Paper Citation Record · LEDGER

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

As of 16 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 4 inbound Pith citation observations for arXiv:2505.23022.

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

pith.paper-citation-record.v1
2505.23022 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:01:08.833699Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:31:30.609964Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T03:17:35.451788Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy26
unresolved7
parse uncertain1
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cf652976-5e64-4903-aa44-52690ad8ff94 · outbound

This paper cites An empirical evaluation of github copilot’s code suggestions.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference An empirical evaluation of github copilot’s code suggestions

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:15.723429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5dac1a84-f3aa-4475-8aa5-0ceb2f7939a5 · outbound

This paper cites Manus, 2025.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Manus, 2025

Reference 3

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T13:01:15.543697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 232529ab-a5f8-4ffe-8597-9b46d4bc9aa1 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Gonzalez, Hao Zhang, and Ion Stoica

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:15.381272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d0f72a92-cd58-4b7c-93d4-a4a6e8da3dc5 · outbound

This paper cites Gonzalez, Clark Barrett, and Ying Sheng.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Gonzalez, Clark Barrett, and Ying Sheng

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:15.150950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b6c4399b-3944-497a-ae77-b944f200abae · outbound

This paper cites Orca: A Distributed Serving System for Transformer-Based Generative Models.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Orca: A Distributed Serving System for Transformer-Based Generative Models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:14.988288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7f5d8508-dcb4-4c4b-94d5-3f66e6f9b151 · outbound

This paper cites Gulavani, and Ramachandran Ramjee.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Gulavani, and Ramachandran Ramjee

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:14.799655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d0f95659-3acb-4308-ae12-40dfa3c7e15c · outbound

This paper cites Tensorrt-llm.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Tensorrt-llm

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:14.648656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 47a7fc43-d000-469b-a164-1d16696392a3 · outbound

This paper cites Towards efficient generative large language model serving: A survey from algorithms to systems, 2023.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Towards efficient generative large language model serving: A survey from algorithms to systems, 2023

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:14.509940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4ba94722-1da6-48c8-a579-b97a3fb7a436 · outbound

This paper cites Queue management for slo- oriented large language model serving, February 2025.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Queue management for slo- oriented large language model serving, February 2025

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:14.319601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6de0359c-649f-47a3-b15f-772ec5ee8e44 · outbound

This paper cites AdaServe: SLO-Customized LLM Serving with Fine-Grained Speculative Decoding, January 2025.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference AdaServe: SLO-Customized LLM Serving with Fine-Grained Speculative Decoding, January 2025

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:14.150235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8e0a672b-8214-4f37-8596-63e9a20e4aee · outbound

This paper cites Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Distserve: Disaggregating prefill and decoding for goodput-optimized large language model serving, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:13.935087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b69eb53a-76f9-45c7-957d-2f957edefd8c · outbound

This paper cites An economical and slo-guaranteed cloud storage service across multiple cloud service providers.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference An economical and slo-guaranteed cloud storage service across multiple cloud service providers

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:13.743479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 404875bf-ea2a-4282-8380-1d8c8e70444e · outbound

This paper cites In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 1049–1062, 2019.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 1049–1062, 2019

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:13.532020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0b93c78e-38ab-48d7-9432-b24199572a72 · outbound

This paper cites Slo-aware inference scheduler for heterogeneous processors in edge platforms.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Slo-aware inference scheduler for heterogeneous processors in edge platforms

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:13.353035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 78dc2b82-2319-4429-9d1b-ab29d95c4b08 · outbound

This paper cites an unresolved cited work.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:01:13.170274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8d4e7a25-c822-4722-905f-4fe02cfff7a8 · outbound

This paper cites Opt: Open pre-trained transformer language models, 2022.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Opt: Open pre-trained transformer language models, 2022

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:12.949214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0c149864-c14e-44bb-a681-4e2072572f4f · outbound

This paper cites S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput, June 2023.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference S$^{3}$: Increasing GPU Utilization during Generative Inference for Higher Throughput, June 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:12.686671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 67290b36-efaf-40ac-9a10-35b663ba8ed4 · outbound

This paper cites Kalbarczyk, Tamer Ba¸ sar, and Ravishankar K.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Kalbarczyk, Tamer Ba¸ sar, and Ravishankar K

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:12.456869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1aa6fd7e-ba90-4fdc-b3fc-eeb749ceffd6 · outbound

