SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.00509 · 2024

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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, 0 violated it and 0 have no contract verdict; 2 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/2409.00509.json · badge: /api/ran/2409.00509.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
zhiyuanhubj/LongRecipe canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
maybe_get_set_global_memory_buffer Ran
ran, honoured the contract we drafted
zhiyuanhubj/LongRecipe/utils/easy_context/dist_flash_attn/async_communication.py
pointer only (licence: NONE) · get_code("ce7333f42d88b05d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhiyuanhubj/LongRecipe 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_get_set_global_memory_buffer_bwd Ran
ran; our contract draft was wrong, not the code
zhiyuanhubj/LongRecipe/utils/easy_context/dist_flash_attn/async_communication.py
pointer only (licence: NONE) · get_code("ee03eab03d798c57")
How it ran

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

process_data_single Ran
ran; our contract draft was wrong, not the code
zhiyuanhubj/LongRecipe/preprocess_token_PI/dataprocessor.py
pointer only (licence: NONE) · get_code("5785cb16b92ebd18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhiyuanhubj/LongRecipe 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_last_time Not yet run
unverified (harvested, no recorded run)
zhiyuanhubj/LongRecipe/utils/easy_context/dist_flash_attn/async_communication.py
pointer only (licence: NONE) · get_code("4be6bef6c83e9c27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, zhiyuanhubj/LongRecipe 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
is_last_time 1 other paper
1 later
2410.17891 (2024-10)
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
maybe_get_set_global_memory_buffer 1 other paper
1 later
2410.17891 (2024-10)
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
maybe_get_set_global_memory_buffer_bwd 1 other paper
1 later
2410.17891 (2024-10)
Scaling Diffusion Language Models via Adaptation from Autoregressive Models

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

Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. Meanwhile, extending the context window in LLMs through post-pretraining is highly resource-intensive. To address this, we introduce LongRecipe, an efficient training strategy for extending the context window of LLMs, including impactful token analysis, position index transformation, and training optimization strategies. It simulates long-sequence inputs while maintaining training efficiency and significantly improves the model's understanding of long-range dependencies. Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size, and reduces computational training resource over 85% compared to full sequence training. Furthermore, LongRecipe also preserves the original LLM's capabilities in general tasks. Ultimately, we can extend the effective context window of open-source LLMs from 8k to 128k, achieving performance close to GPT-4 with just one day of dedicated training using a single GPU with 80G memory. Our code is released at https://github.com/zhiyuanhubj/LongRecipe.

For agents

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

get_harvested_code_for_paper("2409.00509")
get_code_for_paper("2409.00509")
have("2409.00509")

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

curl https://syntology.ai/api/ran/2409.00509.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.00509.svg)](https://syntology.ai/paper/2409.00509)

Connect an agent — have() is free.