Pith. sign in

Paper Citation Record · LEDGER

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

As of 17 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 3 inbound Pith citation observations for arXiv:2507.07996.

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

pith.paper-citation-record.v1
2507.07996 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:33:20.582143Z

measured 29 of 29 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T22:00:48.944002Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T12:36:57.338642Z

Reference resolution

26 of 26 outbound references displayed

  • verified exact1
  • verified fuzzy8
  • unresolved17
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d7a26cbd-3509-4c66-8327-d869ad55327d · outbound

This paper cites Neural module networks.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Neural module networks

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:18.674198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:18.674198Z digest=sha256:d45bfd6409326d70cd2043c35f9727a8941cbb99d7a86ba62ba3cb845da17e90

Observation 1869c13a-d85f-422e-a9af-5f817c52bed5 · outbound

This paper cites Early exit optimizations for additive machine learned ranking systems.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Early exit optimizations for additive machine learned ranking systems

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:22.592653Z

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.

source=pdf_text observed=2026-08-06T18:33:18.728193Z digest=sha256:e73b724ed34bd61ac740c59914e129e4ec746e4975db0d86a5cd509762994c57

Observation 32bceb12-cd5d-4a01-b1ae-e9b06aed766f · outbound

This paper cites Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:18.824715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:18.824715Z digest=sha256:b7772a84449934033f533078bab71b66c6e404ec28ac7871ac93579a21841b4f

Observation b921a512-63f0-4d9e-9224-722786fa34d0 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:18.869586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:18.869586Z digest=sha256:e8b244bed5634d33c83e732fc700be61cbc94084325918e53f94cffe13dd2963

Observation 7cea9865-718d-460f-8427-48947d1a9eea · outbound

This paper cites Universal Transformers.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Universal Transformers

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:18.945114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:18.945114Z digest=sha256:96eb09d1938a3b86a4a95b9d920182d7f8639e3536da486aa80ace20e3766207

Observation aabbfb14-2008-4e3f-b531-226e1d10bdcb · outbound

This paper cites Faith and fate: Limits of transformers on compositionality.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Faith and fate: Limits of transformers on compositionality

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:22.383678Z

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.

source=pdf_text observed=2026-08-06T18:33:19.014231Z digest=sha256:8788b088fd9aa1d46b6c6e87e95662a28c9261abf9f655c9b8ccae97d528e483

Observation b2fcee33-9d97-4b71-8394-cfd48c516dbd · outbound

This paper cites DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs DACT-BERT: Differentiable Adaptive Computation Time for an Efficient BERT Inference

Reference 7

Resolution
verified exact
local_arxiv, observed 2026-08-06T18:33:20.896116Z

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.

source=pdf_text observed=2026-08-06T18:33:19.080315Z digest=sha256:72eae64a841865060f127de94350a7addce67cdd9a2d4714189d9f5d191b2493

Observation 54e80b2d-9a4e-45cd-b894-d3ffe7f781a1 · outbound

This paper cites Reducing Transformer Depth on Demand with Structured Dropout.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Reducing Transformer Depth on Demand with Structured Dropout

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.194766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.194766Z digest=sha256:9df3d328c3d87dde4098fc054632161243e83faa60d809145ca01661c7539a43

Observation 94078844-e10c-4e60-8423-adbe8c9346e9 · outbound

This paper cites Looped Transformers for Length Generalization.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Looped Transformers for Length Generalization

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.337300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.337300Z digest=sha256:71763819506b7a8f0158916d3d53cf904525f6958b1529c2ee8afbb24f0cc48f

Observation b55f4d91-cdd6-4021-a825-612084ff9d7a · outbound

This paper cites Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.442435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.442435Z digest=sha256:1f08255d41c359006163167304acfb5a242fc198ba67d37720a850603d613401

Observation dd5655a8-9313-466c-ba0c-fac2b049e18e · outbound

This paper cites Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.515978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.515978Z digest=sha256:45276a9f3a329a773d83b98fa8f80b7355e47f851fa45c39b63c19ba369c5c6d

Observation cee57b3e-aadb-4b6c-a09b-6995499c7d59 · outbound

This paper cites Mixture of Nested Experts: Adaptive Processing of Visual Tokens.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Mixture of Nested Experts: Adaptive Processing of Visual Tokens

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.618801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.618801Z digest=sha256:b4ebc1224441e13115b17e62f70392f5361945f943c92c9ff52f3771b241cef6

Observation a67d989e-02ae-44e7-9317-17564ded0ee2 · outbound

This paper cites FastBERT: a Self-distilling BERT with Adaptive Inference Time.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs FastBERT: a Self-distilling BERT with Adaptive Inference Time

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.702829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.702829Z digest=sha256:9a1a7a29b6dc8c81e58f688913bbbbb71b873d2dc291b999b34483945ff2052f

Observation 95647168-7130-41b8-b7ef-53db4423b525 · outbound

This paper cites Faster depth-adaptive transformers.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Faster depth-adaptive transformers

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:22.166579Z

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.

source=pdf_text observed=2026-08-06T18:33:19.751026Z digest=sha256:d06dce8d67f562473bcda9dbdc8e256597afb2822338f3e4983f6188afd4d02f

Observation d16d4018-06bf-469c-b2a4-dcab4e02214c · outbound

This paper cites Ebert: Efficient bert inference with dynamic structured pruning.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Ebert: Efficient bert inference with dynamic structured pruning

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:21.923462Z

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.