This paper cites Dlrover-rm: Resource optimization for deep recommendation models training in the cloud, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Dlrover-rm: Resource optimization for deep recommendation models training in the cloud, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:12.262751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 870f7e82-76da-4076-8975-762378b0ca5b · outbound

This paper cites Admission control and routing: Theory and practice.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Admission control and routing: Theory and practice

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:12.078603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 69b7102c-9e21-459f-b6cc-9a91251ff91c · outbound

This paper cites The llama 3 herd of models, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference The llama 3 herd of models, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:11.888905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c647c194-d9b8-4a96-9d06-05f2f1745537 · outbound

This paper cites Gemma 2: Improving open language models at a practical size, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Gemma 2: Improving open language models at a practical size, 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:07.496686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2223d29-da56-4ada-b03e-ebd070464eca · outbound

This paper cites Megatron-lm: Training multi-billion parameter language models using model parallelism, 2020.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Megatron-lm: Training multi-billion parameter language models using model parallelism, 2020

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:07.578575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc53416-df6e-476e-a39a-b87cb25263fb · outbound

This paper cites Sharegpt, 2023.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Sharegpt, 2023

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:11.673642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 12132cd1-53fd-46d2-8b78-365d8284488e · outbound

This paper cites Xing, Joseph E.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Xing, Joseph E

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:07.715642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67bdd9f0-3584-435c-ac05-be4f6e1f7177 · outbound

This paper cites Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving, July 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving, July 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:11.469493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d6efa4cf-8bc3-4d52-b094-b1867b149877 · outbound

This paper cites Azuretrace.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Azuretrace

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:11.203871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3bfbd2bc-654a-4daa-a4a0-81dfb60226be · outbound

This paper cites Efficient LLM Scheduling by Learning to Rank, August 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Efficient LLM Scheduling by Learning to Rank, August 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:10.845757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea2a501c-d317-4001-8ed6-47f7b538e28b · outbound

This paper cites LLM Inference Serving: Survey of Recent Advances and Opportunities, July 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference LLM Inference Serving: Survey of Recent Advances and Opportunities, July 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:10.496033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6e7be845-e55d-49ef-b698-6744e8ab2511 · outbound

This paper cites Splitwise: Efficient generative llm inference using phase splitting, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Splitwise: Efficient generative llm inference using phase splitting, 2024

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:08.307016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c411ed0c-61be-40a8-b174-46208c5ff672 · outbound

This paper cites Fairness in serving large language models.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Fairness in serving large language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:08.310744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d4cbf5a-0656-4f56-8c5b-25f4e63ffe0a · outbound

This paper cites FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:01:08.314236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e529240-54d4-4881-94b8-cbd8ad91c66e · outbound

This paper cites Enabling efficient batch serving for lmaas via generation length prediction, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Enabling efficient batch serving for lmaas via generation length prediction, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:10.126150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation df7a4217-9a31-4ae0-a8c1-5b87bc261274 · outbound

This paper cites Don’t stop me now: Embedding based scheduling for llms, 2024.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Don’t stop me now: Embedding based scheduling for llms, 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:01:09.819602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f6020374-55bf-46f2-a057-d32013c34a1d · outbound

This paper cites prompt.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference prompt

Reference 36

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:01:09.551537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed84c9c1-4808-48f5-8264-3f01d7550e4b · outbound

This paper cites an unresolved cited work.

SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference Unresolved cited work

Reference 37

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T13:01:09.166759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation c6f401d1-54fd-4a9e-b0f0-9371ee13bd67 · inbound

Execution Envelopes: A Shared Admission Contract for Backend AI Execution Requests cites this paper.

Execution Envelopes: A Shared Admission Contract for Backend AI Execution Requests SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:41:23.932858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dcc42ff6-60bb-48ab-bf2f-4314cf540ce3 · inbound

Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation cites this paper.

Demonstrating chart-plot: Closing the Last Mile of Academic Chart Generation SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-03T03:17:35.453716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b5055871-4286-4057-bb44-168a0674ab55 · inbound

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving cites this paper.

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T01:11:57.017686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aae20681-035e-4e0f-b68f-0b984d1c371d · inbound

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving cites this paper.

Trusted Floors Under Untrusted Learners: A Runtime Assured-SLO Guard for ML Serving SCORPIO: Serving the Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T07:31:30.609964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.