SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.09328 · 2024

Auto-Regressive Moving Diffusion Models for Time Series Forecasting

arXiv · PDF · Open in the Atlas

Code that ran

20 of 20 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; 6 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 11 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2412.09328.json · badge: /api/ran/2412.09328.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
daxin007/armd canonical (classifier label)
classifier basis: census
20 ran · 0 no recorded run
FunctionStatusWhere it lives
identity Ran
ran, honoured the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/model_utils.py
code served (permissive licence) · get_code("7f1040f5e3991d5e")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) 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. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:37:21Z). 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

torch.manual_seed(0)

# The identity function simply returns its first argument
# and ignores all other args and kwargs
# So we need to provide a value for t and can optionally provide other args/kwargs

t = torch.randn(2, 4)
extra_arg_1 = torch.randn(3, 5)
extra_arg_2 = "some_string"
extra_kwarg_1 = 42
extra_kwarg_2 = [1, 2, 3]

ARGS = {
    "t": t,
    "args": (extra_arg_1, extra_arg_2),
    "kwargs": {"key1": extra_kwarg_1, "key2": extra_kwarg_2}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
batch_generator Ran
ran on a synthesized input
daxin007/armd/Utils/discriminative_metric.py
code served (permissive licence) · get_code("16dc8797fafc754b")
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. 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

# Set random seed for reproducibility
np.random.seed(0)

# Create small time-series data
# data should be indexable and support len()
# Each element will be accessed via data[i]
data = [np.array([1.0, 2.0, 3.0, 4.0]), 
        np.array([5.0, 6.0, 7.0, 8.0]),
        np.array([9.0, 10.0, 11.0, 12.0]),
        np.array([13.0, 14.0, 15.0, 16.0])]

# Create time information
# time should be indexable and support len()
# Each element will be accessed via time[i]
time = [np.array([0.1, 0.2, 0.3, 0.4]),
        np.array([0.5, 0.6, 0.7, 0.8]),
        np.array([0.9, 1.0, 1.1, 1.2]),
        np.array([1.3, 1.4, 1.5, 1.6])]

# Batch size
batch_size = 2

ARGS = {
    "data": data,
    "time": time,
    "batch_size": batch_size
}
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, 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
cacf_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
daxin007/armd/Utils/cross_correlation.py
code served (permissive licence) · get_code("bef4cca3a23662a6")
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, 10) 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)

# Construct a small tensor with shape (batch=2, time=5, features=4)
# The function expects x to have shape (..., n, n) where n is x.shape[2]
# So we need x.shape[2] to be square-compatible for tril_indices
x = torch.randn(2, 5, 4)

max_lag = 3

dim = (0, 1)

ARGS = {
    "x": x,
    "max_lag": max_lag,
    "dim": dim,
}
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, 10) — shape (2, 3, 10) 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
calculate_fid Ran
ran, honoured the contract we drafted
daxin007/armd/Utils/context_fid.py
code served (permissive licence) · get_code("20a4af10369ee6be")
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) and returned float64, 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
import scipy.linalg

# Create two small activation arrays for testing
# Shape: (batch_size, feature_dim)
np.random.seed(0)
act1 = np.random.randn(2, 4).astype(np.float32)
act2 = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "act1": act1,
    "act2": act2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy — 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, 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
compensate_masking Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/masking_utils.py
code served (permissive licence) · get_code("0c1e47b7a9f0bc5c")
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, 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 small tensors for testing
batch_size = 2
seq_length = 3
feat_dim = 4

# X: (batch_size, seq_length, feat_dim) - the feature vectors
X = torch.randn(batch_size, seq_length, feat_dim)

# mask: (batch_size, seq_length, feat_dim) - binary mask where 1 = active, 0 = masked
# Create a mask with some elements masked (0) and some active (1)
mask = torch.tensor([
    [[1, 1, 0, 1],
     [1, 0, 1, 1],
     [0, 1, 1, 1]],
    [[1, 1, 1, 0],
     [1, 1, 0, 1],
     [1, 0, 1, 1]]
], dtype=torch.float32)

