SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.08137 · CVPR · 2023

LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

Cyberagent, Mayu Otani, Naoto Inoue, Japan, Kotaro Kikuchi, Kota Yamaguchi, Edgar Simo-Serra

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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, 1 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2303.08137.json · badge: /api/ran/2303.08137.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
CyberAgentAILab/layout-dm canonical (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
append_child Ran
ran on a synthesized input
CyberAgentAILab/layout-dm/src/trainer/trainer/datasets/rico.py
code served (permissive licence) · get_code("9de163a84cf5fb0c")
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 1, 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

# Build a nested dict structure representing an element tree
element = {
    'children': [
        {
            'name': 'child1',
            'children': [
                {'name': 'grandchild1'},
                {'name': 'grandchild2'}
            ]
        },
        {
            'name': 'child2'
        }
    ],
    'name': 'root'
}

elements = []

ARGS = {
    'element': element,
    'elements': elements
}
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 list, ndim 1, dtype family float — 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
files_exist Ran
ran on a synthesized input
CyberAgentAILab/layout-dm/src/trainer/trainer/datasets/dataset.py
code served (permissive licence) · get_code("1f09210911a76554")
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 tempfile
import os

# Create temporary files to test the files_exist function
with tempfile.TemporaryDirectory() as tmpdir:
    # Create some test files
    test_file_1 = os.path.join(tmpdir, "test_file_1.txt")
    test_file_2 = os.path.join(tmpdir, "test_file_2.txt")
    
    with open(test_file_1, 'w') as f:
        f.write("test content 1")
    
    with open(test_file_2, 'w') as f:
        f.write("test content 2")
    
    ARGS = {
        "files": [test_file_1, test_file_2]
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
fsspec — 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
to_list Ran
ran, violated the contract we drafted
CyberAgentAILab/layout-dm/src/trainer/trainer/datasets/dataset.py
code served (permissive licence) · get_code("a9178e09ab2d3a5a")
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 1, 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 torch
import numpy as np
from collections.abc import Mapping, Sequence

torch.manual_seed(0)

# Test with a list (Sequence, not str)
list_value = [1, 2, 3, 4]

# Test with a tuple (Sequence, not str)
tuple_value = (5, 6, 7)

# Test with a string (Sequence but should be wrapped)
string_value = "hello"

# Test with a scalar
scalar_value = 42

# Test with a dict (not a Sequence)
dict_value = {"a": 1, "b": 2}

# Test with a tensor (not a Sequence in the abc sense)
tensor_value = torch.randn(2, 4)

# Test with numpy array (not a Sequence in the abc sense)
numpy_value = np.array([1, 2, 3])

# Create multiple test cases for ARGS - using the most representative one
# The function checks if value is a Sequence and not a string
# If yes, return as-is; otherwise wrap in list

ARGS = {
    "value": [1, 2, 3]  # A list (Sequence, not str) - will be returned as-is
}
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 list, ndim 1, 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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
to_list 6 other papers
6 later
2310.15817 (2023-10)
Discriminator Guidance for Autoregressive Diffusion Models
2312.17397 (2023-12)
Classifier-free graph diffusion for molecular property targeting
2403.06020 (2024-03)
Multi-conditioned Graph Diffusion for Neural Architecture Search
and 3 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

Controllable layout generation aims at synthesizing plausible arrangement of element bounding boxes with optional constraints, such as type or position of a specific element. In this work, we try to solve a broad range of layout generation tasks in a single model that is based on discrete state-space diffusion models. Our model, named Lay-outDM, naturally handles the structured layout data in the discrete representation and learns to progressively infer a noiseless layout from the initial input, where we model the layout corruption process by modality-wise discrete diffusion. For conditional generation, we propose to inject layout constraints in the form of masking or logit adjustment during inference. We show in the experiments that our Lay-outDM successfully generates high-quality layouts and outperforms both task-specific and task-agnostic baselines on several layout tasks. 1

For agents

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

get_harvested_code_for_paper("2303.08137")
get_code_for_paper("2303.08137")
have("2303.08137")

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

curl https://syntology.ai/api/ran/2303.08137.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.08137.svg)](https://syntology.ai/paper/2303.08137)

Connect an agent — have() is free.