Paper Citation Record · LEDGER

Harvesting AI Computation at the Edge via Generic Approximation

As of 12 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2606.29518.

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

pith.paper-citation-record.v1
2606.29518 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T01:53:18.755724Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

42 of 42 outbound references displayed

verified exact11
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 884bb269-b18e-4a61-8921-80925af1c9e4 · outbound

This paper cites The internet of things: A survey.Computer networks, 54(15):2787–2805, 2010.

Harvesting AI Computation at the Edge via Generic Approximation The internet of things: A survey.Computer networks, 54(15):2787–2805, 2010

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9fbb792-b365-46b6-a7bc-814f10ca8ecb · outbound

This paper cites In-datacenter performance analysis of a tensor processing unit.

Harvesting AI Computation at the Edge via Generic Approximation In-datacenter performance analysis of a tensor processing unit

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 324211a8-7e0d-4e72-beee-a0403a9f7feb · outbound

This paper cites LEAF: A Learnable Frontend for Audio Classification.

Harvesting AI Computation at the Edge via Generic Approximation LEAF: A Learnable Frontend for Audio Classification

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T03:04:14.342259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 66672c66-65ee-47cb-8364-f85f54999ab4 · outbound

This paper cites MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs.

Harvesting AI Computation at the Edge via Generic Approximation MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.347732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b7f48354-d73b-4e17-943f-b497f271318f · outbound

This paper cites Empowering edge intelligence: A comprehensive survey on on-device ai models.ACM Computing Surveys, 2025.

Harvesting AI Computation at the Edge via Generic Approximation Empowering edge intelligence: A comprehensive survey on on-device ai models.ACM Computing Surveys, 2025

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a3e85f6-684d-4536-87c6-4793c8904622 · outbound

This paper cites Yolo9000: better, faster, stronger.

Harvesting AI Computation at the Edge via Generic Approximation Yolo9000: better, faster, stronger

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfb13ea2-1cdf-4e6f-91d4-e30f2edc7216 · outbound

This paper cites SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size.

Harvesting AI Computation at the Edge via Generic Approximation SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.353479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e577c2e0-7d50-4772-859f-8023851f181a · outbound

This paper cites MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.

Harvesting AI Computation at the Edge via Generic Approximation MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.336837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fdcb8291-8386-4029-9b11-dd130663af65 · outbound

This paper cites Efficientnet: Rethinking model scaling for convolutional neural networks.

Harvesting AI Computation at the Edge via Generic Approximation Efficientnet: Rethinking model scaling for convolutional neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b42c1772-3077-4654-a1bb-9ca87f02d61a · outbound

This paper cites Addressing the issue of processing element under- utilization in general-purpose systolic deep learning accelerators.

Harvesting AI Computation at the Edge via Generic Approximation Addressing the issue of processing element under- utilization in general-purpose systolic deep learning accelerators

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e42fcc-a644-4ead-b7e5-3b1ba96cc43f · outbound

This paper cites FlexNN: A Dataflow-aware Flexible Deep Learning Accelerator for Energy-Efficient Edge Devices.

Harvesting AI Computation at the Edge via Generic Approximation FlexNN: A Dataflow-aware Flexible Deep Learning Accelerator for Energy-Efficient Edge Devices

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.323112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 37f763d1-dac4-45ee-9adb-220991d5e155 · outbound

This paper cites A comprehensive survey of energy-efficient computing to enable sustain- able massive iot networks.Alexandria Engineering Journal, 91:12–29, 2024.

Harvesting AI Computation at the Edge via Generic Approximation A comprehensive survey of energy-efficient computing to enable sustain- able massive iot networks.Alexandria Engineering Journal, 91:12–29, 2024

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90aa7da9-ce59-4acd-aed3-cb9d68d3bf5b · outbound

This paper cites Snnap: Approximate computing on programmable socs via neural acceleration.

Harvesting AI Computation at the Edge via Generic Approximation Snnap: Approximate computing on programmable socs via neural acceleration

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35acd8c4-726a-4638-93e2-40ddafbcfb22 · outbound

This paper cites Neural acceleration for general-purpose approximate programs.

Harvesting AI Computation at the Edge via Generic Approximation Neural acceleration for general-purpose approximate programs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59dd86e7-09c1-40ba-af80-a08370f4a1b2 · outbound

This paper cites Neural network-based accelerators for transcendental function approximation.