ARGS = {
    "X": X,
    "mask": mask
}
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, 4) — shape (2, 3, 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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/armd.py
code served (permissive licence) · get_code("05e94467a0de94a4")
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) and returned Tensor, ndim 1, dtype family float, shape (10,) 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 math

torch.manual_seed(0)

ARGS = {
    "timesteps": 10,
    "s": 0.008
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (10,) — shape (10,) 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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/linear.py
code served (permissive licence) · get_code("083bd130603b9c0b")
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 1, dtype family float, shape (96,) 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 math
import torch

torch.manual_seed(0)

# The function takes two parameters: timesteps (int) and s (float, default 0.008)
# Looking at the function body:
# - timesteps is used in arithmetic operations and torch.linspace
# - s is used in arithmetic operations
# Both are simple scalar values

ARGS = {
    "timesteps": 96,
    "s": 0.008
}
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 1, dtype family float, shape (96,) — shape (96,) 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
costume_collate Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/masking_utils.py
code served (permissive licence) · get_code("6e9a7cc7f3228021")
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 torch

torch.manual_seed(0)

# Create sample data: list of (X, mask) tuples
# X: (seq_length, feat_dim), mask: (seq_length, feat_dim)
batch_size = 2
feat_dim = 4

# First sample: sequence length 5
X1 = torch.randn(5, feat_dim)
mask1 = torch.randint(0, 2, (5, feat_dim)).bool()

# Second sample: sequence length 3
X2 = torch.randn(3, feat_dim)
mask2 = torch.randint(0, 2, (3, feat_dim)).bool()

data = [(X1, mask1), (X2, mask2)]

ARGS = {
    "data": data,
    "max_len": None,
    "mask_compensation": False
}
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 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
default Ran
ran, violated the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/model_utils.py
code served (permissive licence) · get_code("d1ef6b8cb9a28a53")
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) 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

torch.manual_seed(0)

def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if callable(d) else d

# Test case 1: val is not None, should return val
val_1 = "test_value"
d_1 = lambda: "default_value"

# Test case 2: val is None, d is callable, should return d()
val_2 = None
d_2 = lambda: "computed_default"

# Test case 3: val is None, d is not callable, should return d
val_3 = None
d_3 = "static_default"

# Test case 4: val is a number
val_4 = 42
d_4 = 100

# Test case 5: val is a tensor
val_5 = torch.tensor([1.0, 2.0, 3.0])
d_5 = lambda: torch.tensor([0.0])

ARGS = {
    "val": val_1,
    "d": d_1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
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
exists Ran
ran, violated the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/model_utils.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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) 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 torch

def exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
extract_time Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/metric_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from jsyoon0823/TimeGAN, is pointer only (licence: NOASSERTION) · get_code("26f7b8d2b7cae501")
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 jsyoon0823/TimeGAN, 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. A run is recorded.

get_quantile Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/imputation_utils.py
code served (permissive licence) · get_code("b16217f58fce53e0")
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 (2,) 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)
# The function calls torch.quantile(samples, q, dim=dim)
# and then .cpu().numpy() on the result
samples = torch.randn(2, 4)

# q is the quantile value(s) - can be a float or tensor
q = 0.5

# dim is the dimension along which to compute quantiles
dim = 1

ARGS = {
    "samples": samples,
    "q": q,
    "dim": dim,
}
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 ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
linear_beta_schedule Ran
ran, honoured the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/armd.py
code served (permissive licence) · get_code("482723f534770483")
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) and returned Tensor, ndim 1, dtype family float, shape (50,) 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)

ARGS = {
    "timesteps": 50
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, dtype family float, shape (50,) — shape (50,) 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
linear_beta_schedule Ran
ran, honoured the contract we drafted
daxin007/armd/Models/autoregressive_diffusion/linear.py
code served (permissive licence) · get_code("b1c96b38eaa2a9e7")
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 1, dtype family float, shape (96,) 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)

timesteps = 96

ARGS = {
    "timesteps": timesteps
}
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 1, dtype family float, shape (96,) — shape (96,) 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
load_dict_from_json Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/io_utils.py
code served (permissive licence) · get_code("8b8ed7b7f7de3f69")
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 json
import tempfile
import os

