Pith. sign in

Paper Citation Record · LEDGER

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS

As of 20 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2509.06362.

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

pith.paper-citation-record.v1
2509.06362 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:49:32.385870Z

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 exact1
  • verified fuzzy22
  • unresolved8
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 74a61d0d-298b-424b-9f7d-54a7bbed734e · outbound

This paper cites A survey of knowledge enhanced pre- trained language models,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS A survey of knowledge enhanced pre- trained language models,

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:39.406238Z

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.

source=pdf_text observed=2026-08-04T23:49:28.635337Z digest=sha256:31b7276c4b1d7d7aec3f0f44bf9f55e3649fe2e2a0c7f3c7df3b94cce6e2543b

Observation cdfd3d60-1df8-494a-b8a1-ce72ba6292ec · outbound

This paper cites Model-as-a-service (maas): A survey,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Model-as-a-service (maas): A survey,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:39.123174Z

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.

source=pdf_text observed=2026-08-04T23:49:28.729778Z digest=sha256:b452498e430f0fcc479206ea06ae766e703801f3784651d963e8adfea46d8e59

Observation 4fd1bea9-233c-4f4c-91a4-39bb9eea191b · outbound

This paper cites The rise and potential of large language model based agents: a survey,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS The rise and potential of large language model based agents: a survey,

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:38.869277Z

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.

source=pdf_text observed=2026-08-04T23:49:28.806725Z digest=sha256:606021db593667f9aec3d6bab1b7cc90ed0f81dea99f0f885911d658826c4b00

Observation 01d9ad81-0745-4692-a6d3-a127b2eea998 · outbound

This paper cites LLMs Meet Multimodal Generation and Editing: A Survey.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS LLMs Meet Multimodal Generation and Editing: A Survey

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:29.000176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:29.000176Z digest=sha256:aa786338c131d582e95d44d7d70ab09997e3fd5c953c26b2fc6e70ad0c5376ad

Observation dbf870fe-0944-4157-94e3-a32841efe5ee · outbound

This paper cites Intelligent Condition Monitoring of Industrial Plants: An Overview of Methodologies and Uncertainty Management Strategies.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Intelligent Condition Monitoring of Industrial Plants: An Overview of Methodologies and Uncertainty Management Strategies

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:29.124747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:29.124747Z digest=sha256:bb951f5da8fc52d1e21a5745e60ee78690f0535437a078e0181e0ec64e3154dd

Observation d9ed25c2-6a76-479b-b27f-ccf7755b806d · outbound

This paper cites SLO-Aware Scheduling for Large Language Model Inferences.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS SLO-Aware Scheduling for Large Language Model Inferences

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:29.217377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:29.217377Z digest=sha256:e58f1326beb611cdbf89e7bceb4e935239597ddd111bac8bc4db0de333a09c72

Observation 78a59785-b76e-4e89-a2ae-0d0da3823245 · outbound

This paper cites Control Industrial Automation System with Large Language Model Agents.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Control Industrial Automation System with Large Language Model Agents

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:29.352254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:29.352254Z digest=sha256:1e064460e4522018aaa9ef76f6a7a57c947850b5602eabc018430b9639d37552

Observation 75259ac8-05ae-48b1-ad69-0600ff30b7e7 · outbound

This paper cites Advanced intelligent manufactur- ing in process industry using industrial artificial intelligence,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Advanced intelligent manufactur- ing in process industry using industrial artificial intelligence,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:38.534744Z

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.

source=pdf_text observed=2026-08-04T23:49:29.414094Z digest=sha256:cc0b6b11a94d79acd6089d5994ed145133c0e6cae6eccbc6f35dc7fc1957250f

Observation dee9b8c4-157d-4e70-894b-3fc0c29b6624 · outbound

This paper cites Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-08-04T23:49:32.788744Z

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.

source=pdf_text observed=2026-08-04T23:49:29.458736Z digest=sha256:e90d13e5f94cb982b37a2f969b12a5b8004db67d960b34f9fc2b76154b7187b3

Observation 45c0bc62-3d7e-45f2-86b6-c84c40d41f51 · outbound

This paper cites Towards a framework for local interrogation of ai ethics: A case study on text generators, academic integrity, and composing with chatgpt,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Towards a framework for local interrogation of ai ethics: A case study on text generators, academic integrity, and composing with chatgpt,

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:38.232145Z

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.

