Paper Citation Record · LEDGER

DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 23 inbound Pith citation observations for arXiv:2004.12993.

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

pith.paper-citation-record.v1
2004.12993 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 23 of 23 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T17:57:25.837531Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T13:19:50.449132Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation f616e550-5364-42d8-80c6-7dfc5258ceb2 · inbound

Eliciting Latent Predictions from Transformers with the Tuned Lens cites this paper.

Eliciting Latent Predictions from Transformers with the Tuned Lens DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 90

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T16:54:37.545480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 703f5c42-52c4-4c34-92b3-8df30b45ec39 · inbound

TOAST: Transformer Optimization using Adaptive and Simple Transformations cites this paper.

TOAST: Transformer Optimization using Adaptive and Simple Transformations DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-23T19:48:23.054063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 10c0ec90-5f5e-44bc-a123-54a6a7c29592 · inbound

BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts cites this paper.

BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T17:57:25.837531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a40d33dd-baa5-44a5-86fc-7dd146285b79 · inbound

FREE: Fast and Robust Vision Language Models with Early Exits cites this paper.

FREE: Fast and Robust Vision Language Models with Early Exits DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T05:53:46.089881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edd8cf25-2ddd-4d96-a5ce-13456f966539 · inbound

MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG cites this paper.

MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T21:11:18.509710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad0b72b-8ed4-48f1-8c13-e706fae5e322 · inbound

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs cites this paper.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:33:20.378873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae3fcb53-9d36-4050-ba7a-e5247cbe5855 · inbound

Harnessing Input-Adaptive Inference for Efficient VLN cites this paper.

Harnessing Input-Adaptive Inference for Efficient VLN DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T21:16:26.875019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a73c93-bdb9-477d-9aa7-ddfe21a46b85 · inbound

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding cites this paper.

Visual Programmability: A Guide for Code-as-Thought in Chart Understanding DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T19:27:20.989278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d299826c-9f13-4a08-b427-dffafcbfe339 · inbound

T-TAMER: Provably Taming Trade-offs in ML Serving cites this paper.

T-TAMER: Provably Taming Trade-offs in ML Serving DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-04T14:57:00.268518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2514974-4b09-4721-8f51-c78259ff6103 · inbound

Dr.LLM: Dynamic Layer Routing in LLMs cites this paper.

Dr.LLM: Dynamic Layer Routing in LLMs DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T20:04:20.339326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e4a7501-f32b-470c-a47d-18f3c58e7e9b · inbound

Two-dimensional early exit optimisation of LLM inference cites this paper.

Two-dimensional early exit optimisation of LLM inference DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:59:34.202511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1e3502b5-1fba-46f4-9d73-e01985ed0c8f · inbound

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities cites this paper.

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 174

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:16:10.368141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2bdab8cb-bdb3-471d-8d85-2ad6fca39186 · inbound

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks cites this paper.

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:46:40.913935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff6bf392-2166-429b-80d4-b6a997abacfd · inbound

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks cites this paper.

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:50:27.793483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 09a48e45-8264-4d8e-a009-b53da214255a · inbound

Complexity Horizons of Compressed Models in Analog Circuit Analysis cites this paper.

Complexity Horizons of Compressed Models in Analog Circuit Analysis DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:26:10.480372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8f0bba89-c8c5-4349-b7e2-fd510daae1d1 · inbound

HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory cites this paper.

HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:36:09.055857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6c79739b-5262-4d35-bb22-8bd0d2b8584c · inbound

Sparse Layers are Critical to Scaling Looped Language Models cites this paper.

Sparse Layers are Critical to Scaling Looped Language Models DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:21:28.238775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 12411a4e-616a-47d4-8169-a10b05fa6253 · inbound

Sparse Layers are Critical to Scaling Looped Language Models cites this paper.

Sparse Layers are Critical to Scaling Looped Language Models DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:35:29.162165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ffde8642-6b5d-489b-bf19-e7a1170cc3be · inbound

Compute Where it Counts: Self Optimizing Language Models cites this paper.

Compute Where it Counts: Self Optimizing Language Models DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:46:29.797977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cb36b86f-d44d-4757-b725-5863e1f413fb · inbound

Skip a Layer or Loop It? Learning Program-of-Layers in LLMs cites this paper.

Skip a Layer or Loop It? Learning Program-of-Layers in LLMs DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:36:57.368620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5719b8a9-4508-40d8-b385-326950dfdf37 · inbound

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference cites this paper.

RKSC: Reasoning-Aware KV Cache Sharing and Confident Early Exit for Multi-Step LLM Inference DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T23:07:26.769760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9ad77046-a3c2-477b-94ab-5334e38d8151 · inbound

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry cites this paper.

CascadeFormer: Depth-Tapered Transformers Motivated by Gradient Fan-in Asymmetry DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:19:50.450509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 059860f5-77ec-4d59-8e36-817270d08a5f · inbound

Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts cites this paper.

Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T08:13:30.312749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.