SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.24088 · NeurIPS · 2025

Information-Theoretic Discrete Diffusion

Albert No, Sangwoo Shin, Dongjae Jeon, Moongyu Jeon

arXiv · PDF · Open in the Atlas

Code that ran

18 of 18 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 13 failures of our instrument; 0 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/2510.24088.json · badge: /api/ran/2510.24088.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
Dongjae0324/infodis canonical (classifier label)
classifier basis: census
18 ran · 0 no recorded run
FunctionStatusWhere it lives
Batch_Uniform_Sampler Ran
ran, honoured the contract we drafted
Dongjae0324/infodis/losses.py
pointer only (licence: NONE) · get_code("7df53e0f36bfadb4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

add_noise_lambda Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/noise_lib.py
pointer only (licence: NONE) · get_code("866bafb81f8da612")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

add_noise_t Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/noise_lib.py
pointer only (licence: NONE) · get_code("5dc01eaf879d151a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

apply_rotary_pos_emb Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/model/rotary.py
pointer only (licence: NONE) · get_code("b3c9c4aebf03fa97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

direct_sampling Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/catsample.py
pointer only (licence: NONE) · get_code("92369c72d11b7baf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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_noise Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/noise_lib.py
pointer only (licence: NONE) · get_code("c7a7325b30d3491b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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_optimizer Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/losses.py
pointer only (licence: NONE) · get_code("32fa27b9da9341dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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_timestamped_log_name Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/pretrain_markov.py
pointer only (licence: NONE) · get_code("94947db66a485b0d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

gumbel_softmax Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/catsample.py
pointer only (licence: NONE) · get_code("a017bf60b761f427")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

harmonic_number Ran
ran, honoured the contract we drafted
Dongjae0324/infodis/eval_llada.py
pointer only (licence: NONE) · get_code("f64cfe96715fd0bf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

lm1b_detokenizer Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/data.py
pointer only (licence: NONE); the stored copy get_code serves, from jdeschena/blockgen, is pointer only (licence: NONE) · get_code("576e1b9b9bcae8ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

ptb_detokenizer Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/data.py
pointer only (licence: NONE); the stored copy get_code serves, from jdeschena/blockgen, is pointer only (licence: NONE) · get_code("9f7fbdbe7ca280e0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

rotate_half Ran
ran, honoured the contract we drafted
Dongjae0324/infodis/model/rotary.py
pointer only (licence: NONE); the stored copy get_code serves, from hxixixh/gumbel-distill, is pointer only (licence: NONE) · get_code("8526ce179df04bd4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

sample_batch_mask Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/eval_llada.py
pointer only (licence: NONE) · get_code("d32749162ca51e0e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

sample_categorical Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Dongjae0324/infodis/catsample.py
pointer only (licence: NONE); the stored copy get_code serves, from chuwd19/Split-Gibbs-Discrete-Diffusion-Posterior-Sampling, is pointer only (licence: NONE) · get_code("172aa319a831b3ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

sample_mask_indices Ran
ran, honoured the contract we drafted
Dongjae0324/infodis/eval_llada.py
pointer only (licence: NONE) · get_code("737211a5c83c3f1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

sample_masked_indices Ran
ran, violated the contract we drafted
Dongjae0324/infodis/eval_markov.py
pointer only (licence: NONE) · get_code("6687a07f55d20d8a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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.

wt_detokenizer Ran
ran; our contract draft was wrong, not the code
Dongjae0324/infodis/data.py
pointer only (licence: NONE); the stored copy get_code serves, from jdeschena/blockgen, is pointer only (licence: NONE) · get_code("46c10627206a7795")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Dongjae0324/infodis 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 0 the same month, 4 later) and 5 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
lm1b_detokenizer 11 other papers
8 dated earlier, 3 later
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
2412.10193 (2024-12)
Simple Guidance Mechanisms for Discrete Diffusion Models
and 8 more not named here
ptb_detokenizer 10 other papers
7 dated earlier, 3 later
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
2503.09573 (2025-03)
BLOCK DIFFUSION: INTERPOLATING BETWEEN AU-TOREGRESSIVE AND DIFFUSION LANGUAGE MODELS
and 7 more not named here
wt_detokenizer 10 other papers
7 dated earlier, 3 later
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
2503.09573 (2025-03)
BLOCK DIFFUSION: INTERPOLATING BETWEEN AU-TOREGRESSIVE AND DIFFUSION LANGUAGE MODELS
and 7 more not named here
rotate_half 8 other papers
7 dated earlier, 1 later · 1 only as an assembly brick
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2401.12522 (2024-01)
BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models
2402.07754 (2024-02)
Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
and 5 more not named here
gumbel_softmax 4 other papers
4 dated earlier
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2405.20971 (2024-05)
Amortizing intractable inference in diffusion models for vision, language, and control
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
and 1 more not named here
sample_categorical 4 other papers
4 dated earlier
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2405.20971 (2024-05)
Amortizing intractable inference in diffusion models for vision, language, and control
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
and 1 more not named here
get_optimizer 3 other papers
3 dated earlier
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2405.20971 (2024-05)
Amortizing intractable inference in diffusion models for vision, language, and control
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
get_noise 2 other papers
2 dated earlier
2310.16834 (2023-10)
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Batch_Uniform_Sampler 1 other paper
1 dated earlier
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
add_noise_lambda 1 other paper
1 dated earlier
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
add_noise_t 1 other paper
1 dated earlier
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
apply_rotary_pos_emb 1 other paper
1 dated earlier
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
direct_sampling 1 other paper
1 dated earlier
2406.03736 (2024-06)
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

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 present an information-theoretic framework for discrete diffusion models that yields principled estimators of log-likelihood using score-matching losses. Inspired by the I-MMSE identity for the Gaussian setup, we derive analogous results for the discrete setting. Specifically, we introduce the Information-Minimum Denoising Score Entropy (I-MDSE) relation, which links mutual information between data and its diffused version to the minimum denoising score entropy (DSE) loss. We extend this theory to masked diffusion and establish the Information-Minimum Denoising Cross-Entropy (I-MDCE) relation, connecting cross-entropy losses to mutual information in discrete masked processes. These results provide a timeintegral decomposition of the log-likelihood of the data in terms of optimal scorebased losses, showing that commonly used losses such as DSE and DCE are not merely variational bounds but tight and principled estimators of log-likelihood. The I-MDCE decomposition further enables practical extensions, including time-free formula, conditional likelihood estimation in prompt-response tasks, and coupled Monte Carlo estimation of likelihood ratios. Experiments on synthetic and realworld data confirm the accuracy, variance stability, and utility of our estimators. The code is publicly available at https://github.com/Dongjae0324/infodis.

For agents

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

get_harvested_code_for_paper("2510.24088")
get_code_for_paper("2510.24088")
have("2510.24088")

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

curl https://syntology.ai/api/ran/2510.24088.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.24088.svg)](https://syntology.ai/paper/2510.24088)

Connect an agent — have() is free.