SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.04759 · 2026

Stacked from One: Multi-Scale Self-Injection for Context Window Extension

Pan Zhou, Wei Han, Shuicheng Yan, Soujanya Poria

arXiv · PDF · Open in the Atlas

Code that ran

15 of 21 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 11 failures of our instrument; 6 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/2603.04759.json · badge: /api/ran/2603.04759.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
Clement25/SharedLLM canonical (classifier label)
classifier basis: census
15 ran · 6 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Clement25/SharedLLM/modeling/modeling_llama_sharedllm_flash.py
pointer only (licence: NONE) · get_code("f725bc2d76076485")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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_single Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Clement25/SharedLLM/modeling/modeling_llama_sharedllm_flash.py
pointer only (licence: NONE) · get_code("e8582b3a91d38ecb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

build_chat Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/LongBenchTest/summ/compress.py
pointer only (licence: NONE) · get_code("04b0e165da9a0405")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

count_score Ran
ran, honoured the contract we drafted
Clement25/SharedLLM/LongBenchTest/metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from borealisai/radar-decoding, is pointer only (licence: LGPL-3.0) · get_code("b349b79d9cc2934b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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_max_length_in_nested_lists Ran
ran, honoured the contract we drafted
Clement25/SharedLLM/data_beacon.py
pointer only (licence: NONE) · get_code("74dab428120d8998")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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_word_len Ran
ran, honoured the contract we drafted
Clement25/SharedLLM/LongBenchTest/summ/compress.py
pointer only (licence: NONE) · get_code("03bffbf21c24cb7b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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_word_list Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/LongBenchTest/summ/compress.py
pointer only (licence: NONE) · get_code("b80b1e9bf939544f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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_qa_templates Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/dataset_utils.py
pointer only (licence: NONE) · get_code("c1dc7ad8978154d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

normalize_answer Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/LongBenchTest/metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from borealisai/radar-decoding, is pointer only (licence: LGPL-3.0) · get_code("e7e75981cb464788")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

normalize_answer Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from zihangtian/HAPS, is pointer only (licence: NONE) · get_code("6c668580324cfd97")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

normalize_zh_answer Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/LongBenchTest/metrics.py
pointer only (licence: NONE); the stored copy get_code serves, from borealisai/radar-decoding, is pointer only (licence: LGPL-3.0) · get_code("8c5c581f9264c810")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

post_process Ran
ran, violated the contract we drafted
Clement25/SharedLLM/LongBenchTest/pred.py
pointer only (licence: NONE) · get_code("4489113b536ca6eb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

preprocess_alce Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/dataset_utils.py
pointer only (licence: NONE) · get_code("6ec1f8f1d608c575")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

remove_citations Ran
ran; our contract draft was wrong, not the code
Clement25/SharedLLM/utils.py
pointer only (licence: NONE) · get_code("5df8b525aada9853")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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; our contract draft was wrong, not the code
Clement25/SharedLLM/modeling/modeling_llama_sharedllm_flash.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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_eos Not yet run
unverified (harvested, no recorded run)
Clement25/SharedLLM/data_beacon.py
pointer only (licence: NONE) · get_code("be4b1c17cda256bb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

are_elements_of_same_length Not yet run
unverified (harvested, no recorded run)
Clement25/SharedLLM/data_beacon.py
pointer only (licence: NONE) · get_code("1a27d72ff0a9a025")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

build_chat Not yet run
unverified (harvested, no recorded run)
Clement25/SharedLLM/LongBenchTest/pred.py
pointer only (licence: NONE) · get_code("9fc77302e79f7b27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

f1_score Not yet run
unverified (harvested, no recorded run)
Clement25/SharedLLM/utils.py
pointer only (licence: NONE) · get_code("27f9fcd2b79fea52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

load_data Not yet run
unverified (harvested, no recorded run)
Clement25/SharedLLM/dataset_utils.py
pointer only (licence: NONE) · get_code("45d38779c4dcf77e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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.

