Paper Citation Record · LEDGER

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes

As of 6 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2606.20820.

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

pith.paper-citation-record.v1
2606.20820 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T04:50:01.671400Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

41 of 41 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c4d3f61f-5ab1-4ed3-afdd-ffaed72cce90 · outbound

This paper cites Measuring massive multitask language under- standing.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Measuring massive multitask language under- standing

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a23e9a64-24df-47a2-969c-1337dbcf6b10 · outbound

This paper cites Truth- fulQA: Measuring how models mimic human false- hoods.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Truth- fulQA: Measuring how models mimic human false- hoods

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2325adca-7cd6-4619-b525-5635d07d4c91 · outbound

This paper cites Evaluating large language models trained on code.arXiv, 2021.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Evaluating large language models trained on code.arXiv, 2021

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0336edaa-59c1-4e18-ab46-e9bd4bf50fdb · outbound

This paper cites Training language models to follow instructions with human feedback.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Training language models to follow instructions with human feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f887b0-0cf4-44eb-ab83-1d48a55302a0 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da6f48b2-4919-49e6-9814-9b20b403ca01 · outbound

This paper cites an unresolved cited work.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d54e626c-64e1-4824-ac31-57ee158edb7a · outbound

This paper cites Beyond the imitation game: Quantifying and extrap- olating the capabilities of language models.Transac- tions on Machine Learning Research, 2023.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Beyond the imitation game: Quantifying and extrap- olating the capabilities of language models.Transac- tions on Machine Learning Research, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c02233d-e1fb-4f38-be3a-387070439b6b · outbound

This paper cites Holis- tic evaluation of language models.Annals of the New York Academy of Sciences, 1525(1):140–146, 2023.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Holis- tic evaluation of language models.Annals of the New York Academy of Sciences, 1525(1):140–146, 2023

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc08d46-3b8d-40e5-af80-2851590c41f6 · outbound

This paper cites Cer-eval: Certifiable and cost-efficient evaluation framework for llms.arXiv, 2025.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Cer-eval: Certifiable and cost-efficient evaluation framework for llms.arXiv, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6135c387-3078-4c4d-a157-426c082c1fa9 · outbound

This paper cites Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Angelopoulos, Stephen Bates, Clara Fannjiang, Michael I

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 261a384a-88e2-43e8-956f-9400fb2baa5b · outbound

This paper cites Angelopoulos, John C.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Angelopoulos, John C

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9483a7c0-4604-4b07-b3fe-13dd14ae59cd · outbound

This paper cites Estimating means of bounded random variables by betting.Jour- nal of the Royal Statistical Society Series B: Statistical Methodology, 86(1):1–27, 2024.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Estimating means of bounded random variables by betting.Jour- nal of the Royal Statistical Society Series B: Statistical Methodology, 86(1):1–27, 2024

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 538eaf11-cd82-43e0-9eb4-7137707e3495 · outbound

This paper cites Hashimoto.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Hashimoto

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3577c4de-c76b-4498-9a04-bea6d090050e · outbound

This paper cites Can large lan- guage models be an alternative to human evaluations? InACL, 2023.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Can large lan- guage models be an alternative to human evaluations? InACL, 2023

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b8b243b-6f0f-4b24-a333-1cabb4de26bf · outbound

This paper cites Scaling up active testing to large language mod- els.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Scaling up active testing to large language mod- els

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1667cbdc-5144-4d31-a6fa-13f448c37b55 · outbound

This paper cites Confidence sequences for sampling without replacement.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Confidence sequences for sampling without replacement

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1ce2776-81c9-4806-ae6a-f97c198bbade · outbound

This paper cites Concentra- tion inequalities for dependent random variables via the martingale method.Annals of Probability, 36(6): 2126–2158, 2008.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Concentra- tion inequalities for dependent random variables via the martingale method.Annals of Probability, 36(6): 2126–2158, 2008

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b75fcf-9b92-4cac-9341-dd4d9281ee56 · outbound

This paper cites Stabil- ity bounds for stationary φ-mixing and β-mixing pro- cesses.Journal of Machine Learning Research, 11(2), 2010.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Stabil- ity bounds for stationary φ-mixing and β-mixing pro- cesses.Journal of Machine Learning Research, 11(2), 2010

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49275ad4-447e-4770-be86-a3b0fc5e2ec3 · outbound

This paper cites Active testing: Sample-efficient model evaluation.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Active testing: Sample-efficient model evaluation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5923e56a-1b21-411d-8e1e-a9dd12767604 · outbound

This paper cites Adaptive concentration inequalities for sequential decision problems.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Adaptive concentration inequalities for sequential decision problems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecfe21a-055f-44aa-9a88-cbe86a27edc8 · outbound

This paper cites Hypothesis testing with e-values.Foundations and Trends® in Statistics, 1(1-2):1–390, 2025.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Hypothesis testing with e-values.Foundations and Trends® in Statistics, 1(1-2):1–390, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64cd1083-5903-4cec-bbe5-08c8b676baae · outbound