# Create a temporary JSON file with some test data
temp_dir = tempfile.mkdtemp()
json_file = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": 42,
    "key3": [1, 2, 3],
    "key4": {"nested": "dict"}
}

with open(json_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "path": json_file
}
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 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
load_yaml_config Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/io_utils.py
code served (permissive licence) · get_code("ef8e0e1d280c05be")
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 tempfile
import os
import yaml

# Create a temporary YAML file with valid configuration
temp_dir = tempfile.mkdtemp()
config_path = os.path.join(temp_dir, "config.yaml")

sample_config = {
    "model": "test_model",
    "batch_size": 32,
    "learning_rate": 0.001,
    "epochs": 10,
    "layers": [128, 64, 32],
    "dropout": 0.5
}

with open(config_path, 'w') as f:
    yaml.dump(sample_config, f)

ARGS = {
    "path": config_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
merge_opts_to_config Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/io_utils.py
code served (permissive licence) · get_code("66531358d7cefe44")
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 a nested config dictionary that can be modified
config = {
    'model': {
        'hidden_dim': 256,
        'num_layers': 3,
        'dropout': 0.5
    },
    'training': {
        'learning_rate': 0.001,
        'batch_size': 32,
        'epochs': 10
    },
    'data': {
        'path': '/tmp/data',
        'normalize': True
    }
}

# opts is a list of alternating keys (dot-separated paths) and values
opts = [
    'model.hidden_dim', '512',
    'training.learning_rate', '0.0005',
    'data.normalize', 'False'
]

ARGS = {
    'config': config,
    'opts': opts
}
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
padding_mask Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/masking_utils.py
code served (permissive licence) · get_code("fbf2cb45dcc978f2")
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 tensor of sequence lengths for a batch of 2 sequences
# The lengths should be small integers indicating actual sequence lengths
lengths = torch.tensor([3, 2], dtype=torch.long)

# max_len is optional, but we can provide it
max_len = 4

ARGS = {
    "lengths": lengths,
    "max_len": max_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 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
random_mask Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/imputation_utils.py
code served (permissive licence) · get_code("495e06d1db831486")
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. 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)
np.random.seed(0)

# Create sample observed_values: a 2D array with some NaN values
# Using shape (2, 4) for batch=2, dim=4
observed_values = np.array([
    [1.0, 2.0, np.nan, 4.0],
    [5.0, np.nan, 7.0, 8.0]
], dtype=np.float32)

ARGS = {
    "observed_values": observed_values,
    "missing_ratio": 0.1,
    "seed": 1984,
}
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
train_test_divide Ran
ran; our contract draft was wrong, not the code
daxin007/armd/Utils/metric_utils.py
code served (permissive licence) · get_code("1cd2e1e5e6631289")
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

# Set random seed for reproducibility
np.random.seed(0)

# Create small sample data
# data_x: original data - list of arrays/sequences
data_x = [np.random.randn(5, 3) for _ in range(10)]

