SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.00614 · 2024

Learning to Plan for Language Modeling from Unlabeled Data

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 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; 1 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 8 failures of our instrument; 3 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/2404.00614.json · badge: /api/ran/2404.00614.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
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data canonical (classifier label)
classifier basis: census
11 ran · 3 no recorded run
FunctionStatusWhere it lives
bce_loss Ran
ran; our contract draft was wrong, not the code
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/models/muzero.py
pointer only (licence: NONE) · get_code("36b9bffa303911ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

clean_text Ran
ran; our contract draft was wrong, not the code
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/eval_generations.py
pointer only (licence: NONE) · get_code("efc543ba6ad34128")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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_chunk_keys Ran
ran; our contract draft was wrong, not the code
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/dataset.py
pointer only (licence: NONE) · get_code("34d8e57a3a964b1f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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_free_gpus Ran
ran; our contract draft was wrong, not the code
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/pretorch_util.py
pointer only (licence: NONE) · get_code("231d0a6bcffd1e8c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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_nlls Ran
ran, honoured the contract we drafted
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/improvement_v_difficulty.py
pointer only (licence: NONE) · get_code("b5f55a4a778cc37f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

is_embedding_space_prediction Ran
ran, violated the contract we drafted
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/models/muzero.py
pointer only (licence: NONE) · get_code("e33d091e0e0a84f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

load_kmeans_model Ran
ran; our contract draft was wrong, not the code
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/eval_generations.py
pointer only (licence: NONE) · get_code("f71bde6826ec769d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

maybe_expand Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/dataset.py
pointer only (licence: NONE) · get_code("2bcc92df555a69f5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

maybe_unexpand Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/dataset.py
pointer only (licence: NONE) · get_code("b045b24faddec74a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

scalar_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/models/muzero.py
pointer only (licence: NONE) · get_code("8f413d988e80297f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

scores_iso_codes Ran
ran, violated the contract we drafted
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/args.py
pointer only (licence: NONE) · get_code("55f553926509a8a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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_sequence_of_actions Not yet run
unverified (harvested, no recorded run)
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/eval_generations.py
pointer only (licence: NONE) · get_code("09e9c0d9eeda992b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

process_article_batch Not yet run
unverified (harvested, no recorded run)
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/create_oracle_codes.py
pointer only (licence: NONE) · get_code("d3e00ed23e7f2bc5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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.

rank_to_device Not yet run
unverified (harvested, no recorded run)
natithan/learning-to-plan-for-language-modeling-from-unlabeled-data/pretorch_util.py
pointer only (licence: NONE) · get_code("b1541ae798c904ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, natithan/learning-to-plan-for-language-modeling-from-unlabeled-data 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 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 14 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

By training to predict the next token in an unlabeled corpus, large language models learn to perform many tasks without any labeled data. However, their next-token-prediction objective arguably limits their performance in scenarios that require planning, such as writing a coherent article. In this paper, we train a module for planning the future writing process via a self-supervised learning objective. Given the textual context, this planning module learns to predict future abstract writing actions, which correspond to centroids in a clustered text embedding space. By conditioning on these actions, our model extends the successful language model formula to more abstract planning in an unsupervised way. Empirically, we demonstrate that our method improves language modeling performance in general, particularly with respect to the text structure. Because our framework uses a planner module that is unsupervised and external to the language model, new planner modules can be trained at large scale and easily be shared with the community.

For agents

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

get_harvested_code_for_paper("2404.00614")
get_code_for_paper("2404.00614")
have("2404.00614")

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

curl https://syntology.ai/api/ran/2404.00614.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.00614.svg)](https://syntology.ai/paper/2404.00614)

Connect an agent — have() is free.