self):
        return 2
    
    def __getitem__(self, idx):
        return self.data[idx]

class MockLINEDataset:
    """Mock dataset for LINE model"""
    def __init__(self, config):
        self.config = config
        self.edges = [(0, 1), (1, 2)]
    
    def __len__(self):
        return len(self.edges)
    
    def __getitem__(self, idx):
        return self.edges[idx]

# Patch the dataset module
import sys
from types import ModuleType

dataset_module = ModuleType('dataset')
dataset_module.BaseRoadRepDataset = MockBaseRoadRepDataset
dataset_module.LINEDataset = MockLINEDataset
sys.modules['dataset'] = dataset_module

config = MockConfig({
    'task': 'road_representation',
    'model': 'ChebConv',
    'batch_size': 2,
    'num_epochs': 5,
    'learning_rate': 0.001
})

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
dataset, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockBaseRoadRepDataset — a MockBaseRoadRepDataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockBaseRoadRepDataset output the recorded ndim 2 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
str2bool Ran
ran on a synthesized input
paddlepaddle/paddlespatial/paddlespatial/modelzoo/road_representation/util.py
code served (permissive licence) · get_code("d6baefc5e1c20c81")
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 bool, 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 argparse

def str2bool(s):
    if isinstance(s, bool):
        return s
    if s.lower() in ('yes', 'true'):
        return True
    elif s.lower() in ('no', 'false'):
        return False
    else:
        raise argparse.ArgumentTypeError('bool value expected.')

ARGS = {
    's': 'true'
}
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 bool, 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
get_model Not yet run
unverified (harvested, no recorded run)
paddlepaddle/paddlespatial/paddlespatial/modelzoo/road_representation/util.py
code served (permissive licence) · get_code("da53bd4a0fb8b7fa")
How it ran

no invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
paddlepaddle/paddlespatial/paddlespatial/cmdline.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from PaddlePaddle/PaddleHelix, is pointer only (licence: NOASSERTION) · get_code("2f166c1fd0719e77")
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 PaddlePaddle/PaddleHelix, and GitHub could not classify the licence of that repository (NOASSERTION). 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 4 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
main 1 other paper
1 later
2407.09274 (2024-07)
Unifying Sequences, Structures, and Descriptions for Any-to-Any Protein Generation with the Large Multimodal Model HelixProtX

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

Time series forecasting has been a widely explored task of great importance in many applications. However, it is common that real-world time series data are recorded in a short time period, which results in a big gap between the deep model and the limited and noisy time series. In this work, we propose to address the time series forecasting problem with generative modeling and propose a bidirectional variational auto-encoder (BVAE) equipped with diffusion, denoise, and disentanglement, namely D3VAE. Specifically, a coupled diffusion probabilistic model is proposed to augment the time series data without increasing the aleatoric uncertainty and implement a more tractable inference process with BVAE. To ensure the generated series move toward the true target, we further propose to adapt and integrate the multiscale denoising score matching into the diffusion process for time series forecasting. In addition, to enhance the interpretability and stability of the prediction, we treat the latent variable in a multivariate manner and disentangle them on top of minimizing total correlation. Extensive experiments on synthetic and real-world data show that D3VAE outperforms competitive algorithms with remarkable margins. Our implementation is available at https://github.com/PaddlePaddle/PaddleSpatial/tree/main/research/D3VAE.

For agents

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

get_harvested_code_for_paper("2301.03028")
get_code_for_paper("2301.03028")
have("2301.03028")

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

curl https://syntology.ai/api/ran/2301.03028.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.03028.svg)](https://syntology.ai/paper/2301.03028)

Connect an agent — have() is free.