Pith. sign in

Paper Citation Record · LEDGER

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones

As of 12 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2412.19325.

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

pith.paper-citation-record.v1
2412.19325 v1

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T00:46:17.847060Z

measured 50 of 50 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

50 of 50 outbound references displayed

  • verified exact3
  • verified fuzzy17
  • unresolved30
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6b047f6d-c614-4c50-8644-3920bd00f4d0 · outbound

This paper cites write newline.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.674748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.674748Z digest=sha256:7b3528217628a743d18cab5da1088807e3b5eab16812c27a28dc3fce8d40a9a1

Observation 96f9fb34-5070-4468-9e6c-e68f137b8c57 · outbound

This paper cites M., Mallinar, N., Lucas, J., and Nakkiran, P.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones M., Mallinar, N., Lucas, J., and Nakkiran, P

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.469270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.679154Z digest=sha256:977ee366b807586d56a783e23a51ada6a35c6709392fc93fcd45b3971384d5c9

Observation 322b18c9-c923-4dc8-bf44-04df3d88a268 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Accelerating Large Language Model Decoding with Speculative Sampling

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.682571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.682571Z digest=sha256:43764cb4dfe310059ac8837651c33e65e14f34cf45cf6ee53d7e80b95109e9e2

Observation 15721e5e-9611-4ae0-bdc5-bc8941b55cb1 · outbound

This paper cites and Ge, R.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones and Ge, R

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.457855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.687034Z digest=sha256:a9b2a99db9f22c2a8d93aa714223d63fcfdfd1899b4bae36ad5fec114c26d105

Observation 85cd3f88-e0ba-406c-94fb-a8302d1f35c2 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Imagenet: A large-scale hierarchical image database

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.691055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.691055Z digest=sha256:1c35e8849d0440b93d5a41089c8a75851170e6c7cdf919cc8fafcced978417e8

Observation fd2f7f04-dbce-4010-a5dc-378c5856032d · outbound

This paper cites an unresolved cited work.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.694677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.694677Z digest=sha256:cbab1b184dd4f7ee8f99c4314ec094a58b0b86123c19114c98b6ba0fb3101f47

Observation 8acee224-e61f-45b3-ab37-6afcaabda785 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Qlora: Efficient finetuning of quantized llms

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.698823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.698823Z digest=sha256:6e209de5207a821fdeba391353563593d44257003e860e73e92dfc093532e7cf

Observation 90982f90-e08c-42ff-ace3-356ac7217f20 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones An image is worth 16x16 words: Transformers for image recognition at scale

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.428526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.702162Z digest=sha256:999d3edae251b0ec784a728a7a505eae0e17384e034776186ab646348674de67

Observation 7a1f2f3d-82ee-4962-8c77-b681aacae00f · outbound

This paper cites Depth-Adaptive Transformer.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Depth-Adaptive Transformer

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.705612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.705612Z digest=sha256:475f0a2bcdfe2509af2f810f43bb82312ca4317bc53f3b8208ed61bc0a13c27c

Observation 01883388-384a-4c99-a750-7d3ded7ddc1c · outbound

This paper cites Depth-adaptive transformer.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Depth-adaptive transformer

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.417577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.709342Z digest=sha256:18122f738100cb6929ed76204507c356b7bfb69194de8cf6d3956afcc9fc87e3

Observation 01f1c6d6-378d-4c00-b8b7-5689ee95ff32 · outbound

This paper cites Towards Better Selective Classification.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Towards Better Selective Classification

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.712383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.712383Z digest=sha256:ae841901314c9b60e99ef587a15056511be82a37d01c508b06f2798ae261e959

Observation f29ba132-eca4-4f0b-9ebe-a2a562def69d · outbound

This paper cites Compressing BERT : Studying the effects of weight pruning on transfer learning.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Compressing BERT : Studying the effects of weight pruning on transfer learning

Reference 12

Resolution
verified exact
doi, observed 2026-08-11T00:46:17.897772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.716115Z digest=sha256:9a0117fffbc3c93fcf12cd639d9399d1816be19387a7d2eb9038ba824295fc7b

Observation 1676788f-3b71-4bd0-afa4-9a2d4e2d8f40 · outbound

This paper cites and Bagnell, D.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones and Bagnell, D

