Pith. sign in

Paper Citation Record · LEDGER

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference

As of 22 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2608.13076.

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

pith.paper-citation-record.v1
2608.13076 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:23:50.751983Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+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

15 of 15 outbound references displayed

  • verified exact0
  • verified fuzzy6
  • unresolved9
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 462cd428-4fcb-46a2-853d-82212fa0acd8 · outbound

This paper cites Are sixteen heads really better than one?.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Are sixteen heads really better than one?

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T17:23:51.210055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T17:23:50.678391Z digest=sha256:b303be52441032b448530d552459db51d40d7108c977ee56dacdc94f1a30d058

Observation 60ea40c5-1547-4c75-ae43-da03a48849e7 · outbound

This paper cites I-bert: Integer-only bert quantization,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference I-bert: Integer-only bert quantization,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.684753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.684753Z digest=sha256:2c27b1dad0fcf9ca740dd66c67afc2bf9ea52b7c64194b14d2410f79bd61d905

Observation e0781296-9830-4261-a3d6-9873b6244c83 · outbound

This paper cites TinyBERT: Distilling BERT for Natural Language Understanding.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference TinyBERT: Distilling BERT for Natural Language Understanding

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.689785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.689785Z digest=sha256:fca74864678a4e632af2b3a684ca1d58170b650c5d470d0e3119a050de698168

Observation a91e866a-9dbe-4075-8d0e-a80d28ee37a2 · outbound

This paper cites Neurosurgeon: Collaborative intelligence between the cloud and mobile edge,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Neurosurgeon: Collaborative intelligence between the cloud and mobile edge,

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T17:23:51.174612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T17:23:50.695128Z digest=sha256:338a11949f1162387b06bca9ba00e4459ffe6c788ad5a58492edd7c818f52cf4

Observation 9c4020e4-aad7-4d2f-8bdf-9d944edb1e59 · outbound

This paper cites Neural compression and filtering for edge-assisted real-time object detection in challenged networks,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Neural compression and filtering for edge-assisted real-time object detection in challenged networks,

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T17:23:51.156688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T17:23:50.700469Z digest=sha256:32f6abd9b039b50d0ae6aac55d6e5366043b4cbdb3a6cb25ad37483543f6108f

Observation 5251b2db-3995-49c5-938f-01194f34af16 · outbound

This paper cites CeeBERT: Cross-domain inference in early exit BERT,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference CeeBERT: Cross-domain inference in early exit BERT,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T17:23:51.138363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T17:23:50.705511Z digest=sha256:9151a3aef91fc5532ae6e77b3fed7926a9e8cad8ebc9183b3ce21204d86f4d4b

Observation 812521e0-9668-40ad-8ede-683df59f3b2f · outbound

This paper cites Splitee: Early exit in deep neural networks with split computing,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Splitee: Early exit in deep neural networks with split computing,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.711040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.711040Z digest=sha256:b87866145a52d8e3fa71d7c58a3e98bf0f9380c5a476b105c70fb2bc72980eba

Observation 89cb1650-a0bb-4155-a27a-f51f1d0fd960 · outbound

This paper cites I-splitee: Image classi- fication in split computing dnns with early exits,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference I-splitee: Image classi- fication in split computing dnns with early exits,

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T17:23:51.116941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T17:23:50.716003Z digest=sha256:35345ff461aad3a038690a38002701f6a13eb5c5c39671e136a7c76a838ea3b8

Observation b65be7ba-df47-4d22-9a9b-ec47c38dfaf2 · outbound

This paper cites Distributed inference on mobile edge and cloud: An early exit based clustering approach,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Distributed inference on mobile edge and cloud: An early exit based clustering approach,

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-15T17:23:51.094424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-15T17:23:50.721231Z digest=sha256:c831a8c3df150711886fcb92d0e9846d2ff38011146a5d97a7631537a16f37f6

Observation 55687964-a304-4702-91dc-45e4facf98c1 · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.726665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.726665Z digest=sha256:2426e6f67ff97a76bc98626c27da902f2276ece7c8a077418f196cf666735caa

Observation aa7c938e-c6ef-4562-83e0-d5c1f2cde82b · outbound

This paper cites LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.732010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.732010Z digest=sha256:fd5746b8764bd34ea52e6f4680607e7c7b88aab4dead1705c48585ff57565903

Observation 5b8160c1-0fe7-44ae-aee3-6d1b304823a5 · outbound

This paper cites Fast inference from trans- formers via speculative decoding,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Fast inference from trans- formers via speculative decoding,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.737334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.737334Z digest=sha256:290bbaafea2c2e11fbe75635d0d57f43e6fdac92bf625dcc3f08455a709b1039

Observation 7d278428-7df2-4b9d-92c8-2a6a8aa6abd0 · outbound

This paper cites Get To The Point: Summarization with Pointer-Generator Networks.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Get To The Point: Summarization with Pointer-Generator Networks

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.741841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.741841Z digest=sha256:cd82cbecbc2ce48eed5e57b2b6f429bf46b4fc2cade0408c9e57ad234905b727

Observation 9292180e-c3ae-4c89-9116-da4a9a5d504b · outbound

This paper cites The llama 3 herd of models,.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference The llama 3 herd of models,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.747360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.747360Z digest=sha256:67298796e1e57ddd3fc0470b2330cc47c4a62c5c4a438bac888d1d0bfb84e5bc

Observation c127a117-a091-4c3a-92ce-b1c725b58780 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-15T17:23:50.751983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T17:23:50.751983Z digest=sha256:1ad48e52d0b20ad9b21717a91419a18740b269728b49faea006bc1f44f0d726f

Pith citing papers

No inbound Pith citation observations are available.