Pith. sign in

Paper Citation Record · LEDGER

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices

As of 20 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2506.17538.

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

pith.paper-citation-record.v1
2506.17538 v1

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:35:08.525600Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

56 of 56 outbound references displayed

  • verified exact0
  • verified fuzzy38
  • unresolved17
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cde39ea9-3663-4bc1-b523-0935bc8fc729 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:07.874863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:07.874863Z digest=sha256:53bfc6035bf167184e1617ac0dd06ffc593592eb709163e6cfed824270ffc65c

Observation 28b5ee08-c002-4da0-8d15-325bfd25ebb1 · outbound

This paper cites Llama 3.2 3b: Multilingual large language model.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Llama 3.2 3b: Multilingual large language model

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:11.447991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.879699Z digest=sha256:f3575e2ba198527734e2e70ece49be067209456b0479f883187d9be9ef9c3848

Observation e773bc3d-5dfa-4253-85ad-1d31b08d60df · outbound

This paper cites Gemini nano with the google ai edge sdk, 2025.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Gemini nano with the google ai edge sdk, 2025

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:11.384822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.889714Z digest=sha256:af656c4bb366d93529064fa24e6ac099d120e429323c556014fd9a1fe55758a3

Observation c8f67efc-530b-49ff-a96c-07fa91246b3a · outbound

This paper cites Introducing apple intelligence, the personal intelligence system that puts powerful generative models at the core of iphone, ipad, and mac, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Introducing apple intelligence, the personal intelligence system that puts powerful generative models at the core of iphone, ipad, and mac, 2024

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:11.254822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.895122Z digest=sha256:5b839d09ef63e154553c96e1ef1f5eb8076bbe8f016bf1ac2e755018e6f87626

Observation 76dd08f9-1e7f-4b6e-aecf-619bbb5c75a1 · outbound

This paper cites Macbook pro 14- and 16-inch – technical specifications, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Macbook pro 14- and 16-inch – technical specifications, 2024

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:11.114741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.905457Z digest=sha256:72643f06528a3569c2c120b3a0b5164fcb5d5b23b07998bd55860c765e8167c8

Observation baacd431-efe3-4d64-9801-73ccfb2abeee · outbound

This paper cites Stable diffusion web ui, 2022.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Stable diffusion web ui, 2022

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.996045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.909039Z digest=sha256:58aaf18ca07f09a2ea64b0b2f7d24abc6e2ee9408e5d208da2e4c4ce011e002b

Observation 9347a45a-7d67-466c-bac9-2146d4dd075a · outbound

This paper cites Litellm: Python sdk and proxy server for unified llm access, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Litellm: Python sdk and proxy server for unified llm access, 2024

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.949576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.912661Z digest=sha256:fae3bea1d89c9ccdc20c9b2c22e15a7b27a8ea46c3d4ebf986f64c7182b6a660

Observation 5996b7d4-9872-45ff-b2e3-035f19a2db1b · outbound

This paper cites Lawrence Zitnick.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Lawrence Zitnick

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:07.924821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:07.924821Z digest=sha256:78c6257193b58a577feaf4c3b39ca291359b27d59455ba25341bac19076f4c51

Observation 7b88a351-a19f-4a72-8696-e59b770af7c3 · outbound

This paper cites Intel ® performance counter monitor.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Intel ® performance counter monitor

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.905503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.957468Z digest=sha256:a977da132a774826fb4614a5eb1634979068e826d762fbae5f18137a5ffdc236

Observation a67070c9-8d7b-48dd-92e5-6f6608948195 · outbound

This paper cites Nvidia data center gpu manager (dcgm).

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Nvidia data center gpu manager (dcgm)

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.704742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.971332Z digest=sha256:5f252959f87f0a64887646cb273454694e0171d6df4b23a230727e2c9ce7cb4b

Observation c0f921b6-8b3c-4321-aa2c-49713e493dcc · outbound

This paper cites Nvidia multi-process service (mps).