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.407527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.719689Z digest=sha256:8eefd6d6dd14b2f14044cbc83b11011cbed292a3f48b9d5258b54966af91e397

Observation df44c1a0-87cd-48ed-bddb-8de075b5a977 · outbound

This paper cites Minillm: Knowledge distillation of large language models.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Minillm: Knowledge distillation of large language models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.396723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.722671Z digest=sha256:3c80b73f80e6401b244c989aad17c0b852b64475ddb3f21823912c16447f9bf7

Observation 1324b66b-8c72-49b3-82fe-39bfe592a3cc · outbound

This paper cites an unresolved cited work.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.726320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.726320Z digest=sha256:0f3d1285f0209f854bc83aa037066595911655120bd74d2858ab6f893c914c14

Observation 9fee3923-b0ff-48b6-aae1-4d7347a0e554 · outbound

This paper cites E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning

Reference 16

Resolution
verified exact
local_arxiv, observed 2026-08-11T00:46:18.155873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.730008Z digest=sha256:b8c5885bcb65bdced83581c91a6e7e620c05626ff74d2859d1c5bb76491d98b8

Observation 478d80c1-bf64-4c51-89be-1974b228c2a7 · outbound

This paper cites Learning to Weight Samples for Dynamic Early-Exiting Networks, pp.\ 362--378.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Learning to Weight Samples for Dynamic Early-Exiting Networks, pp.\ 362--378

Reference 17

Resolution
verified exact
doi, observed 2026-08-11T00:46:17.886483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.733387Z digest=sha256:99a90124375b2f9c70d200763a271be73aa4bba3c369f6313bf75cbc56fe4f72

Observation 15d7e391-ff2b-4e5a-a3e3-8b403b4187ed · outbound

This paper cites A stitch in time saves nine: A train-time regularizing loss for improved neural network calibration.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones A stitch in time saves nine: A train-time regularizing loss for improved neural network calibration

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.379899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.736711Z digest=sha256:42d1c57cb2bc5244ea03af6ffd5409a109e382b4e203a14732b6119a86464ad7

Observation f246554e-ae1f-419f-ae06-701d33132fe9 · outbound

This paper cites Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.739881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.739881Z digest=sha256:b918a829da453107b48ee2abc4976ac9d3e0fd194f07b22d7e745177921503bf

Observation 350ab2d4-c82c-48f0-b7a3-81bee7c71971 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Distilling the Knowledge in a Neural Network

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.742904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.742904Z digest=sha256:b6ac337f8ca55896a7a6e49631a2eef956cfe28cf95a45ad4d102645635cca01

Observation 7dc95869-bc47-4ca2-a613-1183204816eb · outbound

This paper cites Training Compute-Optimal Large Language Models.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Training Compute-Optimal Large Language Models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.746627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.746627Z digest=sha256:8e504a88d109d3e53c93ea08a8563222b25c444e609aa6ef6df71a0fb1cf7671

Observation f1c541ca-c9c5-426c-82e6-834f01cb508a · outbound

This paper cites Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.750351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.750351Z digest=sha256:9bc1cdab75d7b3fbc29a791c94157f8a7a557ff1a613b059e3f438c3dec520fd

Observation 225c4804-4a31-4c58-b1cc-c248812d257b · outbound

This paper cites an unresolved cited work.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-11T00:46:18.368352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.756173Z digest=sha256:e978076e5628e1c418b2065ffe00f5f5021cc3ac7ca895404fdfdd9dcd81ac10

Observation 006b4c1e-1667-4823-b9cc-9498cb956320 · outbound

This paper cites Adaptive deep neural network inference optimization with eenet.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Adaptive deep neural network inference optimization with eenet

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.356918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.759713Z digest=sha256:ee977d8c7287582b3ebceaf392e5750913bbb6600b760893ed10f255ef560fd7

Observation 0b9d57b8-1da5-4cb6-8036-d72befded7fc · outbound

This paper cites U., Zhang, D., and Nalisnick, E.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones U., Zhang, D., and Nalisnick, E

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.345373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.762670Z digest=sha256:1cd7e050ee7573feea78cb6dd2fe08cfd69ebeaeb91dcc12b512b1c1260957b2

