SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.12920 · ICML · 2024

Generative Marginalization Models

Ryan Adams, Peter Ramadge, Sulin Liu

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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 0 have no contract verdict; 7 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/2310.12920.json · badge: /api/ran/2310.12920.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
PrincetonLIPS/MaM canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
conv_transpose_3x3 Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/MaM/mam/models/nn.py
pointer only (licence: NONE); the stored copy get_code serves, from patrickpynadath1/automatic_cyclical_sampling, is pointer only (licence: NONE) · get_code("abe28c18ca27abc1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

ddpm_conv1x1 Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/MaM/mam/models/layers.py
pointer only (licence: NONE) · get_code("fa9540ea7b02c2f0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

default_init Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/MaM/mam/models/layers.py
pointer only (licence: NONE) · get_code("fdd6aad96accd488")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

image_float_to_int Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PrincetonLIPS/MaM/mam/models/input_embedding.py
pointer only (licence: NONE) · get_code("4f9c97c8629edd97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

make_mlp Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PrincetonLIPS/MaM/mam/models/nn.py
pointer only (licence: NONE) · get_code("60eb5359534cfc1c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

mlp_ebm Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/MaM/mam/models/nn.py
pointer only (licence: NONE) · get_code("3ef3dd39740624ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

variance_scaling Ran
ran; our contract draft was wrong, not the code
PrincetonLIPS/MaM/mam/models/layers.py
pointer only (licence: NONE) · get_code("3ac11bfe0ae80195")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, PrincetonLIPS/MaM 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.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 4 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
variance_scaling 28 other papers
11 dated earlier, 16 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 25 more not named here
default_init 8 other papers
4 dated earlier, 4 later
2206.11892 (2022-06)
DDPM-CD: Denoising Diffusion Probabilistic Models as Feature Extractors for Change Detection
2211.13449 (2022-11)
Fast Sampling of Diffusion Models via Operator Learning
2305.19693 (2023-05)
Spontaneous Symmetry Breaking in Generative Diffusion Models
and 5 more not named here
conv_transpose_3x3 3 other papers
2 dated earlier, 1 later
2209.08183 (2022-09)
Optimal Scaling for Locally Balanced Proposals in Discrete Spaces
2307.04333 (2023-07)
Enhancing Adversarial Robustness via Score-Based Optimization
2402.17699 (2024-02)
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling

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

We introduce marginalization models (MAMs), a new family of generative models for highdimensional discrete data. They offer scalable and flexible generative modeling by explicitly modeling all induced marginal distributions. Marginalization models enable fast approximation of arbitrary marginal probabilities with a single forward pass of the neural network, which overcomes a major limitation of arbitrary marginal inference models, such as any-order autoregressive models. MAMs also address the scalability bottleneck encountered in training any-order generative models for high-dimensional problems under the context of energy-based training, where the goal is to match the learned distribution to a given desired probability (specified by an unnormalized log-probability function such as energy or reward function). We propose scalable methods for learning the marginals, grounded in the concept of "marginalization self-consistency". We demonstrate the effectiveness of the proposed model on a variety of discrete data distributions, including images, text, physical systems, and molecules, for maximum likelihood and energy-based training settings. MAMs achieve orders of magnitude speedup in evaluating the marginal probabilities on both settings. For energy-based training tasks, MAMs enable any-order generative modeling of high-dimensional problems beyond the scale of previous methods. Code is available at github.com/PrincetonLIPS/MaM.

For agents

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

get_harvested_code_for_paper("2310.12920")
get_code_for_paper("2310.12920")
have("2310.12920")

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

curl https://syntology.ai/api/ran/2310.12920.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.12920.svg)](https://syntology.ai/paper/2310.12920)

Connect an agent — have() is free.