SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.01748 · ICCV · 2023

A Complete Recipe for Diffusion Generative Models

Stephan Mandt, Kushagra Pandey

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2303.01748.json · badge: /api/ran/2303.01748.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
mandt-lab/PSLD marked official in Papers with Code
Papers with Code archive
3 ran · 1 no recorded run
FunctionStatusWhere it lives
PSLD Ran
ran on a synthesized input · constructed an object; no result was computed
mandt-lab/PSLD/main/models/sde/psld.py
code served (permissive licence) · get_code("fa622c9f4a07bab5")
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 an instance of its own class, PSLD: the run constructed the object and did not call it, so no result was computed. 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)

# Create a minimal config class that provides all required attributes
class MinimalConfig:
    def __init__(self):
        self.model = ModelConfig()

class ModelConfig:
    def __init__(self):
        self.sde = SDEConfig()

class SDEConfig:
    def __init__(self):
        self.n_timesteps = 10
        self.beta_min = 0.1
        self.beta_max = 20.0
        self.nu = 0.5
        self.gamma = 0.3
        self.kappa = 2.0
        self.numerical_eps = 1e-5
        self.decomp_mode = 'lower'

# Create config instance
config = MinimalConfig()

# Create ARGS dictionary
ARGS = {
    'config': config
}
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 PSLD — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PSLD 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
register_module Ran
ran; our contract draft was wrong, not the code
mandt-lab/PSLD/main/models/sde/psld.py
code served (permissive licence) · get_code("0f7dbb625f311002")
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 function. 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

# Initialize the _MODULES registry
_MODULES = {}

# Define a simple test class to register
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Build arguments for register_module
ARGS = {
    'category': 'backbone',
    'name': 'simple_model'
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
reshape Ran
ran, violated the contract we drafted
mandt-lab/PSLD/main/models/sde/psld.py
code served (permissive licence) · get_code("62c4665c28db4ae0")
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 (8, 1, 1) 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

torch.manual_seed(0)

# Create two tensors with different shapes
# t: shape (2, 4) - a 2D tensor
# rt: shape (2, 3, 4) - a 3D reference tensor with more dimensions

t = torch.randn(2, 4)
rt = torch.randn(2, 3, 4)

ARGS = {
    "t": t,
    "rt": rt
}
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 (8, 1, 1) — shape (8, 1, 1) 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
SDE Not yet run
unverified (harvested, no recorded run)
mandt-lab/PSLD/main/models/sde/psld.py
code served (permissive licence) · get_code("b73524af8fa13564")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
register_module
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.03686 (2025-02)
Variational Control for Guidance in Diffusion Models

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

Score-based Generative Models (SGMs) have demonstrated exceptional synthesis outcomes across various tasks. However, the current design landscape of the forward diffusion process remains largely untapped and often relies on physical heuristics or simplifying assumptions. Utilizing insights from the development of scalable Bayesian posterior samplers, we present a complete recipe for formulating forward processes in SGMs, ensuring convergence to the desired target distribution. Our approach reveals that several existing SGMs can be seen as specific manifestations of our framework. Building upon this method, we introduce Phase Space Langevin Diffusion (PSLD), which relies on score-based modeling within an augmented space enriched by auxiliary variables akin to physical phase space. Empirical results exhibit the superior sample quality and improved speed-quality trade-off of PSLD compared to various competing approaches on established image synthesis benchmarks. Remarkably, PSLD achieves sample quality akin to state-ofthe-art SGMs (FID: 2.10 for unconditional CIFAR-10 generation). Lastly, we demonstrate the applicability of PSLD in conditional synthesis using pre-trained score networks, offering an appealing alternative as an SGM backbone for future advancements. Code and model checkpoints can be accessed at https://github.com/mandt-lab/PSLD.

For agents

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

get_harvested_code_for_paper("2303.01748")
get_code_for_paper("2303.01748")
have("2303.01748")

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

curl https://syntology.ai/api/ran/2303.01748.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.01748.svg)](https://syntology.ai/paper/2303.01748)

Connect an agent — have() is free.