SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.12018 · EMNLP · 2024

CItruS : Chunked Instruction-aware State Eviction for Long Sequence Modeling

Yu Bai, Yang Gao, Heyan Huang, Jackie Chi, Kit Cheung, Sanxing Chen, Marc-Antoine Rondeau, Xiyuan Zou

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 5 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/2406.12018.json · badge: /api/ran/2406.12018.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
ybai-nlp/CItruS marked official in Papers with Code
Papers with Code archive
5 ran · 5 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb_single Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("feb1b3f32d2a6b1d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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_past_key_values_instruction_aware_single Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("bcbb23a09017e873")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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_past_key_values_standard Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("536f4a58379b992a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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_past_key_values_with_instruction_aware_double Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("99816d85ee9c97a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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.

llama_pos_shift_attention_forward Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("fba04c2f8cfb0944")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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.

decoding Not yet run
unverified (harvested, no recorded run)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("56f48a4c656eed1b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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.

enable_llama_pos_shift_attention Not yet run
unverified (harvested, no recorded run)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("54e3e8b62733f14d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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.

enable_mistral_pos_shift_attention Not yet run
unverified (harvested, no recorded run)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("ada54363a9f4af14")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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.

generate_with_citrus Not yet run
unverified (harvested, no recorded run)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("401a35fa33f1eb57")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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.

mistral_pos_shift_attention_forward Not yet run
unverified (harvested, no recorded run)
ybai-nlp/CItruS/src/citrus_methods.py
pointer only (licence: NONE) · get_code("d1c34504b6b5a6a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ybai-nlp/CItruS 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 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 9 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
apply_rotary_pos_emb_single
brick of this paper's assembly: helper
3 other papers
1 dated earlier, 2 later
2405.12528 (2024-05)
SirLLM: Streaming Infinite Retentive LLM
2502.17599 (2025-02)
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference
2603.04759 (2026-03)
Stacked from One: Multi-Scale Self-Injection for Context Window Extension

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

Long sequence modeling has gained broad interest as large language models (LLMs) continue to advance. Recent research has identified that a large portion of hidden states within the key-value caches of Transformer models can be discarded (also termed evicted) without affecting the perplexity performance in generating long sequences. However, we show that these methods, despite preserving perplexity performance, often drop information that is important for solving downstream tasks, a problem which we call information neglect. To address this issue, we introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. In addition, we design a method for chunked sequence processing to further improve efficiency. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget, while preserving language modeling perplexity. The code and data have been released at https: //github.com/ybai-nlp/CItruS.

For agents

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

get_harvested_code_for_paper("2406.12018")
get_code_for_paper("2406.12018")
have("2406.12018")

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

curl https://syntology.ai/api/ran/2406.12018.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.12018.svg)](https://syntology.ai/paper/2406.12018)

Connect an agent — have() is free.