Observation cf48251e-45f3-4ce9-993e-69389c3d6e8f · outbound

This paper cites To trust or not to trust a classifier.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones To trust or not to trust a classifier

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.334436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.765743Z digest=sha256:b0fbe058158066983d2fcfd1fe10fdca791b859d8f909ad6e902a0f5028ce24d

Observation 003b5b20-5a2b-4065-b0d0-dcb77daad5d7 · outbound

This paper cites Scaling Laws for Neural Language Models.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Scaling Laws for Neural Language Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.769378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.769378Z digest=sha256:56562ea9401aa45b59c13fc6b70c47650f54b334fd171b7768bb74c1e0d2c4e6

Observation 7cef64ea-02b0-4d42-a0b4-8e2f6dde263c · outbound

This paper cites Shallow-deep networks: Understanding and mitigating network overthinking.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Shallow-deep networks: Understanding and mitigating network overthinking

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.323629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.773100Z digest=sha256:a8f44c95eef30f3e8f8214a749be78bbfd187dbcea10cc3476611f8d0e5f486a

Observation 61028688-bb4a-4f65-90cb-de91095e7c51 · outbound

This paper cites Crafting papers on machine learning.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Crafting papers on machine learning

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.776544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.776544Z digest=sha256:08a8e0f518804008e692854634384efc5c921cc143ebecb901f7057f0c967f2d

Observation 1a4b9d83-166f-4033-a52d-428c4eb4a790 · outbound

This paper cites an unresolved cited work.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-11T00:46:18.306165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.779898Z digest=sha256:4fc8816319dbfc4b226c0c155421b7fdae705544fba8856fca2eb82456248ca7

Observation 0d783e10-8e7a-4830-8a16-96bba326f3d2 · outbound

This paper cites Fast inference from transformers via speculative decoding.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Fast inference from transformers via speculative decoding

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.783342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.783342Z digest=sha256:184b49c3ec77e0d305aa0c26d53dc8371c28f5216397752a14aa042b873cbd8c

Observation 7a88efa8-2955-4038-b02d-b04f6546180b · outbound

This paper cites P., Salakhutdinov, R.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones P., Salakhutdinov, R

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.786656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.786656Z digest=sha256:8d967e9457b7d875862694f44e55572714e18684a6cd4425bd34622021d69f33

Observation f428284a-c002-439f-bc90-01f885e658c6 · outbound

This paper cites Decoupled Weight Decay Regularization.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Decoupled Weight Decay Regularization

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.790117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.790117Z digest=sha256:89761ebb3ab4ca96752b930af27cffb5621155ff999a23d0d7027f73cd6b7681

Observation 04dc7294-ab78-4fd3-9355-d82b13b6312d · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.793499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.793499Z digest=sha256:09293c7eceb1520695f80ed16123f40c08fdf102f5e5f7a68851aa174fee3684

Observation e424f07b-086b-470a-b623-736677643bdc · outbound

This paper cites Fixing overconfidence in dynamic neural networks.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Fixing overconfidence in dynamic neural networks

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.282455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.797035Z digest=sha256:5b1356547a240c3ebfaf3e018d1febba0422910d73d1bedc8577b8283750895c

Observation 1594f0c1-d798-40fb-87bf-a1687e38929f · outbound

This paper cites P., Cooper, G.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones P., Cooper, G

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.271126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.800150Z digest=sha256:c1bd27d8c35d2b0ba3cb5e0ec0230a2252a760d5a43c66737c65b205bc325afd

Observation 2522d9bb-0547-44f1-b87d-246eb35c51ac · outbound

This paper cites On-the-fly operation batching in dynamic computation graphs.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones On-the-fly operation batching in dynamic computation graphs

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.259805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.803367Z digest=sha256:c4415b8ee9d586b36b35ebc69c4cd55b3a1d2cee9d11bb69c36bb9ab40322d1b

Observation b92c40c8-d9aa-432d-8ed8-f11188968ae6 · outbound

This paper cites W., Zhang, L., Jerfel, G., and Tran, D.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones W., Zhang, L., Jerfel, G., and Tran, D

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.248113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.806654Z digest=sha256:e45b8f0ccd9956bb69e990c05a358a61bad257cf58ba869fdbf15f9cbca4e75a