This paper cites Probability inequalities for sums of bounded random variables.Journal of the American Statistical Association, 58(301):13–30, 1963.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Probability inequalities for sums of bounded random variables.Journal of the American Statistical Association, 58(301):13–30, 1963

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50acafe5-6d71-4f03-9fdb-d2db74c75999 · outbound

This paper cites On statistical bias in active learning: How and when to fix it.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes On statistical bias in active learning: How and when to fix it

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c314573a-f40c-466f-8378-73524da79659 · outbound

This paper cites Adaptive sub- modularity: Theory and applications in active learning and stochastic optimization.Journal of Artificial Intel- ligence Research, 42:427–486, 2011.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Adaptive sub- modularity: Theory and applications in active learning and stochastic optimization.Journal of Artificial Intel- ligence Research, 42:427–486, 2011

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b92adf3c-642e-434e-80a5-cc14b0473ad6 · outbound

This paper cites Manning, Andrew Ng, and Christopher Potts.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Manning, Andrew Ng, and Christopher Potts

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab56bfbe-b751-4198-949e-4be6a6953889 · outbound

This paper cites Character-level convolutional networks for text classi- fication.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Character-level convolutional networks for text classi- fication

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e4f48c-0f7a-41c3-8c0f-85f2d40a09b9 · outbound

This paper cites Instruction-following evaluation for large language models.arXiv, 2023.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Instruction-following evaluation for large language models.arXiv, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e748abb4-1302-4a4c-9c04-280bfb2f4344 · outbound

This paper cites Safetybench: Eval- uating the safety of large language models.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Safetybench: Eval- uating the safety of large language models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c62b072-f55d-41c5-8004-74fb62ac8ef4 · outbound

This paper cites Adversarial glue: A multi-task bench- mark for robustness evaluation of language models.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Adversarial glue: A multi-task bench- mark for robustness evaluation of language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b53cfc2-3ea0-4b24-9ec9-dcdfa56159b7 · outbound

This paper cites Promptrobust: Towards evaluating the robustness of large language models on adversarial prompts.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Promptrobust: Towards evaluating the robustness of large language models on adversarial prompts

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a5e7f3-9b72-4e46-b579-27ee189684bc · outbound

This paper cites Active surrogate estimators: An active learning approach to label-efficient model eval- uation.NeurIPS, 2022.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Active surrogate estimators: An active learning approach to label-efficient model eval- uation.NeurIPS, 2022

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23d040f8-4dba-4713-aff1-cf5d41315b88 · outbound

This paper cites Ash, Chicheng Zhang, Akshay Krishna- murthy, John Langford, and Alekh Agarwal.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Ash, Chicheng Zhang, Akshay Krishna- murthy, John Langford, and Alekh Agarwal

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e728233-4fae-4575-b053-42ac40d7ff94 · outbound

This paper cites Howard, Aaditya Ramdas, Jon McAuliffe, and Jasjeet Sekhon.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Howard, Aaditya Ramdas, Jon McAuliffe, and Jasjeet Sekhon

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39040900-c91e-43e1-970d-ed4385492cad · outbound

This paper cites Howard, Aaditya Ramdas, Jon McAuliffe, and Jasjeet Sekhon.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Howard, Aaditya Ramdas, Jon McAuliffe, and Jasjeet Sekhon

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3aa5727-af23-46bf-83a9-90d09a957f09 · outbound

This paper cites Active statisti- cal inference.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Active statisti- cal inference

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c06ea35c-69a0-4b55-99af-4c22d40575ae · outbound

This paper cites Adaptive prediction-powered autoeval with reliability and efficiency guarantees.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Adaptive prediction-powered autoeval with reliability and efficiency guarantees

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86036245-e084-409d-aaec-b29987423c77 · outbound

This paper cites Active, anytime-valid risk controlling prediction sets.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Active, anytime-valid risk controlling prediction sets

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ecb0a2e-aeaa-4c01-82ff-e835a7b2ddea · outbound

This paper cites Revisiting active sequential prediction-powered mean estimation.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Revisiting active sequential prediction-powered mean estimation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60dce39-d78f-43d9-a1fa-7429f2c76c83 · outbound

This paper cites Levin, Yu- val Peres, Csaba Szepesvari, and Geoffrey Wolfer.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes Levin, Yu- val Peres, Csaba Szepesvari, and Geoffrey Wolfer

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df062ce-e14e-490b-98c7-cac681be3860 · outbound

This paper cites 1 N NX n=1 ˜ℓf (xn) # +E.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes 1 N NX n=1 ˜ℓf (xn) # +E

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2f34179-3b60-4eed-8a44-f290a15d8baa · outbound

This paper cites This proves that(C t)1≤t≤N is(1−α)anytime-valid forR.

CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes This proves that(C t)1≤t≤N is(1−α)anytime-valid forR

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-29T04:50:01.671400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.