SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.11089 · 2023

Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 1 has no contract verdict; 3 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/2305.11089.json · badge: /api/ran/2305.11089.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
lanl/blackout-diffusion canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
crop_resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lanl/blackout-diffusion/datasets.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from rarazafin/score_diffusion_ensemble, is pointer only (licence: NONE) · get_code("fd14d238ccd5f679")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from rarazafin/score_diffusion_ensemble, 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.

get_data_inverse_scaler Ran
ran; our contract draft was wrong, not the code
lanl/blackout-diffusion/datasets.py
code served (permissive licence) · get_code("6c419026e778dee2")
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 numpy as np
from types import SimpleNamespace

torch.manual_seed(0)

# Build a minimal config object with a data attribute that has a 'centered' field
config = SimpleNamespace()
config.data = SimpleNamespace()
config.data.centered = True

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 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
get_data_scaler Ran
ran; our contract draft was wrong, not the code
lanl/blackout-diffusion/datasets.py
code served (permissive licence) · get_code("346d2e6cc8b48a5d")
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
from types import SimpleNamespace

torch.manual_seed(0)

# Create a minimal config object with the data.centered attribute
config = SimpleNamespace(
    data=SimpleNamespace(
        centered=True
    )
)

ARGS = {
    "config": config
}
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
restore_checkpoint_withEval Ran
ran on a synthesized input
lanl/blackout-diffusion/utils.py
code served (permissive licence) · get_code("516ce9c96cccd2a5")
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 torch.nn as nn
import os
import tempfile

torch.manual_seed(0)

# Create a minimal model
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal optimizer
model = MinimalModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Create a minimal EMA (Exponential Moving Average) object
class MinimalEMA(nn.Module):
    def __init__(self, model):
        super().__init__()
        self.model = model
    
    def load_state_dict(self, state_dict, strict=True):
        pass

ema = MinimalEMA(model)

# Create state dict with all required fields
state = {
    'optimizer': optimizer,
    'model': model,
    'ema': ema,
    'step': 0,
    'lossHistory': [],
    'evalLossHistory': []
}

# Create a temporary checkpoint file
with tempfile.TemporaryDirectory() as tmpdir:
    ckpt_path = os.path.join(tmpdir, 'checkpoint.pt')
    
    # Save a checkpoint to disk
    checkpoint = {
        'optimizer': optimizer.state_dict(),
        'model': model.state_dict(),
        'ema': ema.state_dict(),
        'step': 42,
        'lossHistory': [0.5, 0.4, 0.3],
        'evalLossHistory': [0.6, 0.5, 0.4]
    }
    torch.save(checkpoint, ckpt_path)
    
    device = 'cpu'
    
    ARGS = {
        'ckpt_dir': ckpt_path,
        'state': state,
        'device': device
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow, 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
restore_checkpoint Not yet run
unverified (harvested, no recorded run)
lanl/blackout-diffusion/utils.py
code served (permissive licence) · get_code("2b9c5e011b00f419")
How it ran

no invocation recorded.

restore_checkpoint_BD Not yet run
unverified (harvested, no recorded run)
lanl/blackout-diffusion/utils.py
code served (permissive licence) · get_code("a72a700d5e6341f5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 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
get_data_inverse_scaler 17 other papers
8 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 14 more not named here
get_data_scaler 17 other papers
8 dated earlier, 1 the same month, 7 later, 1 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 14 more not named here
crop_resize 13 other papers
6 dated earlier, 1 the same month, 5 later, 1 same year, order not determinable
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 10 more not named here

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

Typical generative diffusion models rely on a Gaussian diffusion process for training the backward transformations, which can then be used to generate samples from Gaussian noise. However, real world data often takes place in discrete-state spaces, including many scientific applications. Here, we develop a theoretical formulation for arbitrary discrete-state Markov processes in the forward diffusion process using exact (as opposed to variational) analysis. We relate the theory to the existing continuous-state Gaussian diffusion as well as other approaches to discrete diffusion, and identify the corresponding reverse-time stochastic process and score function in the continuous-time setting, and the reverse-time mapping in the discrete-time setting. As an example of this framework, we introduce ``Blackout Diffusion'', which learns to produce samples from an empty image instead of from noise. Numerical experiments on the CIFAR-10, Binarized MNIST, and CelebA datasets confirm the feasibility of our approach. Generalizing from specific (Gaussian) forward processes to discrete-state processes without a variational approximation sheds light on how to interpret diffusion models, which we discuss.

For agents

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

get_harvested_code_for_paper("2305.11089")
get_code_for_paper("2305.11089")
have("2305.11089")

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

curl https://syntology.ai/api/ran/2305.11089.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.11089.svg)](https://syntology.ai/paper/2305.11089)

Connect an agent — have() is free.