source=pdf_text observed=2026-08-06T18:33:19.829868Z digest=sha256:6fd85cc2be79ae50a5e72cbd5d7447b3220efc498f5e87d647693d2171deb229

Observation 5be22ff9-fbb4-4592-98d1-6d273aaad627 · outbound

This paper cites Anytime Dense Prediction with Confidence Adaptivity.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Anytime Dense Prediction with Confidence Adaptivity

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:19.899681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:19.899681Z digest=sha256:9ce5856381b7e2d09c29fbd8ffacb879a32ba65b039482864de22c3fe142793c

Observation 6467bace-6a83-454b-bf80-d41bd7e7b32b · outbound

This paper cites On limitations of the transformer architecture.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs On limitations of the transformer architecture

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:21.734761Z

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.

source=pdf_text observed=2026-08-06T18:33:19.970608Z digest=sha256:a4084ba91b8e182bc719a989463b12d23bbdc34d441bcefa4dadf62b375029d1

Observation 8181068c-b182-440f-8f3c-3b76f1043e29 · outbound

This paper cites Scaling Language Models: Methods, Analysis & Insights from Training Gopher.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Scaling Language Models: Methods, Analysis & Insights from Training Gopher

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:20.036112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:20.036112Z digest=sha256:4155fbe513e8486aac99867d8349008518fb813ba4a2b4f8053fa83f4778ac08

Observation 7960cd81-b139-40c1-b0e7-5b43dcd2710a · outbound

This paper cites You need multiple exiting: Dynamic early exiting for accelerating unified vision language model.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs You need multiple exiting: Dynamic early exiting for accelerating unified vision language model

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:21.502530Z

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.

source=pdf_text observed=2026-08-06T18:33:20.118401Z digest=sha256:e395ad0ec7c99d8d5121f4549e45777ce83e1e75ec6ad8acebe479d545f01022

Observation 35ad1247-b75e-4230-8ff2-a47cf72342b0 · outbound

This paper cites Branchynet: Fast inference via early exiting from deep neural networks.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Branchynet: Fast inference via early exiting from deep neural networks

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:20.189870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:20.189870Z digest=sha256:f4796df43a2a8a73fd192669d8662233e3cc2639e7105e0ef47ed0d443c5e3f1

Observation 2efbc4f3-9921-4d8b-b746-56bd1faa0354 · outbound

This paper cites DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:20.272894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:20.272894Z digest=sha256:c8612c5636ffe1744c5bd6f97c894beda6326c28e9f2933eae9ab3f72a8ab68e

Observation d772d0ca-3939-40d3-a7f7-1b8394918ccd · outbound

This paper cites Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:20.319719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:20.319719Z digest=sha256:2c2f68fb8d1d1b751e8b1f5b99b297dbf4574c68e0fd9cc734153cf501fb49cd

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

This paper cites DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference.

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.

source=pdf_text observed=2026-08-06T18:33:20.378873Z digest=sha256:8b8032ebe3f726d9722004022ae0277aa269dede315fbd200f18a2a3341cfd2a

Observation c64381ee-1188-4625-8aa4-517ffdd3ffa8 · outbound

This paper cites Lgvit: Dynamic early exiting for accelerating vision transformer.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Lgvit: Dynamic early exiting for accelerating vision transformer

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:21.277639Z

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.

source=pdf_text observed=2026-08-06T18:33:20.451573Z digest=sha256:25723473a7e3fa73ba0255468f181bf723cd1b6654b94cd9d4ca03889ae3561f

Observation d55f31ec-99ae-4bfe-8207-672fe36795e3 · outbound

This paper cites Looped Transformers are Better at Learning Learning Algorithms.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Looped Transformers are Better at Learning Learning Algorithms

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T18:33:20.499325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T18:33:20.499325Z digest=sha256:247942a4e2812cb7d3b8bb9cb8f86459ea3bc4b5fe36253b2bd3696f73dd9083

Observation a8c89171-2c8a-4720-9f14-c6ae96ba4fbd · outbound

This paper cites Bert loses patience: Fast and robust inference with early exit.

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs Bert loses patience: Fast and robust inference with early exit

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T18:33:21.105730Z

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.

source=pdf_text observed=2026-08-06T18:33:20.582143Z digest=sha256:084494faaacb246f42e4d9d3829091a9110ed52894c5fbccb43c86972ebc7dcb

Pith citing papers

Observation 8468b482-8a3c-4a7c-8aed-3c8825e93da9 · inbound

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

Dr.LLM: Dynamic Layer Routing in LLMs Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-21T20:04:20.298986Z

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.

source=pdf_text observed=2026-05-21T20:01:48.806709Z digest=sha256:3669798a7b6a553a2d64216fddb856d839f234e71c1bbe7b755d9ba2f8c886e4

Observation da8f35f1-6a78-44dc-8505-e22bebcc4ddd · 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 Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-07-02T12:36:57.341253Z

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.

source=pdf_text observed=2026-06-28T01:56:34.435152Z digest=sha256:25d7828d04f8956e4ba1634c98286ead5c290415fc64f6f6f09754e9593a1219

Observation f25bee59-153a-4efb-b85a-4f65d9f843e3 · inbound

MACRO: Markov Chain Routing of Transformer Layers cites this paper.

MACRO: Markov Chain Routing of Transformer Layers Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T22:00:48.944002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:00:48.944002Z digest=sha256:a799fcfe10f0315e1a1dc8e0c143855e2967b19086a758fd67405719bfffdd6c