Paper Citation Record · LEDGER

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference

As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2607.20327.

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

pith.paper-citation-record.v1
2607.20327 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:14:15.769111Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

28 of 28 outbound references displayed

verified exact0
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7e6c972b-025f-4e46-90f7-24537d427c2d · outbound

This paper cites GPT-4 Technical Report.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:12.383244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0545cfab-e194-4e13-8ad2-0ea522a64c51 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Accelerating Large Language Model Decoding with Speculative Sampling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:12.591431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac93d4e0-5e35-4490-885f-7b9d42ff64db · outbound

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

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:12.721693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7222c22-3a5e-4dda-9082-13cbf2705f88 · outbound

This paper cites Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.051550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2142e741-ccc8-4c55-82c7-e54f924f1ce9 · outbound

This paper cites MiniLLM: On-Policy Distillation of Large Language Models.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference MiniLLM: On-Policy Distillation of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.380909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad5fdaf3-25e9-4fd7-9e57-51fcfe9a1fd5 · outbound

This paper cites doi: 10.18653/v1/2024.acl-long.211.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference doi: 10.18653/v1/2024.acl-long.211

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.467160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a10967e-af6f-4723-9c09-c4f692f58998 · outbound

This paper cites AIME 2024 dataset.https://huggingface.co/datasets/HuggingFaceH4/aime_2024,.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference AIME 2024 dataset.https://huggingface.co/datasets/HuggingFaceH4/aime_2024,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.630835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 715ee1e4-58b9-4173-a258-1f06008d172c · outbound

This paper cites arXiv:2309.06180.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference arXiv:2309.06180

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.802085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa795d4c-df4d-440f-bea1-abce99604d42 · outbound

This paper cites Fast Inference from Transformers via Speculative Decoding.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Fast Inference from Transformers via Speculative Decoding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.949395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e56ab1-c631-452a-9a7e-f119d3609eb5 · outbound

This paper cites AIME 2025 dataset.https://huggingface.co/datasets/yentinglin/aime_2025,.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference AIME 2025 dataset.https://huggingface.co/datasets/yentinglin/aime_2025,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.246023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b91f3a8-d83a-4312-9ee4-4266a104c688 · outbound

This paper cites Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.320563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530deb04-d18a-42bf-a086-9ff81f68fe40 · outbound

This paper cites RouteLLM: Learning to Route LLMs with Preference Data.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference RouteLLM: Learning to Route LLMs with Preference Data

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.391012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1410c7ab-d4e5-4fee-afb6-e11cc1348204 · outbound

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

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.449461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a57438e5-8adf-41b2-a66c-fc8ac83177bc · outbound

This paper cites Learning to Decode Collaboratively with Multiple Language Models.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Learning to Decode Collaboratively with Multiple Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.517955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 723212a3-74bc-4b8a-a9ae-27150fab658f · outbound

This paper cites MixLLM: Dynamic Routing in Mixed Large Language Models.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference MixLLM: Dynamic Routing in Mixed Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.711685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9308cf6-41ea-4b30-9dfb-0195d6820f7c · outbound

This paper cites Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, and Zhifang Sui.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li, and Zhifang Sui

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.832244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d44352d-c718-4c95-81c8-019008783cb1 · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.991489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b676662-3a8c-4c5a-88bc-d3b92cbbcff0 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:15.165921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f84fa8b-bdc9-4553-88f3-5f5630551f5c · outbound

This paper cites GlimpRouter: Efficientcollaborativeinferencebyglimpsingonetokenofthoughts.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference GlimpRouter: Efficientcollaborativeinferencebyglimpsingonetokenofthoughts

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:15.345869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d168707e-35fe-4e43-95d1-751aaff63efd · outbound

This paper cites GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:15.519244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9791e570-20ef-4b91-9855-395ec8fb6379 · outbound

This paper cites CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:15.660311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8ef10d5-80c2-4f41-b327-f3fbafc0deb2 · outbound

This paper cites Takeaway.The trace separates model roles cleanly: the SLM supplies the governing equation, while the LLM completes the BCC-specific substitution, unit conversion, and rounding.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Takeaway.The trace separates model roles cleanly: the SLM supplies the governing equation, while the LLM completes the BCC-specific substitution, unit conversion, and rounding

Reference 28

Resolution: malformed identifier; no resolver link, observed 2026-08-01T10:14:15.769111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f250f1a5-a5dd-4351-b8e0-89b29314acf0 · outbound

This paper cites Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, and Haifeng Chen.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, and Haifeng Chen

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.597267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a404b17-ab33-40ef-b445-4eff6cb665a6 · outbound

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

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference 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 2026-08-01T10:14:14.063270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 550fd14e-acad-4d3e-8dde-855233cb7ced · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:13.211948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 293ae174-3f07-4053-a5c8-0d0d8fdb048d · outbound

This paper cites On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:12.501030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc175f25-7347-46ce-9df0-4ad2217144d1 · outbound

This paper cites LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:14.184268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a15f6de-1c3f-45dc-a32c-53193cb650e6 · outbound

This paper cites Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities.

PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-01T10:14:12.873655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.