Pith. sign in

Paper Citation Record · LEDGER

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination

As of 10 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2608.07341.

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

pith.paper-citation-record.v1
2608.07341 v1

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T06:02:27.994149Z

measured 54 of 54 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 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

54 of 54 outbound references displayed

  • verified exact4
  • verified fuzzy17
  • unresolved33
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d7dc0e89-79b5-481c-87cf-f918672263dd · outbound

This paper cites LNE -Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination LNE -Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models

Reference 1

Resolution
verified exact
doi, observed 2026-08-10T06:02:28.228112Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.740716Z digest=sha256:a60d99f5183d7b462313950ff1f91a527932602bd01bbdf6e7a5ba6e5eb52dc6

Observation 02e918b6-b44b-4b19-b33c-6f4fec5de48a · outbound

This paper cites Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis

Reference 2

Resolution
verified exact
doi, observed 2026-08-10T06:02:28.213191Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.747195Z digest=sha256:64e632f644054cc7397e6e87c23aca7d8eaeac4202ae79dfb187ed7b1830c4ec

Observation 3b679bda-9fbe-4449-ba69-6a0961e31184 · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination The Thirteenth International Conference on Learning Representations , year=

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.773965Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.752835Z digest=sha256:70b62685a7de78459e663ff0b8a9633ee32ce221d49a36aa60ec31012e964225

Observation b94b7bb4-6e53-4207-a00a-d0bf051febaf · outbound

This paper cites DeepSeek-V4 : Towards Highly Efficient Million-Token Context Intelligence.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination DeepSeek-V4 : Towards Highly Efficient Million-Token Context Intelligence

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.757864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.757864Z digest=sha256:91ff2149bf17ebf4702a1ee5192dc2450f7dfc9cd946dd83e427598108467206

Observation f3faf0c9-2c57-4b72-b710-0a8fda80ff42 · outbound

This paper cites Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.758493Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.762702Z digest=sha256:689b51fc7627384dd7fab8c1e642866457ddf7fa2f4205aa4525e1a386f8f427

Observation 799ed2d2-eb18-458b-ae47-a45aba6f4e16 · outbound

This paper cites OpenOrca : An Open Dataset of GPT Augmented FLAN Reasoning Traces.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination OpenOrca : An Open Dataset of GPT Augmented FLAN Reasoning Traces

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.742644Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.767463Z digest=sha256:2ef52c72fb0a7a55f80cddcfe222f2ba9c6e2198b2a8aa9d8f4514acbfd12d88

Observation 1e5f1813-3186-458d-ade2-a42e97a82854 · outbound

This paper cites Gemma 4 Technical Report.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Gemma 4 Technical Report

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.772444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.772444Z digest=sha256:ca95c1ed80589ea8c7fa4e4d6df7629fb9e6348cb2b41e9106b33a365a18cc03

Observation 6b072f53-aa78-40f9-961c-14e1a412e8f7 · outbound

This paper cites and Zhou, Denny.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination and Zhou, Denny

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.726506Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.778487Z digest=sha256:24174bc3df6dcdcec53016e84f8438f9301f9c5574a969f1bdd0505b2e274416

Observation b013282a-0dc2-4804-8ab3-894d2e50c897 · outbound

This paper cites and Le, Quoc V.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination and Le, Quoc V

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.710640Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.783126Z digest=sha256:94e15b94d7a351f5983a601a7f02d59d5d8d59ac3ee5375871b4be19530686bc

Observation 0d24cd1d-2c3e-4ff3-963f-d67b9d1b5c7b · outbound

This paper cites Chain-of-Dictionary Prompting Elicits Translation in Large Language Models.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Chain-of-Dictionary Prompting Elicits Translation in Large Language Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.788123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.788123Z digest=sha256:48831820756069944d76e719af8747137749f12728b56b8586d2b2265ae359af

Observation c6f55e24-0f54-49e1-bcb9-d723dce71c50 · outbound

This paper cites Chain-of-Thought Reasoning Without Prompting.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Chain-of-Thought Reasoning Without Prompting

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.793116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.793116Z digest=sha256:65af3c0b072fee5c252fd3852dcbe07e222b2e93a0a42ed26518b4fbac5ad84f

Observation 2e42c8f1-431c-427a-90e4-d81927a8802a · outbound

This paper cites Leak, Cheat, Repeat:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Leak, Cheat, Repeat:

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.798336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.798336Z digest=sha256:e8447f958805b62bae3a5b033453ac9e9f2d3d470a8746d23544e443a2ebe3ce