parse_args Not yet run
unverified (harvested, no recorded run)
Clement25/SharedLLM/LongBenchTest/pred.py
pointer only (licence: NONE) · get_code("0dcb2bf78dd172f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Clement25/SharedLLM 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 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 16 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 2 the same month, 9 later) and 4 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
rotate_half 360 other papers
331 dated earlier, 5 the same month, 21 later, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
normalize_answer 133 other papers
125 dated earlier, 3 the same month, 4 later, 1 undated · 1 only as an assembly brick
1508.06615 (2015-08)
Character-Aware Neural Language Models
1606.05250 (2016-06)
SQuAD: 100,000+ Questions for Machine Comprehension of Text
1608.07905 (2016-08)
Machine Comprehension Using Match-LSTM and Answer Pointer
and 130 more not named here
apply_rotary_pos_emb 83 other papers
81 dated earlier, 2 later · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
normalize_zh_answer 28 other papers
26 dated earlier, 1 later, 1 undated
2311.04934 (2023-11)
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
2311.09198 (2023-11)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training
2024.findings-emnlp.230 (2024 (year only))
CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models
and 25 more not named here
count_score 24 other papers
22 dated earlier, 1 later, 1 undated
2311.04934 (2023-11)
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
2311.09198 (2023-11)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training
2402.02750 (2024-02)
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
and 21 more not named here
f1_score 19 other papers
19 dated earlier
1809.09600 (2018-09)
HOTPOTQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
1905.05460 (2019-05)
Cognitive Graph for Multi-Hop Reading Comprehension at Scale
1911.02896 (2019-11)
Contextualized Sparse Representations for Real-Time Open-Domain Question Answering
and 16 more not named here
post_process 14 other papers
13 dated earlier, 1 later
2311.09198 (2023-11)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training
2402.02750 (2024-02)
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
2404.14469 (2024-04)
SnapKV: LLM Knows What You are Looking for Before Generation
and 11 more not named here
remove_citations 7 other papers
7 dated earlier
2305.14627 (2023-05)
Enabling Large Language Models to Generate Text with Citations
2311.07838 (2023-11)
LLatrieval: LLM-Verified Retrieval for Verifiable Generation
2402.04315 (2024-02)
Training Language Models to Generate Text with Citations via Fine-grained Rewards
and 4 more not named here
apply_rotary_pos_emb_single 3 other papers
3 dated earlier
2405.12528 (2024-05)
SirLLM: Streaming Infinite Retentive LLM
2406.12018 (2024-06)
CItruS : Chunked Instruction-aware State Eviction for Long Sequence Modeling
2502.17599 (2025-02)
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
build_chat 1 other paper
1 later
2604.10900 (2026-04)
CASK: Core-Aware Selective KV Compression for Reasoning Traces
get_max_length_in_nested_lists 1 other paper
1 dated earlier
2401.06532 (2024-01)
INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning
get_word_len 1 other paper
1 later
2604.10900 (2026-04)
CASK: Core-Aware Selective KV Compression for Reasoning Traces
get_word_list 1 other paper
1 later
2604.10900 (2026-04)
CASK: Core-Aware Selective KV Compression for Reasoning Traces
load_data 1 other paper
1 dated earlier
2402.16617 (2024-02)
Long-Context Language Modeling with Parallel Context Encoding
load_qa_templates 1 other paper
1 dated earlier
2402.16617 (2024-02)
Long-Context Language Modeling with Parallel Context Encoding
preprocess_alce 1 other paper
1 dated earlier
2402.16617 (2024-02)
Long-Context Language Modeling with Parallel Context Encoding

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

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward solution, it incurs prohibitive data acquisition and computational costs. To address this challenge, we propose SHAREDLLM, a novel framework based on multi-grained context compression and query-aware information acquisition. SHAREDLLM comprises two stacked short-context LLMs: a lower model serving as a compressor and an upper model acting as a decoder. The lower model compresses long inputs into compact, multi-grained representations, which are then forwarded to the upper model for context-aware processing. To maximize efficiency, this information transfer occurs exclusively at the lowest layers, bypassing lengthy forward passes and redundant cross-attention operations. This entire process, wherein the upper and lower models are derived from the same underlying LLM layers, is termed self-injection. To support this architecture, a specialized tree-based data structure enables the efficient encoding and queryaware retrieval of contextual information. Despite being trained on sequences of only 8K tokens, SHAREDLLM effectively generalizes to inputs exceeding 128K tokens. Across a comprehensive suite of long-context modeling and understanding benchmarks, SHAREDLLM achieves performance superior or comparable to strong baselines, striking an optimal balance between efficiency and accuracy. Furthermore, these design choices allow SHAREDLLM to substantially reduce the memory footprint and yield notable inference speedups (2× over streaming and 3× over encoder-decoder architectures). The core implementation code, along with training and evaluation details, is open-sourced at https://github.com/Clement25/SharedLLM. More detailes are provided in the appendix and supplementary materials.

For agents

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

get_harvested_code_for_paper("2603.04759")
get_code_for_paper("2603.04759")
have("2603.04759")

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

curl https://syntology.ai/api/ran/2603.04759.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.04759.svg)](https://syntology.ai/paper/2603.04759)

Connect an agent — have() is free.