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Nvidia multi-process service (mps)

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.594412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.975645Z digest=sha256:f8ffd42da5eab99c272bf1b07e8cca58bbb392b4121d1aa214db9cbc454e6514

Observation 6ee18a91-9d1f-4f8b-9540-b9fb4fb12f81 · outbound

This paper cites Earnings-21: A Practical Benchmark for ASR in the Wild.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Earnings-21: A Practical Benchmark for ASR in the Wild

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:07.979254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:07.979254Z digest=sha256:b3fe6f50be05f1ddf613bdd978abc0d9f83099710ca4d32ca8d2bfec4aa8e209

Observation b78d1334-309e-4073-84c5-30964e61bacc · outbound

This paper cites Mobile-bench: An evaluation benchmark for llm-based mobile agents, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Mobile-bench: An evaluation benchmark for llm-based mobile agents, 2024

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.436357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:07.983617Z digest=sha256:08deec73ccaeae28fe9d55fc8ac58529d1734803bc215ab3e3418809436cdcd4

Observation e87c369b-2c7a-47b9-ba63-37f3659551cc · outbound

This paper cites Qlora: Efficient finetuning of quantized llms, 2023.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Qlora: Efficient finetuning of quantized llms, 2023

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:07.987826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:07.987826Z digest=sha256:4ba1d0a3aeca5027795dc3721edb7e496668c814b442d6ae144fe5aa510dcb79

Observation 2354a223-8ced-4898-86af-edb7739e766c · outbound

This paper cites Gptq: Accurate post-training quantization for generative pre-trained transformers, 2023.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Gptq: Accurate post-training quantization for generative pre-trained transformers, 2023

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:07.995563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:07.995563Z digest=sha256:7ac74520f85a0db72192dfceb931aee1630047ddb70a1ec361527692732a75e3

Observation d4539482-5036-497d-a329-2a3494cb477f · outbound

This paper cites llama.cpp: Llm inference in c/c++, 2023.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices llama.cpp: Llm inference in c/c++, 2023

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.397935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.009958Z digest=sha256:ef3ff91a0f83d6bb26699c88647b78640326a57e7518b8a777e9be65b0e32ed6

Observation 0fae8d99-3c26-45be-9a39-84add379d777 · outbound

This paper cites Stabletoolbench: Towards stable large-scale benchmarking on tool learning of large language models, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Stabletoolbench: Towards stable large-scale benchmarking on tool learning of large language models, 2024

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.285227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.018242Z digest=sha256:0d2c2af3a6cc6c80f64cbadae47011aee4373815e9d7a8157110d0f9bca0fb04

Observation eaa80891-6721-44ac-b9e5-84a0615bef5b · outbound

This paper cites A critical review of large language models: Sensitivity, bias, and the path toward specialized ai.Quantitative Science Studies, 5(3):736–756, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices A critical review of large language models: Sensitivity, bias, and the path toward specialized ai.Quantitative Science Studies, 5(3):736–756, 2024

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.222893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.024340Z digest=sha256:a55bc7a7aaff298536311f78ee5bd028d91ef9e99e8f9bc48e8ef558a0dc1e2b

Observation 786b1042-65f1-4c67-beeb-4d22b307a4b2 · outbound

This paper cites Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.172691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.032130Z digest=sha256:02cc2707be27043e95507434583c3feefa5619280c0cc8d4d23f146a233ccb33

Observation 465b8c39-805d-4b41-900e-8a0ce14715ec · outbound

This paper cites Hybrid slm and llm for edge- cloud collaborative inference.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Hybrid slm and llm for edge- cloud collaborative inference

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.134184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.036690Z digest=sha256:66609477d91e22941827901ef2f517f26238f2086e0b86abdbc83c689ef8ae5b

Observation dce1f626-b9f7-4edc-92fe-598e7176e6c1 · outbound

This paper cites Searching for mobilenetv3.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Searching for mobilenetv3

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.052383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.052383Z digest=sha256:e987eec951fe0604f6525fdd18d60db55af4fd07e6b9c71a3e51c4c37cb5bfce

Observation 3a004605-7fa7-42b1-b88d-84c559243a56 · outbound

This paper cites Running average power limit (rapl) energy reporting.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Running average power limit (rapl) energy reporting

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.102234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.062991Z digest=sha256:ae7053577200a1f432e362400c17788bb7655afea098b802eb0160b179d3bfd4

Observation 915e4c92-6a8d-4b9e-9d4a-ed966c555a1b · outbound

This paper cites Benchmarking edge ai platforms for high-performance ml inference, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Benchmarking edge ai platforms for high-performance ml inference, 2024