# data_x_hat: generated/synthetic data - list of arrays/sequences
data_x_hat = [np.random.randn(5, 3) for _ in range(8)]

# data_t: original time - list of arrays/sequences
data_t = [np.random.randn(5, 2) for _ in range(10)]

# data_t_hat: generated time - list of arrays/sequences
data_t_hat = [np.random.randn(5, 2) for _ in range(8)]

# train_rate: ratio of training data from original data
train_rate = 0.8

ARGS = {
    "data_x": data_x,
    "data_x_hat": data_x_hat,
    "data_t": data_t,
    "data_t_hat": data_t_hat,
    "train_rate": train_rate
}
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 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 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 18 are also present in other papers whose code we hold (18 with at least one paper dated earlier, 5 the same month, 7 later) and 0 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
exists 144 other papers
108 dated earlier, 4 the same month, 27 later, 5 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
default 79 other papers
57 dated earlier, 3 the same month, 16 later, 3 same year, order not determinable · 15 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
and 76 more not named here
identity 54 other papers
43 dated earlier, 2 the same month, 8 later, 1 same year, order not determinable · 11 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 51 more not named here
linear_beta_schedule 18 other papers
11 dated earlier, 1 the same month, 6 later · 12 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
and 15 more not named here
cosine_beta_schedule 13 other papers
10 dated earlier, 1 the same month, 2 later · 5 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2303.11579 (2023-03)
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
2303.17959 (2023-03)
Diffusion Action Segmentation
and 10 more not named here
extract_time 3 other papers
2 dated earlier, 1 later
2210.02040 (2022-10)
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
2409.14013 (2024-09)
ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation
2510.06699 (2025-10)
A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
merge_opts_to_config 3 other papers
3 dated earlier
2211.11694 (2022-11)
Exploring Discrete Diffusion Models for Image Captioning
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
padding_mask 3 other papers
2 dated earlier, 1 later
2403.07300 (2024-03)
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
2502.06910 (2025-02)
TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting
batch_generator 2 other papers
2 dated earlier
2210.02040 (2022-10)
GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
calculate_fid 2 other papers
2 dated earlier
2403.01742 (2024-03)
Diffusion-TS: Interpretable Diffusion for General Time Series Generation
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
compensate_masking 2 other papers
2 dated earlier
2010.02803 (2020-10)
A Transformer-based Framework for Multivariate Time Series Representation Learning
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
load_dict_from_json 2 other papers
2 dated earlier
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
load_yaml_config 2 other papers
2 dated earlier
2305.01319 (2023-05)
Long-Term Rhythmic Video Soundtracker
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
train_test_divide 2 other papers
2 dated earlier
2309.03755 (2023-09)
TSGBench: Time Series Generation Benchmark
2409.14013 (2024-09)
ChronoGAN: Supervised and Embedded Generative Adversarial Networks for Time Series Generation
cacf_torch 1 other paper
1 dated earlier
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
costume_collate 1 other paper
1 dated earlier
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
get_quantile 1 other paper
1 dated earlier
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow
random_mask 1 other paper
1 dated earlier
2411.07506 (2024-11)
FlowTS: Time Series Generation via Rectified Flow

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 (TSF) is essential in various domains, and recent advancements in diffusion-based TSF models have shown considerable promise. However, these models typically adopt traditional diffusion patterns, treating TSF as a noise-based conditional generation task. This approach neglects the inherent continuous sequential nature of time series, leading to a fundamental misalignment between diffusion mechanisms and the TSF objective, thereby severely impairing performance. To bridge this misalignment, and inspired by the classic Auto-Regressive Moving Average (ARMA) theory, which views time series as continuous sequential progressions evolving from previous data points, we propose a novel Auto-Regressive Moving Diffusion (ARMD) model to first achieve the continuous sequential diffusion-based TSF. Unlike previous methods that start from white Gaussian noise, our model employs chain-based diffusion with priors, accurately modeling the evolution of time series and leveraging intermediate state information to improve forecasting accuracy and stability. Specifically, our approach reinterprets the diffusion process by considering future series as the initial state and historical series as the final state, with intermediate series generated using a sliding-based technique during the forward process. This design aligns the diffusion model's sampling procedure with the forecasting objective, resulting in an unconditional, continuous sequential diffusion TSF model. Extensive experiments conducted on seven widely used datasets demonstrate that our model achieves state-of-the-art performance, significantly outperforming existing diffusion-based TSF models. Our code is available on GitHub: https://github.com/daxin007/ARMD.

For agents

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

get_harvested_code_for_paper("2412.09328")
get_code_for_paper("2412.09328")
have("2412.09328")

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

curl https://syntology.ai/api/ran/2412.09328.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.09328.svg)](https://syntology.ai/paper/2412.09328)

Connect an agent — have() is free.