Harvesting AI Computation at the Edge via Generic Approximation Neural network-based accelerators for transcendental function approximation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50ee451-063f-448f-9d81-8aa7269b1374 · outbound

This paper cites A Comprehensive Survey on Hardware-Aware Neural Architecture Search.

Harvesting AI Computation at the Edge via Generic Approximation A Comprehensive Survey on Hardware-Aware Neural Architecture Search

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.312440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ed36c064-9a6b-412e-a18a-aedd837ea560 · outbound

This paper cites Neural ar- chitecture search: A survey.Journal of Machine Learning Research, 20(55):1–21, 2019.

Harvesting AI Computation at the Edge via Generic Approximation Neural ar- chitecture search: A survey.Journal of Machine Learning Research, 20(55):1–21, 2019

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44738867-1321-48a6-ad9a-4b42147f68df · outbound

This paper cites Fbnet: Hardware-aware efficient convnet design via differ- entiable neural architecture search.

Harvesting AI Computation at the Edge via Generic Approximation Fbnet: Hardware-aware efficient convnet design via differ- entiable neural architecture search

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c643c4-359f-4be4-bb84-e8e86f387d4b · outbound

This paper cites ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware.

Harvesting AI Computation at the Edge via Generic Approximation ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.317352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 049969c3-3329-46ec-abff-0549c7453e03 · outbound

This paper cites Memory- efficient patch-based inference for tiny deep learning.Advances in Neural Information Processing Systems, 34:2346–2358, 2021.

Harvesting AI Computation at the Edge via Generic Approximation Memory- efficient patch-based inference for tiny deep learning.Advances in Neural Information Processing Systems, 34:2346–2358, 2021

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e4c333-43b9-4dac-ba52-33fd802ba609 · outbound

This paper cites Pruning vs quantization: Which is better?Advances in neural information processing systems, 36:62414–62427, 2023.

Harvesting AI Computation at the Edge via Generic Approximation Pruning vs quantization: Which is better?Advances in neural information processing systems, 36:62414–62427, 2023

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc33adbf-92c3-4943-9203-442fb104fafa · outbound

This paper cites Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review.

Harvesting AI Computation at the Edge via Generic Approximation Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.332330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0863311c-9fe4-4ef0-a8d1-08e88258aa8c · outbound

This paper cites A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices.

Harvesting AI Computation at the Edge via Generic Approximation A Survey on Deep Neural Network Partition over Cloud, Edge and End Devices

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.296869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2ccd2c87-eccd-4a00-b83e-ddc7274ce065 · outbound

This paper cites Survey of deep learning accelerators for edge and emerging computing.Electronics, 13(15):2988, 2024.

Harvesting AI Computation at the Edge via Generic Approximation Survey of deep learning accelerators for edge and emerging computing.Electronics, 13(15):2988, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1fc9af3-d914-459c-9f4f-1ebaaa5aa224 · outbound

This paper cites Efficient processing of deep neural networks: A tutorial and survey.Proceedings of the IEEE, 105(12):2295–2329, 2017.

Harvesting AI Computation at the Edge via Generic Approximation Efficient processing of deep neural networks: A tutorial and survey.Proceedings of the IEEE, 105(12):2295–2329, 2017

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc82685a-9e43-43a3-b444-c200edf684d4 · outbound

This paper cites {SHEPHERD}: Serving{DNNs}in the wild.

Harvesting AI Computation at the Edge via Generic Approximation {SHEPHERD}: Serving{DNNs}in the wild

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 443452c4-0d6d-401e-a4f2-31ad342cdd85 · outbound

This paper cites Maeri: Enabling flexible dataflow mapping over dnn accelerators via recon- figurable interconnects.ACM Sigplan Notices, 53(2):461–475, 2018.

Harvesting AI Computation at the Edge via Generic Approximation Maeri: Enabling flexible dataflow mapping over dnn accelerators via recon- figurable interconnects.ACM Sigplan Notices, 53(2):461–475, 2018

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43868bdb-7e32-49e6-ae5e-2c5aa710944b · outbound

This paper cites Eyeriss: A spatial archi- tecture for energy-efficient dataflow for convolutional neural networks.

Harvesting AI Computation at the Edge via Generic Approximation Eyeriss: A spatial archi- tecture for energy-efficient dataflow for convolutional neural networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e9e70de-3811-44e0-80c2-60dfe28fb16c · outbound

This paper cites A formalism of dnn accelerator flexibility.

