Paper Citation Record · LEDGER

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities

As of 16 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2412.00408.

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

pith.paper-citation-record.v1
2412.00408 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T05:29:37.615787Z

measured 41 of 41 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 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

41 of 41 outbound references displayed

verified exact0
verified fuzzy38
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7bebb4af-5443-403c-be28-d0adde046e60 · outbound

This paper cites Introducing chatgpt,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Introducing chatgpt,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.114220Z

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 17fe12d9-4f9a-49e2-9373-22486fc3ee65 · outbound

This paper cites Multilayer fee dforward networks are universal approximators,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Multilayer fee dforward networks are universal approximators,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.103433Z

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 a27fd3a7-9c59-4a9f-a725-3a438452a92e · outbound

This paper cites Gaussian error linear units (gelus),.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Gaussian error linear units (gelus),

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.092053Z

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 8ef5c3fc-cc90-45ad-a124-20e4552bc641 · outbound

This paper cites Attention is all you need,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Attention is all you need,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.069035Z

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 001de6c2-d927-48a7-b27f-39b88dcd746c · outbound

This paper cites Nn-lut: neural approximation of non-linear operations for efﬁcien t transformer inference,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Nn-lut: neural approximation of non-linear operations for efﬁcien t transformer inference,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.058539Z

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 15a99da5-fb92-4b93-bd92-72807d773b2c · outbound

This paper cites Peano -vit: Power- efﬁcient approximations of non-linearities in vision tran sformers,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Peano -vit: Power- efﬁcient approximations of non-linearities in vision tran sformers,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.047464Z

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 2db7d1a4-4099-4687-baef-952d9d2e3770 · outbound

This paper cites Ml-pla c: Multiplierless piecewise linear approximation for nonlin ear function evaluation,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Ml-pla c: Multiplierless piecewise linear approximation for nonlin ear function evaluation,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.035951Z

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 9e67dbf1-c9dd-445c-9a4e-8a3e2754d0ff · outbound

This paper cites Hardware-efﬁcient softmax approximation for self-attention networks,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Hardware-efﬁcient softmax approximation for self-attention networks,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.024459Z

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 d42dc450-5846-4d6b-a88c-bbaa94cd3f8c · outbound

This paper cites Softermax: Hardware/software co-design of an efﬁcient so ftmax for transformers,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Softermax: Hardware/software co-design of an efﬁcient so ftmax for transformers,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.013000Z

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 5c25f0dc-bc70-4d9d-a311-f15c930ce600 · outbound

This paper cites A fast, compact approximation of th e exponential function,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities A fast, compact approximation of th e exponential function,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.001612Z

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 cdd3c068-a7cd-4dff-9dd9-2d10817a1a5d · outbound

This paper cites Ieee standard for ﬂoating-point arithmetic,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Ieee standard for ﬂoating-point arithmetic,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.991218Z

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 014f5894-5357-4b22-a43b-da46000178cc · outbound

This paper cites Simple multiple precision algorithms for exponential functions [tips and t ricks],.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Simple multiple precision algorithms for exponential functions [tips and t ricks],

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.979714Z

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 d1bdd336-8b50-4d0a-88a0-99b313757c2f · outbound

This paper cites TensorFlow: Large-scale machine learning on heterogeneo us systems,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities TensorFlow: Large-scale machine learning on heterogeneo us systems,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.968195Z

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 dd447936-5613-4999-aa2c-16e9c3fcebde · outbound

This paper cites Visionﬁve 2 datasheet,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Visionﬁve 2 datasheet,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.957459Z

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 d904b55f-d98c-4412-8ef1-2244d0143884 · outbound

This paper cites Imagenet: A large-scale hierarchical image database,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Imagenet: A large-scale hierarchical image database,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.945020Z

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 5f3a642f-07a0-47ad-bec3-b032d43d572c · outbound

This paper cites Libr ispeech: An asr corpus based on public domain audio books,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Libr ispeech: An asr corpus based on public domain audio books,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.933297Z

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 a3ba0686-f42a-4d3f-97a0-95a3480484d9 · outbound

This paper cites Hellaswag: Can a machine really ﬁnish your sentence?.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Hellaswag: Can a machine really ﬁnish your sentence?

