Paper Citation Record · LEDGER

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices

As of 21 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2506.18035.

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

pith.paper-citation-record.v1
2506.18035 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:59:59.176427Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+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

21 of 21 outbound references displayed

verified exact1
verified fuzzy17
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 911de27b-6ba4-49a9-a319-b1f1918efb91 · outbound

This paper cites an unresolved cited work.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-15T18:59:59.676802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9767d3b2-d9a5-405a-a699-eadf77d5a99b · outbound

This paper cites BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T18:59:59.061856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d636fcdb-5d36-428f-a421-d83aecb858c3 · outbound

This paper cites Distillation-based training for multi-exit architectures,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Distillation-based training for multi-exit architectures,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.653876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9aa49c67-b79f-4081-8a41-79dd0cf4f86a · outbound

This paper cites Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-15T18:59:59.253918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c74b9ec-df38-4cfa-b4ae-7b4b4ec8081c · outbound

This paper cites Temporal early exiting for streaming speech commands recognition,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Temporal early exiting for streaming speech commands recognition,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.625590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d971d32b-bcaa-46ef-8e40-5a3c2f60c40f · outbound

This paper cites Zipformer: A faster and better encoder for automatic speech recognition,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Zipformer: A faster and better encoder for automatic speech recognition,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.595041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5ef59281-eb43-49cd-a429-ff0a64721867 · outbound

This paper cites Conformer: Convolution-augmented transformer for speech recognition,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Conformer: Convolution-augmented transformer for speech recognition,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.574972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 74dc0e50-d9eb-4ef6-b52c-d8d3263d4c92 · outbound

This paper cites Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.555177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 977b7b67-889d-402d-885b-ae51d12d8f5e · outbound

This paper cites Squeezeformer: An efficient transformer for automatic speech recognition,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Squeezeformer: An efficient transformer for automatic speech recognition,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.536220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 055fdcb2-d02c-4981-beed-fb53eda6a630 · outbound

This paper cites ImageNet classification with deep convolutional neural networks,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices ImageNet classification with deep convolutional neural networks,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.518450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3f8aea9d-7e24-4d1f-80aa-4a6a52aa19c5 · outbound

This paper cites HuBERT: self-supervised speech representation learning by masked prediction of hidden units,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices HuBERT: self-supervised speech representation learning by masked prediction of hidden units,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.498186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0ebc7d96-b5ce-4cbb-b518-9dcf808e4809 · outbound

This paper cites Avoid overthinking in self- supervised models for speech recognition,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Avoid overthinking in self- supervised models for speech recognition,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.477076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c0867a2e-92d3-4fdc-a6cf-2628d585fc6e · outbound

This paper cites WavLM: Large-scale self-supervised pre-training for full stack speech processing,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices WavLM: Large-scale self-supervised pre-training for full stack speech processing,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.456375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5ed31a8e-7a66-432a-9ca9-d0247a5641e4 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices U-net: Convolutional networks for biomedical image segmentation,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.434797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 96535d59-0d85-4775-b553-c19c6e80a7be · outbound

This paper cites Attention is all you need,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Attention is all you need,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.413480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 60c3bb4e-66ae-4072-8cbd-725855dd65a3 · outbound

This paper cites Con- nectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Con- nectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.390965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 62e08c51-b61c-4fb6-adfa-414145bf29ff · outbound

This paper cites Librispeech: An ASR corpus based on public domain audio books,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Librispeech: An ASR corpus based on public domain audio books,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.368368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6b5c62ff-36e2-4cb6-b270-bebbfdcf672c · outbound

This paper cites TED-LIUM 3: Twice as much data and corpus repartition for experi- ments on speaker adaptation,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices TED-LIUM 3: Twice as much data and corpus repartition for experi- ments on speaker adaptation,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.349310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 70cbc9f1-8a33-4828-977f-3e85f3708651 · outbound

This paper cites Wav2vec 2.0: A framework for self-supervised learning of speech representations,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Wav2vec 2.0: A framework for self-supervised learning of speech representations,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.327862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6c2e0203-76e6-4e58-a765-812d4638df07 · outbound

This paper cites Neural machine translation of rare words with subword units,.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Neural machine translation of rare words with subword units,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T18:59:59.304924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation af8677d3-646a-40fe-8798-ec6c875a5347 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices Adam: A Method for Stochastic Optimization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T18:59:59.176427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.