Harvesting AI Computation at the Edge via Generic Approximation A formalism of dnn accelerator flexibility

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00b16100-2c8e-4649-8c2f-a27a2b7334fb · outbound

This paper cites Tpu v4: An optically reconfigurable supercomputer for machine learning with hardware support for embeddings.

Harvesting AI Computation at the Edge via Generic Approximation Tpu v4: An optically reconfigurable supercomputer for machine learning with hardware support for embeddings

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc87a9e7-3d98-45bf-8515-cb6f3bf90afe · outbound

This paper cites Approximation by superpositions of a sigmoidal function.Mathematics of control, signals and systems, 2(4):303–314, 1989.

Harvesting AI Computation at the Edge via Generic Approximation Approximation by superpositions of a sigmoidal function.Mathematics of control, signals and systems, 2(4):303–314, 1989

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc3a58a3-b078-485c-9eab-c21886796323 · outbound

This paper cites Approximation capabilities of multilayer feedforward networks.Neural networks, 4(2):251–257, 1991.

Harvesting AI Computation at the Edge via Generic Approximation Approximation capabilities of multilayer feedforward networks.Neural networks, 4(2):251–257, 1991

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41be1f5a-0ee6-4ccd-87aa-2eff2336f3aa · outbound

This paper cites Error bounds for approximations with deep relu networks.Neural networks, 94:103–114, 2017.

Harvesting AI Computation at the Edge via Generic Approximation Error bounds for approximations with deep relu networks.Neural networks, 94:103–114, 2017

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6170bc4-afe8-443e-93b3-0ce7cb023920 · outbound

This paper cites Optimal approximation rates for deep relu neural networks on sobolev and besov spaces.Journal of Machine Learning Research, 24(357):1–52, 2023.

Harvesting AI Computation at the Edge via Generic Approximation Optimal approximation rates for deep relu neural networks on sobolev and besov spaces.Journal of Machine Learning Research, 24(357):1–52, 2023

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7a4d602-2f75-490d-bd3d-5bd4892978a4 · outbound

This paper cites The expressive power of neural networks: A view from the width.

Harvesting AI Computation at the Edge via Generic Approximation The expressive power of neural networks: A view from the width

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29935294-0654-4a02-812a-d1da2c1965e5 · outbound

This paper cites Neural networks with small weights and depth-separation barriers.Advances in neural information processing systems, 33:19433–19442, 2020.

Harvesting AI Computation at the Edge via Generic Approximation Neural networks with small weights and depth-separation barriers.Advances in neural information processing systems, 33:19433–19442, 2020

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01e097b-0d2e-4c8e-b3e9-99457d86a793 · outbound

This paper cites Optimal approximation of piecewise smooth functions using deep relu neural networks.Neural Networks, 108:296–330, 2018.

Harvesting AI Computation at the Edge via Generic Approximation Optimal approximation of piecewise smooth functions using deep relu neural networks.Neural Networks, 108:296–330, 2018

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1fb4d68-9f33-42a8-a3df-9185d39dd578 · outbound

This paper cites DARTS: Differentiable Architecture Search.

Harvesting AI Computation at the Edge via Generic Approximation DARTS: Differentiable Architecture Search

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-06-30T03:04:14.328209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dcd1304b-d4aa-41b3-80f0-60279a79bfea · outbound

This paper cites DARTS+: Improved Differentiable Architecture Search with Early Stopping.

Harvesting AI Computation at the Edge via Generic Approximation DARTS+: Improved Differentiable Architecture Search with Early Stopping

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.301801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 49a5ea82-91dc-4598-a2d9-2aeed04abde4 · outbound

This paper cites Understanding and Robustifying Differentiable Architecture Search.

Harvesting AI Computation at the Edge via Generic Approximation Understanding and Robustifying Differentiable Architecture Search

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-06-30T03:04:14.307125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 345396c8-e73d-4a96-9324-71f20d921976 · outbound

This paper cites Fair darts: Eliminating unfair advantages in differentiable architecture search.

Harvesting AI Computation at the Edge via Generic Approximation Fair darts: Eliminating unfair advantages in differentiable architecture search

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e39a8c1-a270-449d-8142-0b917882315a · outbound

This paper cites Ultra-low power dnn accelerators for iot: Resource characterization of the max78000.

Harvesting AI Computation at the Edge via Generic Approximation Ultra-low power dnn accelerators for iot: Resource characterization of the max78000

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-30T01:53:18.755724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.