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.922472Z

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 e368a388-75e3-49ea-b84d-e9b8bcb960f7 · outbound

This paper cites Raspberry pi 5,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Raspberry pi 5,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.910570Z

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 0d556b6e-3a99-4fcd-908f-bd3811cb25e7 · outbound

This paper cites Raspberry pi zero 2 w,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Raspberry pi zero 2 w,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.900076Z

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 a02bb970-a875-4145-8510-9bf095d0ccfa · outbound

This paper cites Amd epyc™ 7002 series processors: A new standard for the modern data center,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Amd epyc™ 7002 series processors: A new standard for the modern data center,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.889489Z

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 0ab505c7-5705-408f-88e5-86b8efddbab5 · outbound

This paper cites An image is worth 16x16 words: Trans- formers for image recognition at scale,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities An image is worth 16x16 words: Trans- formers for image recognition at scale,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.877739Z

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 f6d1516f-c6c5-4093-8a67-293300577062 · outbound

This paper cites Swin transformer: Hierarchical vision transforme r using shifted windows,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Swin transformer: Hierarchical vision transforme r using shifted windows,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.866725Z

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 a09ba3f3-7585-4b53-aa20-2de8f2de3126 · outbound

This paper cites A convnet for the 2020s,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities A convnet for the 2020s,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.854922Z

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 25c3fcb9-6002-4ab1-a6c5-012b054b6a01 · outbound

This paper cites Y olov8,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Y olov8,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.844373Z

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 21145929-d4e0-4600-8ff3-a95640d11108 · outbound

This paper cites Fast Segment Anything.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Fast Segment Anything

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T05:29:37.549859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd2e5eaf-e328-44fb-8bbe-f5f344e4a1a5 · outbound

This paper cites Robust speech recognition via large-scale w eak supervi- sion,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Robust speech recognition via large-scale w eak supervi- sion,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.832419Z

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 dabd77da-3ae0-472a-b36d-e676ddd6a677 · outbound

This paper cites Opt: Open pre-trained transformer langua ge models,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Opt: Open pre-trained transformer langua ge models,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.819326Z

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 29ef1638-31db-457f-a112-f5aa68dc4be6 · outbound

This paper cites Language models are few-shot l earners,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Language models are few-shot l earners,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.794351Z

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 d9ae364c-633f-4afe-824e-961a60ff270e · outbound

This paper cites Language models are unsupervised multitask learners,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Language models are unsupervised multitask learners,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.771327Z

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 7b5174ed-19ba-4865-965b-a92db533715f · outbound

This paper cites an unresolved cited work.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-12T05:29:37.760009Z

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 828ab826-8a23-4d3a-abf2-9652ee2b1985 · outbound

This paper cites Computer multiplication and division using binary logarithms,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Computer multiplication and division using binary logarithms,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.748330Z

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 7e80b562-036d-4ea6-854a-dd19ab565820 · outbound

This paper cites sqrt implementation in fdlibm,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities sqrt implementation in fdlibm,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.735477Z

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 6b74f9a1-f8f6-4d06-829f-ef96d0bafe96 · outbound

This paper cites Fast inverse square root,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Fast inverse square root,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.722908Z

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 a91fe7c1-ab1f-4d05-bb05-237a16963929 · outbound

This paper cites Aifes: A next-generation edge ai framewo rk,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Aifes: A next-generation edge ai framewo rk,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.711434Z

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 b8913d59-8ff0-4605-b9f4-663d9633e825 · outbound

This paper cites C ompiling kb- sized machine learning models to tiny iot devices,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities C ompiling kb- sized machine learning models to tiny iot devices,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.699553Z

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 02529958-b4cf-4d72-8433-67f2e6f072fc · outbound

This paper cites Fast approximations of expon ential and loga- rithm functions combined with efﬁcient storage/retrieval for combustion kinetics calculations,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Fast approximations of expon ential and loga- rithm functions combined with efﬁcient storage/retrieval for combustion kinetics calculations,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.686827Z

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 af1fe935-f520-4d96-971e-0ce81fb7af7a · outbound

This paper cites Two-pass softmax algorit hm,.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Two-pass softmax algorit hm,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.673758Z

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 1c8bc1d8-5f0b-48e5-a8dd-aaf58f78435a · outbound

This paper cites an unresolved cited work.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-12T05:29:37.661110Z

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 6bab3e4e-c2d6-4e71-a72c-9b2c84c04894 · outbound

This paper cites Available: https://arxiv.org/abs/2005.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Available: https://arxiv.org/abs/2005

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.782911Z

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 f3a75dd2-d26f-4767-8f61-a30a5c823124 · outbound

This paper cites Available: https://arxiv.org/abs/2205.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Available: https://arxiv.org/abs/2205

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:37.806700Z

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 91dd5b4a-4e16-46ba-adb9-20515d988059 · outbound

This paper cites Available: https://arxiv.org/abs/1606.

QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities Available: https://arxiv.org/abs/1606

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T05:29:38.080912Z

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

No inbound Pith citation observations are available.