SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.01748 · 2026

Discrete World Models via Regularization

Luciano Serafini, Davide Bizzaro

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures 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/2603.01748.json · badge: /api/ran/2603.01748.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
dbizzaro/DWMR community
Papers with Code archive
5 ran · 1 no recorded run
FunctionStatusWhere it lives
ConvolutionalPredictor Ran
ran on a synthesized input · constructed an object; no result was computed
dbizzaro/DWMR/architecture.py
pointer only (licence: NONE) · get_code("f0384c7dc685a1bd")
How it ran

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

EMA Ran
ran on a synthesized input · constructed an object; no result was computed
dbizzaro/DWMR/architecture.py
pointer only (licence: NONE) · get_code("5c5069ffb63ff035")
How it ran

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

JEPABitsConfig Ran
ran on a synthesized input · constructed an object; no result was computed
dbizzaro/DWMR/architecture.py
pointer only (licence: NONE) · get_code("dffd486af72eee89")
How it ran

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

Predictor Ran
ran on a synthesized input · constructed an object; no result was computed
dbizzaro/DWMR/architecture.py
pointer only (licence: NONE) · get_code("d66fe076df46a83d")
How it ran

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

ResidualBlock Ran
ran on a synthesized input · constructed an object; no result was computed
dbizzaro/DWMR/architecture.py
pointer only (licence: NONE) · get_code("be26527e672b3604")
How it ran

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

JEPABits Not yet run
unverified (harvested, no recorded run)
dbizzaro/DWMR/architecture.py
pointer only (licence: NONE) · get_code("4cb0bc97ab83e8d7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dbizzaro/DWMR 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. 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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

World models aim to capture the states and dynamics of an environment in a compact latent space. Moreover, using Boolean state representations is particularly useful for search heuristics and symbolic reasoning and planning. Existing approaches keep latents informative via decoder-based reconstruction, or instead via contrastive or reward signals. In this work, we introduce Discrete World Models via Regularization (DWMR): a reconstruction-free and contrastive-free method for unsupervised Boolean world-model learning. In particular, we introduce a novel world-modeling loss that couples latent prediction with specialized regularizers. Such regularizers maximize the entropy and independence of the representation bits through variance, correlation, and coskewness penalties, while simultaneously enforcing a locality prior for sparse action changes. To enable effective optimization, we also introduce a novel training scheme improving robustness to discrete roll-outs. Experiments on two benchmarks with underlying combinatorial structure show that DWMR learns more accurate representations and transitions than reconstruction-based alternatives. Finally, DWMR can also be paired with an auxiliary reconstruction decoder, and this combination yields additional gains.

For agents

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

get_harvested_code_for_paper("2603.01748")
get_code_for_paper("2603.01748")
have("2603.01748")

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

curl https://syntology.ai/api/ran/2603.01748.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.01748.svg)](https://syntology.ai/paper/2603.01748)

Connect an agent — have() is free.