Observation d2e906ae-999f-4aa2-b35f-b1ac8b37f6ef · outbound

This paper cites Large Scale Kernel Machines , author =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Large Scale Kernel Machines , author =

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.695314Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.803038Z digest=sha256:81ee0b78c82952f8e7c50c2d68a8a622ffb9cdb055601db531b6388d05851c14

Observation fc81245f-475d-4b99-8bdd-7649ab6b12cd · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Evaluating Large Language Models Trained on Code

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.807650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.807650Z digest=sha256:880791970c0adada09fc426f5184c0bc9ea3686e37d89a937809dc60a6d3b93a

Observation e56585dc-b039-4315-a18a-de56c1f1be79 · outbound

This paper cites Findings of the Association for Computational Linguistics:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Findings of the Association for Computational Linguistics:

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.812585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.812585Z digest=sha256:f0c4a68209d4f6bfdbf6c97e7ae408e64bc5068a53c2cc0c521533cbe8f5e803

Observation 38c5e3ce-ca40-41cb-be76-c9d1d72f8e72 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Training Verifiers to Solve Math Word Problems

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.817062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.817062Z digest=sha256:572c0ac0274a7d991636f7750101d5e42750735cb45b64858454a3da0dab5919

Observation 21d222fa-acb9-4937-b738-0a60d99dbfdd · outbound

This paper cites Unveiling the Spectrum of Data Contamination in Language Model: A Survey from Detection to Remediation , booktitle =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Unveiling the Spectrum of Data Contamination in Language Model: A Survey from Detection to Remediation , booktitle =

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.821781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.821781Z digest=sha256:e1deebf362c50a9efe783fce55563e0bac1b35502ff6c7b004d02f7ee190636a

Observation 5c12fa61-9aaf-47c4-933c-2cf7a59df6c2 · outbound

This paper cites Pretraining.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Pretraining

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.826574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.826574Z digest=sha256:0ed9ffe3a192a8bb519de03c0453f1217920d2ef6d2c56ec60f99fecc0d84ece

Observation de4f2eda-60d6-4b51-8a3d-666952a3447a · outbound

This paper cites Generalization or Memorization:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Generalization or Memorization:

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.831286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.831286Z digest=sha256:5b281005b923eff0c8e9156a614540bdef5383c025e32fbddee22e8a745760c7

Observation 02eaa788-d44d-42ca-b46c-40bb600a3908 · outbound

This paper cites The Llama 3 Herd of Models.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination The Llama 3 Herd of Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.835926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.835926Z digest=sha256:5ebc585553c72d7fe749d305a749bdb5d143101c9b289f3748b4577682b968e3

Observation 6739cf4b-ba39-4914-9630-21428556c78e · outbound

This paper cites 2023 , journal =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination 2023 , journal =

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.680155Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.840805Z digest=sha256:856b4f85ccd19eed8927cac34e12c6caf9ffb71dc766dcaec4fa45f8ef2906d9

Observation c60bd7b2-9bb1-49b5-afd6-ab53f3303007 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:

Reference 22

Resolution
verified exact
doi, observed 2026-08-10T06:02:28.123179Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.845191Z digest=sha256:5a306f4b0e323f54ac8a06d34719fce8d2106d84284d599508db4ebddd3d4356

Observation fd2ac138-5a0e-4983-8c1b-90720ec659e1 · outbound

This paper cites Treeeval:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Treeeval:

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.665242Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.849759Z digest=sha256:bf3e21d8790fe60f9231016c6c4ac84c888c32f33cf513b86f7475f8ead40530

Observation 0fb6a903-0109-44ab-a35c-c39c093b0e00 · outbound

This paper cites and Dodge, Jesse , year =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination and Dodge, Jesse , year =

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.650218Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.854332Z digest=sha256:734285255622c8df83c439dfb608910d957ec853876e4d88c3a853a54551eea0

Observation b0892300-bfe3-490d-8554-982ae3166c11 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) , address=.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) , address=

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.858536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.858536Z digest=sha256:aee0a3874868266c23a3e8decf32de81d6fafaa0d8d1f39913de80d78dd0f527

Observation efeea341-8de7-40da-8d8d-e2b229beab9e · outbound

This paper cites The Twelfth International Conference on Learning Representations , author =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination The Twelfth International Conference on Learning Representations , author =

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.625870Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.862663Z digest=sha256:005e7fcbcf7c05e5fe5112f0268609dc53dda4bc543fbc1e8b26f53120b78b4c