source=pdf_text observed=2026-08-04T23:49:29.554645Z digest=sha256:9131904b41f57702f1e53649a5659ae197106f6b1764e9fae4c931bbde0c8e3c

Observation 4ced0d2f-1842-43ac-98f0-cea6f05e3024 · outbound

This paper cites Alpaserve: Statistical multiplexing with model parallelism for deep learning serving,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Alpaserve: Statistical multiplexing with model parallelism for deep learning serving,

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:37.955159Z

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.

source=pdf_text observed=2026-08-04T23:49:29.648304Z digest=sha256:b45a5a9b6db1113b5b9d00ece43045d98ed953b2ef88a11bf53ba0301fc3e7d5

Observation 262a0f9c-ec69-4b92-a5b1-e1d8d0129895 · outbound

This paper cites Alpa: Automating inter- and intra- operator parallelism for distributed deep learning,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Alpa: Automating inter- and intra- operator parallelism for distributed deep learning,

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:37.658864Z

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.

source=pdf_text observed=2026-08-04T23:49:29.768834Z digest=sha256:0679778253867e7bdaaa91037a1395f4a8aac184a24f4d830a3b8e097e8063f0

Observation f487e54d-dc5b-4a44-8edb-8894d0412490 · outbound

This paper cites Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:37.302835Z

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.

source=pdf_text observed=2026-08-04T23:49:29.964752Z digest=sha256:315458163a92891abc42f2f12873c351230031d47484b0c56b696449ce7afaa5

Observation 396035ee-f993-4a2e-8c65-843a8102b5fd · outbound

This paper cites Efficient large-scale language model training on GPU clusters using megatron-lm,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Efficient large-scale language model training on GPU clusters using megatron-lm,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:36.894744Z

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.

source=pdf_text observed=2026-08-04T23:49:30.094754Z digest=sha256:96535db3fc0df8af40374aeae95a56920b785d280c5e386fda103ff8bbbc4a55

Observation 47803e7c-08e8-4858-b9f6-80caa269b530 · outbound

This paper cites Gpipe: Efficient training of giant neural networks using pipeline parallelism,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Gpipe: Efficient training of giant neural networks using pipeline parallelism,

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:36.679905Z

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.

source=pdf_text observed=2026-08-04T23:49:30.178713Z digest=sha256:97c6fcab63cd37b785e44ec560c3d3b8368d049404fd3f0f0889a18cfc47db85

Observation b0045f25-9a30-42b5-a352-93e7e4598008 · outbound

This paper cites Pipedream: generalized pipeline parallelism for DNN training,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Pipedream: generalized pipeline parallelism for DNN training,

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:36.297887Z

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.

source=pdf_text observed=2026-08-04T23:49:30.364748Z digest=sha256:10ddd7fe63f44cd9c3f7fc0bc96505ecc9db4387014a9c1176ffe2e9ce392443

Observation 64fada89-301c-49a8-a594-18b4feec8e28 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Efficient memory management for large language model serving with pagedattention,

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:36.024293Z

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.

source=pdf_text observed=2026-08-04T23:49:30.535274Z digest=sha256:923e75378121a102ba6371a6d7794e617121f2daab6d3b1e4c5ddb40c1a09c79

Observation 1b160eab-3434-4b6b-95f9-965e9d26893f · outbound

This paper cites Sglang: Efficient execution of structured language model programs,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Sglang: Efficient execution of structured language model programs,

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:35.675197Z

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.

source=pdf_text observed=2026-08-04T23:49:30.665181Z digest=sha256:9fdec190ccbfd200b95ef366462453e7491a93c60bd9530c2d6f4ba1b74ef1d5

Observation 37ffac39-53e4-43bc-93ab-a9d1e5025f2e · outbound

This paper cites Orca: A distributed serving system for transformer-based generative models,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Orca: A distributed serving system for transformer-based generative models,

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:35.278621Z

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.

source=pdf_text observed=2026-08-04T23:49:30.812286Z digest=sha256:3d40b556996fe1efe94ee7fcc048dbc96a99fd01d3ccff7dab3060bfdba6891a

Observation f19792ce-130f-41e5-9590-c5c6ee47f099 · outbound

This paper cites DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM Serving.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM Serving

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:30.927283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:30.927283Z digest=sha256:9eb09b731d63e560b59491fd523ba353fa11214ad6cd1ea8914e75e50fced11c