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.050290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.085308Z digest=sha256:4a5dffddc85a37ef8143e98a673473297b76fe4a56f244f0573152029f124952

Observation 35ef2d87-3a53-4021-a0f4-522ecb46ad5a · outbound

This paper cites Melting point: Mobile evaluation of language transformers, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Melting point: Mobile evaluation of language transformers, 2024

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:10.032285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.111273Z digest=sha256:92720250fe2edc11c588a7414b8047827589910dd14b07549167561bcc636330

Observation 3b55ec8f-95c5-4918-bec5-8d3999c6f136 · outbound

This paper cites Api-bank: A comprehensive benchmark for tool-augmented llms, 2023.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Api-bank: A comprehensive benchmark for tool-augmented llms, 2023

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.115170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.115170Z digest=sha256:076b685e924030e90d75a3a11ff4e1659b4bbed98d7e216dcf2ef2fad83947fe

Observation 28024f20-52eb-4a0f-84cb-abe5028f7f5c · outbound

This paper cites Snapfusion: Text-to-image diffusion model on mobile devices within two seconds.Advances in Neural Information Processing Systems, 36:20662–20678, 2023.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Snapfusion: Text-to-image diffusion model on mobile devices within two seconds.Advances in Neural Information Processing Systems, 36:20662–20678, 2023

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.944751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.145362Z digest=sha256:aa627e4a321a610ed07af88664e0e7fbf9b3eacc6a0e7e8958e495a239b44c73

Observation 01fabfdb-64ae-4271-b5e0-e3d959e29e4c · outbound

This paper cites Palmbench: A comprehensive benchmark of compressed large language models on mobile platforms, 2025.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Palmbench: A comprehensive benchmark of compressed large language models on mobile platforms, 2025

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.884745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.167609Z digest=sha256:691f659fd82de4ac5f69775facf6993b4236f71d3203778cad4ad59be4e8b175

Observation 1334d925-e154-45be-82be-fdc07c27ab99 · outbound

This paper cites Awq: Activation-aware weight quantization for llm compression and acceleration, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Awq: Activation-aware weight quantization for llm compression and acceleration, 2024

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.183025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.183025Z digest=sha256:7a75d7f9fdbb2284bf4730f079719f76ba9112e9fca9e2ed1fd21a05fa996539

Observation 6344b794-dfc0-401e-8af2-abd8daee2be0 · outbound

This paper cites Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.205979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.205979Z digest=sha256:9dbf9e4e7bd491e8063d9fe242ea1be5ae939496b5f413f196442985b6ecf043

Observation ddbfa408-e3da-4ca7-933e-bbb29155d3f0 · outbound

This paper cites AgentBench: Evaluating LLMs as Agents.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices AgentBench: Evaluating LLMs as Agents

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.219056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.219056Z digest=sha256:1e9205110a58321a89ca375d7ee187ddb29db3652718ac725bac37c91e42b3f4

Observation 06bec722-e593-490c-a7d6-e231c08d4aba · outbound

This paper cites Turning whisper into real-time transcription system.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Turning whisper into real-time transcription system

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.782187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.225512Z digest=sha256:d1b49bdc5cc63a078863da24bcadacbe667baa539dd9d91630db4e737ed82699

Observation 0cdb84b0-1598-4ed4-8d54-007157ffb5dc · outbound

This paper cites AIOS: LLM Agent Operating System.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices AIOS: LLM Agent Operating System

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.232724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.232724Z digest=sha256:545fb039c00cd1c1af2fd7c4ec7b05d75b081e1a0cdea3bffde1fdf87fb6015f

Observation 53e6cc89-c86c-407b-aff9-e3e5e49c1ace · outbound

This paper cites Mo- bileaibench: Benchmarking llms and lmms for on-device use cases, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Mo- bileaibench: Benchmarking llms and lmms for on-device use cases, 2024

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.734939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.236656Z digest=sha256:9a844b917356c54d543bfd707829de830574ed7ec0d6ca308a4b137e3795ed23

Observation 3bd499e5-a156-45b3-a383-1e695d9a1237 · outbound

This paper cites Green contexts - cuda driver api.https://docs.nvidia.com/cuda/cuda-driver- api/group__CUDA__GREEN__CONTEXTS.html, 2025.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Green contexts - cuda driver api.https://docs.nvidia.com/cuda/cuda-driver- api/group__CUDA__GREEN__CONTEXTS.html, 2025

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.719280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.243999Z digest=sha256:452e45de4df3bc00b12182bcfd537f63ea4da6194d174b3bc47c155963f55fa0

Observation 33c5e2d9-9fae-4d3e-8d5c-66f4092f8fd5 · outbound

This paper cites Nvidia multi-instance gpu (mig).

