SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.13397 · 2022

Generative Modelling With Inverse Heat Dissipation

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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 4 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/2206.13397.json · badge: /api/ran/2206.13397.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
aaltoml/generative-inverse-heat-dissipation canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
KL Ran
ran on a synthesized input
aaltoml/generative-inverse-heat-dissipation/model_code/utils.py
code served (permissive licence) · get_code("340b29b54fa65057")
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 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 numpy as np
import torch

torch.manual_seed(0)

# Analyze the function:
# - dists: appears to be a numeric array/tensor used in arithmetic operations
# - sigma0: scalar, used in arithmetic operations
# - sigma1: scalar, used in arithmetic operations  
# - dim: integer, used in arithmetic operations and as a multiplier

# Create small numpy arrays/scalars for the computation
dists = np.array([[1.2, 0.8, 1.5, 0.9],
                  [0.7, 1.1, 0.6, 1.3]])  # shape (2, 4)

sigma0 = 0.5  # scalar standard deviation

sigma1 = 1.0  # scalar standard deviation

dim = 4  # dimension parameter

ARGS = {
    "dists": dists,
    "sigma0": sigma0,
    "sigma1": sigma1,
    "dim": dim
}
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 ndarray, 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
L_K_upperbound Ran
ran on a synthesized input
aaltoml/generative-inverse-heat-dissipation/model_code/utils.py
code served (permissive licence) · get_code("9823142d89172cd2")
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 (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
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create a simple blur module that accepts input and blur steps
class BlurModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, blur_steps):
        # blur_steps is a list of K values, one per sample
        # Just pass through the linear layer for this mock
        return self.linear(x)

# Create tiny dataloaders
# Each batch is a tuple of (images, labels)
# We need small batch sizes and small spatial/feature dimensions

def create_dataloader(num_samples, batch_size, feature_dim=4):
    data = []
    for i in range(0, num_samples, batch_size):
        batch_size_actual = min(batch_size, num_samples - i)
        # Create random feature tensors
        x = torch.randn(batch_size_actual, 1, feature_dim, feature_dim)
        y = torch.randint(0, 2, (batch_size_actual,))
        data.append((x, y))
    return data

train_size = 6
test_size = 4
batch_size = 2
feature_dim = 4

trainloader = create_dataloader(train_size, batch_size, feature_dim)
testloader = create_dataloader(test_size, batch_size, feature_dim)

blur_module = BlurModule()

ARGS = {
    'K': 3,
    'trainloader': trainloader,
    'testloader': testloader,
    'blur_module': blur_module,
    'sigma_inf': 1.0,
    'sigma_prior': 2.0,
    'dim': 4,
    'train_size': train_size,
    'test_size': test_size,
    'device': 'cpu'
}
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 1, dtype family float, shape (4,) — shape (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
dct Ran
ran; our contract draft was wrong, not the code
aaltoml/generative-inverse-heat-dissipation/model_code/torch_dct.py
pointer only (licence: MIT); the stored copy get_code serves, from FlowDPS-Inverse/FlowDPS, is pointer only (licence: NONE) · get_code("b15209709fb2b21d")
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 FlowDPS-Inverse/FlowDPS, 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. A run is recorded.

dct_2d Ran
ran; our contract draft was wrong, not the code
aaltoml/generative-inverse-heat-dissipation/model_code/torch_dct.py
code served (permissive licence) · get_code("44a9ca7722415b89")
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 4, dtype family float, shape (2, 4, 3, 5) 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 numpy as np

torch.manual_seed(0)

# dct_2d takes two parameters: x and norm
# x should be a tensor (based on the function body which calls .shape, .contiguous(), etc.)
# norm should be None or 'ortho'

# Create a small test tensor with shape (batch, height, width, channels)
# Using distinct sizes: batch=2, height=4, width=3 for clarity
x = torch.randn(2, 4, 3, 5, dtype=torch.float32)

ARGS = {
    'x': x,
    'norm': None
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) 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
idct Ran
ran; our contract draft was wrong, not the code
aaltoml/generative-inverse-heat-dissipation/model_code/torch_dct.py
code served (permissive licence) · get_code("180be391371dcdc7")
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 numpy as np
import torch

torch.manual_seed(0)

# Create a small input tensor for the idct function
# The function expects X to have shape (..., N) where N is the last dimension
# Let's create a tensor with shape (2, 4) - batch size 2, last dimension 4
X = torch.randn(2, 4, dtype=torch.float32)

# The norm parameter can be None or 'ortho'
norm = None

ARGS = {
    'X': X,
    'norm': norm
}
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 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
zero_module Ran
ran; our contract draft was wrong, not the code
aaltoml/generative-inverse-heat-dissipation/model_code/nn.py
code served (permissive licence) · get_code("129b804760b3115f")
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 SimpleModule. 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 torch.nn as nn

torch.manual_seed(0)

# Create a simple module with some parameters
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.conv = nn.Conv1d(2, 2, 3)
    
    def forward(self, x):
        return x

module = SimpleModule()

# Verify the module has non-zero parameters before zeroing
for p in module.parameters():
    assert p.abs().sum() > 0, "Parameters should be non-zero initially"

ARGS = {
    "module": module
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
avg_pool_nd Not yet run
unverified (harvested, no recorded run)
aaltoml/generative-inverse-heat-dissipation/model_code/nn.py
code served (permissive licence) · get_code("ecd0fc28815b65ae")
How it ran

no invocation recorded.

conv_nd Not yet run
unverified (harvested, no recorded run)
aaltoml/generative-inverse-heat-dissipation/model_code/nn.py
code served (permissive licence) · get_code("fe4eb545bbb728e0")
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, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 6 later) and 2 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
zero_module 196 other papers
12 dated earlier, 2 the same month, 182 later · 49 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
and 193 more not named here
conv_nd 121 other papers
10 dated earlier, 2 the same month, 109 later · 32 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 118 more not named here
avg_pool_nd 113 other papers
11 dated earlier, 2 the same month, 100 later · 31 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 110 more not named here
dct 7 other papers
7 later
2209.11888 (2022-09)
JPEG Artifact Correction using Denoising Diffusion Restoration Models
2306.00288 (2023-06)
Training-free Neural Architecture Search for RNNs and Transformers
2309.03350 (2023-09)
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
and 4 more not named here
dct_2d 4 other papers
4 later
2302.02693 (2023-02)
PatchDCT: Patch Refinement for High Quality Instance Segmentation
2306.00288 (2023-06)
Training-free Neural Architecture Search for RNNs and Transformers
2406.12814 (2024-06)
Dissecting Adversarial Robustness of Multimodal LM Agents
and 1 more not named here
idct 2 other papers
2 later
2209.11888 (2022-09)
JPEG Artifact Correction using Denoising Diffusion Restoration Models
2510.08273 (2025-10)
One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting

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

While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and the empirical success of coarse-to-fine modelling, we propose a new diffusion-like model that generates images through stochastically reversing the heat equation, a PDE that locally erases fine-scale information when run over the 2D plane of the image. We interpret the solution of the forward heat equation with constant additive noise as a variational approximation in the diffusion latent variable model. Our new model shows emergent qualitative properties not seen in standard diffusion models, such as disentanglement of overall colour and shape in images. Spectral analysis on natural images highlights connections to diffusion models and reveals an implicit coarse-to-fine inductive bias in them.

For agents

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

get_harvested_code_for_paper("2206.13397")
get_code_for_paper("2206.13397")
have("2206.13397")

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

curl https://syntology.ai/api/ran/2206.13397.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.13397.svg)](https://syntology.ai/paper/2206.13397)

Connect an agent — have() is free.