Observation c22c024e-289e-4079-9aca-226c9eb07d30 · outbound

This paper cites Borg, omega, and kubernetes,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Borg, omega, and kubernetes,

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:35.027006Z

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.

source=pdf_text observed=2026-08-04T23:49:31.085235Z digest=sha256:ec87941fa866bd4effdb6b45be74d30eaf3473ad46899af852b33d5de21cb75d

Observation 80145378-544c-439d-85da-45c2a39cb1b9 · outbound

This paper cites Nvidia dynamo.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Nvidia dynamo

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:34.766385Z

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.

source=pdf_text observed=2026-08-04T23:49:31.162926Z digest=sha256:de965de9c9380361f089f0584af1e53e747aff5b1212015de358ef58a505f708

Observation 1ce99e3c-fdb0-4d9b-a830-b1114f96a3b9 · outbound

This paper cites Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:31.251317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:31.251317Z digest=sha256:ed610f8b5fecb080898f10e72e9d69711a8c9c4256833efa476aa9db4bd63c70

Observation 9b8f9ffc-1cce-4abb-b71c-d940234800cf · outbound

This paper cites Beyond data and model parallelism for deep neural networks,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Beyond data and model parallelism for deep neural networks,

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:34.387490Z

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.

source=pdf_text observed=2026-08-04T23:49:31.364752Z digest=sha256:36c42664e06c7987af9e91d34e1869d0fbffcaba7f33e8980285901240cd4e4d

Observation fdb18142-a848-48c6-8916-c64d8e36612f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:31.443587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:31.443587Z digest=sha256:113d213cb9a030c6ac8e86276704644a3d69bdeb76b59a6e9ee3cc72d67748b9

Observation 463ce327-a4af-43b6-b69f-ecc7ea68e078 · outbound

This paper cites Qwen Technical Report.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Qwen Technical Report

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-04T23:49:31.540516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T23:49:31.540516Z digest=sha256:e78276650db7938f30b60c78c5f3e72b96b6ba58ef3ac6b468083fc61a8b63a2

Observation b3b5a29f-e7c8-4be7-8096-d1be4a47db34 · outbound

This paper cites Amazon ec2.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Amazon ec2

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:34.163313Z

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.

source=pdf_text observed=2026-08-04T23:49:31.637669Z digest=sha256:fd5e78c460344020d5aa57a168880857844c13c2009ef4b832d9ff3e0de3caa9

Observation 8f381536-4d64-4d25-9a78-a8948207f133 · outbound

This paper cites Serving dnns like clockwork: Performance predictability from the bottom up,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Serving dnns like clockwork: Performance predictability from the bottom up,

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:33.936952Z

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.

source=pdf_text observed=2026-08-04T23:49:31.783870Z digest=sha256:bb444a4b553cd2567f7012c34bd071d6a41744f289ee13f69aca889b1e38fb51

Observation 9ae1fdde-433d-4883-92aa-a3c2d40bfc11 · outbound

This paper cites Inferline: latency-aware provisioning and scaling for prediction serving pipelines,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Inferline: latency-aware provisioning and scaling for prediction serving pipelines,

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:33.709785Z

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.

source=pdf_text observed=2026-08-04T23:49:31.964740Z digest=sha256:9497ff2d3724d1a4c9a80fab1e80dcdb3cfd929c5714fabbe1e45b97308c38d7

Observation ddf0e0c5-df59-40d8-ad5c-b888e4ec8044 · outbound

This paper cites Nexus: a GPU cluster engine for accelerating dnn-based video analysis,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Nexus: a GPU cluster engine for accelerating dnn-based video analysis,

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:33.414090Z

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.

source=pdf_text observed=2026-08-04T23:49:32.125227Z digest=sha256:c3a20b8e78f3922ffe501837d99fa49ef1f1e46246a292ccfa9c6d40c450d6b6

Observation 3b069fc1-dd10-4deb-afe0-acb210fe432d · outbound

This paper cites Clipper: A low-latency online prediction serving system,.

MaaSO: SLO-aware Orchestration of Heterogeneous Model Instances for MaaS Clipper: A low-latency online prediction serving system,

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-04T23:49:33.161438Z

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.

source=pdf_text observed=2026-08-04T23:49:32.385870Z digest=sha256:2bb4d7464301d29e0c2463f917ae32ea3a7592112a1b760348f7e32fc7291541

Pith citing papers

No inbound Pith citation observations are available.