Observation a086d665-37c6-4346-bd47-e8db86cb0b6c · outbound

This paper cites 2016 , volume =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination 2016 , volume =

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.611623Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.866563Z digest=sha256:a252e8b9da37cbd42a11148f3791e04692fc862206443ccaf558202caf7833fb

Observation 4e0a3506-1721-4e7c-9eb7-6049c9d5961b · outbound

This paper cites Language Models are Few-Shot Learners.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Language Models are Few-Shot Learners

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.870440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.870440Z digest=sha256:f0dbbcaad9d2d622c337c8e3cd0f0e993de7ed188a9c4d59689211013de28e44

Observation 912e8849-8496-4542-be09-2460d1e5e043 · outbound

This paper cites 2023 , eprint =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination 2023 , eprint =

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.874530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.874530Z digest=sha256:855bd7a91bb876c75edd575f786491e8c303242b9e4f4d641f63e7aa162b1115

Observation 68012d3d-a7cc-4914-b0aa-912ccfa7bff5 · outbound

This paper cites Privacy Risks of General-Purpose Language Models , booktitle =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Privacy Risks of General-Purpose Language Models , booktitle =

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.586670Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.878400Z digest=sha256:a25f8b4179b59624359eaa6b5ec8f59614ed5c68acf236085236136a6dc69ba3

Observation 2e9ede79-c27b-40e9-9e6a-5efd4a8f9ddb · outbound

This paper cites Don't Make Your LLM an Evaluation Benchmark Cheater.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Don't Make Your LLM an Evaluation Benchmark Cheater

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.882400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.882400Z digest=sha256:5e2df6f3426cbfb62b69b8949ba20b1e45170b5cb82998ede78402fa9af51da4

Observation 13615bf3-77df-4b8d-b153-3737578c7886 · outbound

This paper cites Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.886353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.886353Z digest=sha256:25958bb601c42985af9cc7a37c11bea30aec4a1cfad34982a5d1b2e8e857eed9

Observation 6aa0321a-9e9f-42e9-b599-59ca0f263cc9 · outbound

This paper cites Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.891496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.891496Z digest=sha256:53d8e2e58d03d916c4a32cc31c9f8cb458dbb7014918e21b24112b8e7ee418a1

Observation 41e8f71b-fdad-4951-903b-e7f07db99eb0 · outbound

This paper cites 2006 , journal =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination 2006 , journal =

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.571341Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.896375Z digest=sha256:f6b850325d216eae1df2051c9d1997599577880b456d2c7762a531d254ddc574

Observation 1438432d-7512-4c88-b0cf-cea4e97eca08 · outbound

This paper cites Chain-of-Symbol Prompting for Spatial Reasoning in Large Language Models , booktitle =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Chain-of-Symbol Prompting for Spatial Reasoning in Large Language Models , booktitle =

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.556718Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.901086Z digest=sha256:c7382ba9b39451c310fe34b317027c8898c1707c94c7551c1b84ee3aa393bbbb

Observation 4b0fff4c-1a87-4db3-94e7-ee84b51529a2 · outbound

This paper cites Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1:

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.905509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.905509Z digest=sha256:c4876f16c3210be0196f34d3861a09092f6c6671280a5f950d21dab8b2344a87

Observation 929c8c72-44c0-4045-8818-d6ad35adaaeb · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.910224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.910224Z digest=sha256:fb59147172310c30f3bc7b048f9808d43cc4902a3ead2f73420dfe05a754f82b

Observation 063346a9-d529-4a27-b971-116dc34e7570 · outbound

This paper cites StarCoder: may the source be with you!.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination StarCoder: may the source be with you!

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.914735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.914735Z digest=sha256:89a74f3bc3e637f891591aa1dcdc27bc25d6c4f0736f89fee0f30ace2cee056c

Observation ed307eb7-0c73-44fa-a888-517c3b418fd1 · outbound

This paper cites TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.919399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.919399Z digest=sha256:e165ecadd7fe81cb5879160fb4547487ec3b692128a3bbfe7a381123f29edf3f

Observation 3bda2178-6507-4e9a-ad6d-d93c2f4ffc54 · outbound

This paper cites 2004 , month = jul, pages =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination 2004 , month = jul, pages =

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.541126Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.924422Z digest=sha256:cb84925b3b69e93baa7f0d956d974b6f5e01603897d266e13eccef932cbf1c4c

Observation c2c69a22-e0d4-4e3b-9e6d-c75298206ca4 · outbound

This paper cites 2023 , month = may, pages =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination 2023 , month = may, pages =

