Paper Citation Record · LEDGER

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining

As of 20 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2608.12419.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2608.12419 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:37:13.242455Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy5
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 10ecf9ea-2e27-4767-99a6-8c3b2fde81fe · outbound

This paper cites ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.103205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ffdd637-eb79-4e81-9bfe-41a66ce05bf8 · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Generating Long Sequences with Sparse Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.124172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e9b861-ffff-48dd-aa7c-c523e445bb0d · outbound

This paper cites WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.139255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7c9018b-0724-4c60-876b-770efc6c2e16 · outbound

This paper cites Mixtral of Experts.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Mixtral of Experts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.149309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1277a8b-720f-455f-93c4-adf05d28d50b · outbound

This paper cites LM2: Large Memory Models.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining LM2: Large Memory Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.154209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a88d323c-1b27-44f5-9edc-13d59e00b0c0 · outbound

This paper cites Cmmlu: Measuring massive multitask language understanding in chinese.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Cmmlu: Measuring massive multitask language understanding in chinese

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:37:13.819645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d4f6923e-5c28-47b0-88b4-46c00825abb2 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.164298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d674f108-fe07-4546-b148-6356289e6d4f · outbound

This paper cites YAYI 2: Multilingual Open-Source Large Language Models.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining YAYI 2: Multilingual Open-Source Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.168892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bbb0316-3e14-4ae9-b64f-1085d797167f · outbound

This paper cites and Lin, S.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining and Lin, S

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.173742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbefe8db-0d73-4a7d-bc6c-a1a9659ed2ef · outbound

This paper cites D., Man, H., Ngo, N.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining D., Man, H., Ngo, N

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:37:13.801749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3972f525-b459-4225-aedb-07acd82cc0a9 · outbound

This paper cites GPT-4 Technical Report.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining GPT-4 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.183149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 083e52af-51bf-4f5d-9672-fc0c05802e3e · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining MemGPT: Towards LLMs as Operating Systems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.188096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5c7008d-2b31-435d-bf08-e1f8ea2e907f · outbound

This paper cites Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.192754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e57663f-f5c3-4323-8c67-1a5822d3e045 · outbound

This paper cites Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.197652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1af0f49-2fba-435d-94f6-2d4a7a6c8f49 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.202478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1feda2-20a5-42ac-9a25-f641f915325e · outbound

This paper cites Skywork: A More Open Bilingual Foundation Model.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Skywork: A More Open Bilingual Foundation Model

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.207202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e3d6708-b9fc-4208-b9f9-f5e2fda05e47 · outbound

This paper cites Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.211915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c22f5d8-e225-45e1-ba7e-79e2b7b284ce · outbound

This paper cites Qwen2.5 Technical Report.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Qwen2.5 Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.216593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 825b28e8-4f0f-47bc-b8b7-d613da9a8ad1 · outbound

This paper cites MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.221795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d9df4fd-26f9-4f69-aff4-d974594451fb · outbound

This paper cites an unresolved cited work.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:37:13.771403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a366ad2c-0efd-4a46-9fbb-8d00dbd114e0 · outbound

This paper cites It contains 7,473 training and 1,319 hand-written test questions, each requiring two to eight sequential reasoning steps.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining It contains 7,473 training and 1,319 hand-written test questions, each requiring two to eight sequential reasoning steps

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:37:13.755433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation caef4196-23c6-4ca0-a02d-71256b7aca81 · outbound

This paper cites Newton,” “Calculus,.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Newton,” “Calculus,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:37:13.738655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6953884a-d2cc-4c52-8824-39dea6a68f0a · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Training Verifiers to Solve Math Word Problems

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.134132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5b64e7-082e-4341-af5e-da75f2a443b5 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.129282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 220ca2b1-b40f-44bf-a4fb-4d2a54465cd1 · outbound

This paper cites InternLM2 Technical Report.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining InternLM2 Technical Report

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.097937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94cda244-ea9a-499e-a5a3-27ddf39a7204 · outbound

This paper cites ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.144294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af8ef260-a15d-4e14-91de-e2b3839592e9 · outbound

This paper cites We organize our supplementary as follows.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining We organize our supplementary as follows

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:37:13.786856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 84fed58e-b464-4c71-8c58-4dac96563597 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Evaluating Large Language Models Trained on Code

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.108617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a340e0f-f967-49f9-b52a-5820bd73ee6e · outbound

This paper cites Longformer: The Long-Document Transformer.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Longformer: The Long-Document Transformer

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.091654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40db4f9e-3cbf-42d5-a60e-9c119a3c28d1 · outbound

This paper cites Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.113611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff30059-21b8-4350-8253-f25a27c34997 · outbound

This paper cites Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory.

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-16T00:37:13.118951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.