SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.05643 · 2024

Improving Token-Based World Models with Parallel Observation Prediction

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 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/2402.05643.json · badge: /api/ran/2402.05643.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
leor-c/rem canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_lambda_returns Ran
ran; our contract draft was wrong, not the code
leor-c/rem/src/utils.py
pointer only (licence: GPL-3.0) · get_code("1df223f536480c3e")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

convert_to_matrix Ran
ran, honoured the contract we drafted
leor-c/rem/results/results.py
pointer only (licence: GPL-3.0); the stored copy get_code serves, from hggforget/PIGDreamer, is pointer only (licence: NONE) · get_code("148d1a3e4581ed2a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

extract_state_dict Ran
ran; our contract draft was wrong, not the code
leor-c/rem/src/utils.py
pointer only (licence: GPL-3.0) · get_code("72d867b022cd4358")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

generate_reconstructions_with_tokenizer Ran
ran, honoured the contract we drafted
leor-c/rem/src/make_reconstructions.py
pointer only (licence: GPL-3.0) · get_code("0004f875db350c4a")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

load_json_scores Ran
ran; our contract draft was wrong, not the code
leor-c/rem/results/results.py
pointer only (licence: GPL-3.0) · get_code("08180d560581f597")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

reconstruct_through_tokenizer Ran
ran; our contract draft was wrong, not the code
leor-c/rem/src/make_reconstructions.py
pointer only (licence: GPL-3.0) · get_code("1ce787baaa0d05ee")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

score_normalization Ran
ran; our contract draft was wrong, not the code
leor-c/rem/results/results.py
pointer only (licence: GPL-3.0) · get_code("e2b0e923581cf3f5")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

tensor_to_np_frames Ran
ran; our contract draft was wrong, not the code
leor-c/rem/src/make_reconstructions.py
pointer only (licence: GPL-3.0); the stored copy get_code serves, from vmicheli/delta-iris, is pointer only (licence: GPL-3.0) · get_code("9c2849252ed2f23d")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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.

configure_optimizer Not yet run
unverified (harvested, no recorded run)
leor-c/rem/src/utils.py
pointer only (licence: GPL-3.0) · get_code("ff6a9322b949853b")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, leor-c/rem, is not in the permissive set Syntology serves inline. 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 7 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
convert_to_matrix 1 other paper
1 later
2508.02159 (2025-08)
PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning
tensor_to_np_frames 1 other paper
1 later
2406.19320 (2024-06)
Efficient World Models with Context-Aware Tokenization

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

Motivated by the success of Transformers when applied to sequences of discrete symbols, token-based world models (TBWMs) were recently proposed as sample-efficient methods. In TBWMs, the world model consumes agent experience as a language-like sequence of tokens, where each observation constitutes a sub-sequence. However, during imagination, the sequential token-by-token generation of next observations results in a severe bottleneck, leading to long training times, poor GPU utilization, and limited representations. To resolve this bottleneck, we devise a novel Parallel Observation Prediction (POP) mechanism. POP augments a Retentive Network (RetNet) with a novel forward mode tailored to our reinforcement learning setting. We incorporate POP in a novel TBWM agent named REM (Retentive Environment Model), showcasing a 15.4x faster imagination compared to prior TBWMs. REM attains superhuman performance on 12 out of 26 games of the Atari 100K benchmark, while training in less than 12 hours. Our code is available at \url{https://github.com/leor-c/REM}.

For agents

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

get_harvested_code_for_paper("2402.05643")
get_code_for_paper("2402.05643")
have("2402.05643")

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

curl https://syntology.ai/api/ran/2402.05643.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.05643.svg)](https://syntology.ai/paper/2402.05643)

Connect an agent — have() is free.