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.929374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.929374Z digest=sha256:e89061614ac8af87e98ccb1d3f8f40d3eb031dbf064f2fa4a10ee0b13e424208

Observation 530b11b1-e72e-404c-8d0b-5fc66ad01a44 · outbound

This paper cites Data Contamination:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Data Contamination:

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.940213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.940213Z digest=sha256:81a8a3aea89bee227dbc50e7b6cfe1ec13d84584cc20c7e9184d29cd560ad039

Observation 9109c435-2a1a-473e-8840-4007fa50134d · outbound

This paper cites Detecting Pretraining Data from Large Language Models , booktitle =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Detecting Pretraining Data from Large Language Models , booktitle =

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.525743Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.944963Z digest=sha256:0dff671f50f2753b928151e7baadc645e4378edae351bc3afc6406f6aee362c3

Observation 982db8d6-4ea8-41e2-be15-95c48e073422 · outbound

This paper cites Chain-of-Thought Reasoning without Prompting , booktitle =.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Chain-of-Thought Reasoning without Prompting , booktitle =

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-10T06:02:28.508631Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.949480Z digest=sha256:16a84f54c0ee7512fce51d2e42694823d6fbcb14a7798ccd328b0bf00608b0a0

Observation e8711cba-63a5-4c37-9fc9-959dd8e10b82 · outbound

This paper cites CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.954034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.954034Z digest=sha256:e8b68e989b13eed4bf081eca3ab60b1672ceafed55c6d5df935e9723b41d061f

Observation d04425ab-053e-4ec3-8b66-33e6ea411669 · outbound

This paper cites Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.958702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.958702Z digest=sha256:e730323049eae931cb414f92b59c1c5044f9ec4e5dc590a32e41f17651abee15

Observation c2f6011a-e862-4dd9-a037-b0586e67b740 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Code Llama: Open Foundation Models for Code

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.963441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.963441Z digest=sha256:cc46bd25a7676de34260fb129654369fd41b9e35bd345050b47690161646f9db

Observation 49ed2925-d938-425b-9ee9-894ef6696f16 · outbound

This paper cites Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics:

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.968263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.968263Z digest=sha256:e5ab8101ee173caa380ed730c6e3f8120364177beaa10faa11e2467351d6869d

Observation 7ea003ac-6a3b-4bac-ae59-5b7313bfb4b8 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.973110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.973110Z digest=sha256:3283e2c6254297262b7c7d377295999a35171a1c4f3f987a303c853d045abf25

Observation 24e70c34-4774-402f-8899-bb1cd1f96b1e · outbound

This paper cites Towards Understanding Chain-of-Thought Prompting:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Towards Understanding Chain-of-Thought Prompting:

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.977880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.977880Z digest=sha256:436c6d8dc46cc40e6f0cb54d79542dfd0221ef917470ddf2e2cf6c5efd1f3fbc

Observation e2096714-03e9-454d-a549-08df010e6e34 · outbound

This paper cites Data Contamination Calibration for Black-Box.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Data Contamination Calibration for Black-Box

Reference 51

Resolution
verified exact
doi, observed 2026-08-10T06:02:28.052443Z

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.

source=arxiv_source observed=2026-08-10T06:02:27.982120Z digest=sha256:8c72715c1fcb4c459e70d36f9db38eca29316c1d0741cef4868001c12f8714ff

Observation 6ed97392-827c-42cc-80aa-34d3ca1a2bb8 · outbound

This paper cites Self-Edit:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Self-Edit:

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.986129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.986129Z digest=sha256:4a368d03e07067a59c4a091154a22ae41b1fd30a425aaa26fcb3f8857ee18b12

Observation b3051fb7-1264-46c2-ae22-5c473129c3d2 · outbound

This paper cites A Careful Examination of Large Language Model Performance on Grade School Arithmetic.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination A Careful Examination of Large Language Model Performance on Grade School Arithmetic

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.990201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.990201Z digest=sha256:479eb708cb392e2e1c16152dbfbd685370eb610265f23d9326e531f36c558e75

Observation 4038ac83-4f4f-4f91-928a-a3ac7bac5ec2 · outbound

This paper cites Multilingual Machine Translation with Large Language Models:.

Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination Multilingual Machine Translation with Large Language Models:

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-10T06:02:27.994149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T06:02:27.994149Z digest=sha256:df43f29078155316f9316aa0b63bbd0a9cd0947d9768201c9bd5be76b1256e04

Pith citing papers

No inbound Pith citation observations are available.