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Nvidia multi-instance gpu (mig)

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.709628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.249870Z digest=sha256:3e36bc926e4eec43d00a9cae04fd7b89d0a7fb84e8d65dbd394c71fc05a0d790

Observation eb6c69c4-669f-4ce6-9d67-df8d29eface8 · outbound

This paper cites NVIDIA, August 2018.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices NVIDIA, August 2018

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.697207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.254675Z digest=sha256:86977659c3902c112ecbd84be6d2ddcfcf3eeab7f4451816e1430e158b285733

Observation 617db296-5dfd-4086-a702-e4406c6941cb · outbound

This paper cites Nvidia management library (nvml).https://developer.nvidia.com/ management-library-nvml, 2025.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Nvidia management library (nvml).https://developer.nvidia.com/ management-library-nvml, 2025

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.673523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.261596Z digest=sha256:a82176d4ab7adad914ddf4d808ff825fcd038c90f2adf576c74aac01dfef6e5e

Observation 27655bf3-4c5d-4d7f-8648-ec4755a315d6 · outbound

This paper cites an unresolved cited work.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-06T23:35:09.661521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.267144Z digest=sha256:5101ceb0c9e39eb36906e7f013d960738a4edfaba2e0adad376be8c587ef97d9

Observation a16a33a5-8583-47f5-8dc6-e813d90c3996 · outbound

This paper cites Attention u-net: Learning where to look for the pancreas.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Attention u-net: Learning where to look for the pancreas

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.612494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.275550Z digest=sha256:0c77100e03b8ffa5bee7385e22d3cb6461f28d50f3e96becf149709a49a67612

Observation 335c40c3-d47d-40cc-98ef-5f0f9ecc52c9 · outbound

This paper cites Openai api, 2020.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Openai api, 2020

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.494745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.289722Z digest=sha256:f4202fdce719ac718265e6ec44f6309e64d4db4cebed867d60f6ddc7af102f12

Observation bcf9b970-33b6-4c9c-979b-45b7b5c71914 · outbound

This paper cites Memgpt: Towards llms as operating systems.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Memgpt: Towards llms as operating systems

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.293738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.293738Z digest=sha256:461f8304de20741852733802ae00b1a95263aaa2a64f83d139bd6e7ab2079ddd

Observation 57e1adcc-bd4e-4c8e-b7f7-34586eb35c56 · outbound

This paper cites Snapdragon x elite product brief.https://www.qualcomm.com/ content/dam/qcomm-martech/dm-assets/documents/Product-Brief-Snapdragon- X-Elite.pdf, October 2023.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Snapdragon x elite product brief.https://www.qualcomm.com/ content/dam/qcomm-martech/dm-assets/documents/Product-Brief-Snapdragon- X-Elite.pdf, October 2023

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.354812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.324748Z digest=sha256:ed57e157d4b12c570f0a0b7952e557bf5b3280109a76764bab635ea7b055d385

Observation 69d4e83f-fa2c-43d8-8301-0fca857564da · outbound

This paper cites Robust speech recognition via large-scale weak supervision, 2022.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Robust speech recognition via large-scale weak supervision, 2022

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.348765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.348765Z digest=sha256:fe83e43a91aec5d42dd78944e160123ff2cd74d88222b6516fe86fafd4185b8b

Observation fa917fc4-c001-4d64-8250-d22fa0659983 · outbound

This paper cites Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Scott Gardner, Itay Hubara, Sachin Idgunji, Thomas B

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.194749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.353500Z digest=sha256:cd9a64efa52c9cee750a4d7da31e78b63d61dbc66574f4e823dc1e6601c97285

Observation e4a9fc49-1da4-472f-8389-ebf13cd5c93b · outbound

This paper cites ‘smolagents‘: a smol library to build great agentic systems.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices ‘smolagents‘: a smol library to build great agentic systems

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.142377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.365430Z digest=sha256:0443635338b39687f1577bbef13fa05adfd466a262e95adc04dba362a43a1857

