Paper Citation Record · LEDGER

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training

As of 17 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2509.24050.

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

pith.paper-citation-record.v1
2509.24050 v4

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T14:43:55.953976Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6294805d-9f52-465e-a7b5-ffb76721b9ff · outbound

This paper cites GPT-4 Technical Report.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:53.762733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 362a7aa6-3502-458b-9d6f-cd33b3dc6442 · outbound

This paper cites CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.496833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79cee0f-e56e-4a7d-8ace-642e78c8d546 · outbound

This paper cites Routing to the expert: Efficient reward-guided ensemble of large language models.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Routing to the expert: Efficient reward-guided ensemble of large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.834871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b3cfade-80e9-4e5d-b256-1d9af198ecac · outbound

This paper cites Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.986258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63d3f026-4875-4e12-b017-8b2e9b499ec6 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.162713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56eaaeb7-ba01-40e4-bdd9-7fbe2694f17f · outbound

This paper cites A Thorough Examination of Decoding Methods in the Era of LLMs.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training A Thorough Examination of Decoding Methods in the Era of LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.322520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e601e73e-0d00-4f07-b679-a059b0e6583d · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training LLaMA: Open and Efficient Foundation Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.450205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea04f92-1cbd-4b9d-a662-418fd2dad359 · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Finetuned Language Models Are Zero-Shot Learners

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.538761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c7773f0-9bd1-42a8-b13b-87268b176017 · outbound

This paper cites Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversations

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.719733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3a2ff3b-2304-4c1e-9fbd-aa985898ff4e · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Fine-Tuning Language Models from Human Preferences

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.821657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cd9ffc5-2071-4047-82ef-8c7574928987 · outbound

This paper cites The Countdown task is an arith- metic puzzle where the model must combine a given set of numbers using basic arithmetic operations (+,−,×,÷) to reach a specified target number.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training The Countdown task is an arith- metic puzzle where the model must combine a given set of numbers using basic arithmetic operations (+,−,×,÷) to reach a specified target number

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.953976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c784c6-9798-4e4f-ad24-e1fb01660bab · outbound

This paper cites On-Device Language Models: A Comprehensive Review.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training On-Device Language Models: A Comprehensive Review

Reference 1992

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:55.645299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972cc23e-17cd-4882-8b96-d058ae7f201d · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.119424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd503892-46af-4e2e-b307-b2c81be56dd0 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.008788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccbc9f12-93f1-4be4-84a2-4a2f3e852ef0 · outbound

This paper cites Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.655669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e02e11a-adc3-4dd3-b7f1-1c1fa58b574f · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:53.869680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34404daf-c9dd-4db4-94bb-db3556637f08 · outbound

This paper cites Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training Federated Sketching LoRA: A Flexible Framework for Heterogeneous Collaborative Fine-Tuning of LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.224975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0fefbed-76c6-4d8e-8c6d-f2fc7168b50a · outbound

This paper cites DeBERTa: Decoding-enhanced BERT with Disentangled Attention.

Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training DeBERTa: Decoding-enhanced BERT with Disentangled Attention

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:54.378053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.