Observation 42bbcd89-deb3-4f56-a373-22772c741cde · outbound

This paper cites Can you trust your model's uncertainty? evaluating predictive uncertainty under dataset shift.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Can you trust your model's uncertainty? evaluating predictive uncertainty under dataset shift

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.810196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.810196Z digest=sha256:06a6fc7d19203dc5503b43b094aaf6c0f4c05f3aa15eb5b703aff108c93dabd0

Observation 8edd0389-6668-4b5a-aea0-6ac515b4335c · outbound

This paper cites Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.813332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.813332Z digest=sha256:58978bab2a454d5da77ddcd0aa1a581e41df72fd2fd17fe6c4af1db35a6a3f5a

Observation 41723cf0-a234-4908-9e1e-2796de5b3e46 · outbound

This paper cites Consistent Accelerated Inference via Confident Adaptive Transformers.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Consistent Accelerated Inference via Confident Adaptive Transformers

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.816920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.816920Z digest=sha256:bb19236e51df73a4c595cdfba7ff124e77c4b457ca1771006c647c2feff46890

Observation 7889afeb-f476-4712-860c-e0e901dd79c1 · outbound

This paper cites Confident adaptive language modeling.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Confident adaptive language modeling

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.820743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.820743Z digest=sha256:64fdb5c40c7c8283b11413488dca63e3cd77575cf556a63f2e200ba1ecfd546f

Observation 8d524fcb-9f4c-4b42-a162-1ea91cbabb0d · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones A Simple and Effective Pruning Approach for Large Language Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.823761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.823761Z digest=sha256:ffb63b695b621e5cdba7356aa00e73a530a796e9297e529e18d84114e11529f0

Observation cdc59e29-9908-4fb1-9b2a-68050dc67d0b · outbound

This paper cites and Naganuma, H.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones and Naganuma, H

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.827082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.827082Z digest=sha256:ca3599c1ef2b5c99b57faf8cc958ac1ee43c2a59304956e982ce07883ab31c3e

Observation b00f86cc-a165-4c26-aa23-60b93e71860f · outbound

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

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Branchynet: Fast inference via early exiting from deep neural networks

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.830171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.830171Z digest=sha256:49cd636cf881ae060c03b26e4bd7c4b0229f27c2222f1a614928cdffe3f695ed

Observation f2b11145-d33f-4198-9acc-a5a22a317f94 · outbound

This paper cites Open-set recognition: A good closed-set classifier is all you need? 2021.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Open-set recognition: A good closed-set classifier is all you need? 2021

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.218173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.833039Z digest=sha256:dc85a4409b7294c954f0315b938acf5b9656080390bb58e6324b25c693560451

Observation 014d507a-7c2b-485a-b489-423324ccc811 · outbound

This paper cites Calibration in Deep Learning: A Survey of the State-of-the-Art.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Calibration in Deep Learning: A Survey of the State-of-the-Art

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.836629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.836629Z digest=sha256:ce61aa455a2cba2e39a85dfe3baf637d8fe0afe7282393a6a07743f1023f74d1

Observation 4afa6e13-0f3a-411a-9fdf-418dd922f402 · outbound

This paper cites Rethinking calibration of deep neural networks: Do not be afraid of overconfidence.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Rethinking calibration of deep neural networks: Do not be afraid of overconfidence

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T00:46:18.205918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-08-11T00:46:17.840081Z digest=sha256:1c63183629b10e49fc0de0ed4e5e5d4bf860f572e96f555ae3cb12639a7013fb

Observation ebf1b9b5-f4bb-4ddd-8288-9940641da336 · outbound

This paper cites Emergent Abilities of Large Language Models.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Emergent Abilities of Large Language Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.843536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.843536Z digest=sha256:e9bf641bff7bd30e287326bd074a39ad414afe0119addb19ecbad9a2da03e2b3

Observation d0555f4e-ad26-41fb-ba95-a6a7c57b28a6 · outbound

This paper cites Pytorch image models.

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones Pytorch image models

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-11T00:46:17.847060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T00:46:17.847060Z digest=sha256:3334345cff2e75d93abba0cba628033ef7673753565a106a177fc9a50aad2982

Pith citing papers

No inbound Pith citation observations are available.