Observation cfbab400-b993-4b3a-b075-e22fb4ac73a1 · outbound

This paper cites Specialist or generalist? instruction tuning for specific NLP tasks.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Specialist or generalist? instruction tuning for specific NLP tasks

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.130918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.382089Z digest=sha256:8953039c763367564163e230a209e5e11082dc41ec7b665828d53f3a9861c6f0

Observation 591bc2a7-5b8e-4b80-8acc-1c1fa7bc6be8 · outbound

This paper cites Orion: Interference-aware, fine-grained gpu sharing for ml applications.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Orion: Interference-aware, fine-grained gpu sharing for ml applications

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.110780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.388624Z digest=sha256:1f07ee5fb2871ede273d80ee4ee547f95103e665a1c0f1561e260d139c2b2439

Observation 3a242025-dc8f-40d9-9dde-4ca905e0a5a6 · outbound

This paper cites Stable diffusion 3.5 medium turbo, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Stable diffusion 3.5 medium turbo, 2024

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.099289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.401453Z digest=sha256:11ba7dd0ab88e886644ca087eacee9c139a648c18dd32ef5401ccc4a4ad49089

Observation fe64f7fa-9c24-45dd-8613-9dc5a900243c · outbound

This paper cites Large language model performance benchmarking on mobile platforms: A thorough evaluation.arXiv preprint arXiv:2410.03613, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Large language model performance benchmarking on mobile platforms: A thorough evaluation.arXiv preprint arXiv:2410.03613, 2024

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.404936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.404936Z digest=sha256:6c97af44437ee06482f8281578b88592f413e07c0515bb5acd4710c57285aa0c

Observation 3f0f6806-6b7e-4941-af00-4d9cc7736351 · outbound

This paper cites Crab: Cross-environment agent benchmark for multimodal language model agents, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Crab: Cross-environment agent benchmark for multimodal language model agents, 2024

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.088830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.408716Z digest=sha256:7f5d124418a4d716b39ee70958e7ea3cbbd7439ea67067157a0fe4e8fa86ed94

Observation fbcf175f-d9cc-443e-bcb2-9af5d7e80549 · outbound

This paper cites Qwen2.5 Technical Report.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Qwen2.5 Technical Report

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.415971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.415971Z digest=sha256:31b26133ebcc9bc484c5f61d8fc13ae7b2cd37f3d350e66e56ddf82bce9d59b4

Observation 83d26fd9-e693-43f2-adc4-66fee72e734f · outbound

This paper cites an unresolved cited work.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Unresolved cited work

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-06T23:35:08.428862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:08.428862Z digest=sha256:48f2739bed1a8ae15ab4294e8f99e4b0f36b01e7131bf4b4ca38642cf77a4481

Observation 962cde96-9f27-4109-84d9-44b2587edb6a · outbound

This paper cites Faaswap: Slo-aware, gpu-efficient serverless inference via model swapping, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Faaswap: Slo-aware, gpu-efficient serverless inference via model swapping, 2024

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.061990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.439718Z digest=sha256:5037f9c4b3ebf0c80b3fda2a07308e141f12b8c637bb55be4016cb5144fc97b1

Observation 6c152d9f-d345-4b9a-8461-a9b88ae2c5af · outbound

This paper cites Mobilediffusion: Instant text-to-image generation on mobile devices, 2024.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Mobilediffusion: Instant text-to-image generation on mobile devices, 2024

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.049211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.454747Z digest=sha256:4471928fa71415c4649f1cd7610938fdd1ca4096dced32b08a9491173f260338

Observation 2c87434d-288d-4128-b60f-ec78dcac9d7d · outbound

This paper cites brainstorm.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices brainstorm

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:35:09.022722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-06T23:35:08.525600Z digest=sha256:750c488d38148bdd320fc3bc3283acfd0e3dec34ed879b34a6cb2367fd6a4cc8

Observation 59b42814-11c4-4acd-bada-538cfadc42cf · outbound

This paper cites an unresolved cited work.

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices Unresolved cited work

Reference 2025

Resolution
parse uncertain
no resolver link, observed 2026-08-06T23:35:07.965408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:35:07.965408Z digest=sha256:734220ef5712caaa56d45391428a7405417f8b73e27aeec71d4cbffe69cbd977

Pith citing papers

No inbound Pith citation observations are available.