Pith. sign in

Paper Citation Record · LEDGER

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis

As of 18 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 2 inbound Pith citation observations for arXiv:2505.03019.

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

pith.paper-citation-record.v1
2505.03019 v1

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:07:34.103309Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:46:43.991193Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T21:11:50.756949Z

Reference resolution

20 of 20 outbound references displayed

  • verified exact0
  • verified fuzzy3
  • unresolved16
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 24695354-4742-42e9-b906-b71d8acad233 · outbound

This paper cites https://www.europarl.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis https://www.europarl

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.029898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.029898Z digest=sha256:f93bd017dcd4feabbe2650f7cb30c655199b71b5bc8ea0ba5eaeafd72266a089

Observation 74e7b0e7-b359-4b1f-939b-e5db3fc9da6b · outbound

This paper cites Quantifying Memorization Across Neural Language Models.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Quantifying Memorization Across Neural Language Models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.038036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.038036Z digest=sha256:852ec4a9c6bc97d78502f2dceb3760c6e1e81785df414cc864830cbbe0069dd7

Observation c02fa179-cee8-4225-809f-bd6510e53573 · outbound

This paper cites Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.046125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.046125Z digest=sha256:e96d3f897aaa9dac53fc763308fa3c041391b2f0dae9b43e02cfec4afd4811d4

Observation 2d90c191-cc0c-4928-98fd-5be4986b5eec · outbound

This paper cites Do Membership Inference Attacks Work on Large Language Models?.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Do Membership Inference Attacks Work on Large Language Models?

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.049906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.049906Z digest=sha256:dc836310a386daf235136577a1512fe0feaf62a7be54542b12be2bf06d1faa70

Observation 491d7ee5-ea69-436e-9c82-ae585f9333f4 · outbound

This paper cites Time Travel in LLMs: Tracing Data Contamination in Large Language Models.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Time Travel in LLMs: Tracing Data Contamination in Large Language Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.058192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.058192Z digest=sha256:5ed269384de7cfc7a2236b7fd7416fc24dc6559453326ad887814ce4ebad0691

Observation 25f11f27-2646-4ece-9566-77cc24e1ba57 · outbound

This paper cites SoK: Memorization in General-Purpose Large Language Models.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis SoK: Memorization in General-Purpose Large Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.062031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.062031Z digest=sha256:e7a5536558004872e322d1d4e54e88aeab4ceeb2b9dc32b0fa244c6874007092

Observation 085a9689-365d-48d6-8de6-3c3d82ded7e8 · outbound

This paper cites org/abstract/document/10179300/.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis org/abstract/document/10179300/

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.069793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.069793Z digest=sha256:2843e028700b471cbc5843627793ecd162aa28b9433de79014fb5ff65d8cb77b

Observation f0025452-bc9f-4144-9d08-b75b6aa59c95 · outbound

This paper cites On Leakage of Code Generation Evaluation Datasets.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis On Leakage of Code Generation Evaluation Datasets

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.073640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.073640Z digest=sha256:79eec08eed55641ce5666d97aed120a38ed217da05cdb3d03f0c546bfa8eaaa2

Observation 444a8571-d1cf-4bfb-be2a-b42fa80f90ec · outbound

This paper cites Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cap- pelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., and Launay, J.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Penedo, G., Malartic, Q., Hesslow, D., Cojocaru, R., Cap- pelli, A., Alobeidli, H., Pannier, B., Almazrouei, E., and Launay, J

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:07:34.439529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T00:07:34.077528Z digest=sha256:0702afc17f94a678293e36ad166620fe39d2bbe51857e4281bc73bde02d72d12

Observation 98f64cc9-4df8-4990-bbb0-b131bb0bb45f · outbound

This paper cites The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.081143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.081143Z digest=sha256:37cec7cfab89d0b369a39c60746b71b0aaffcec3b6d0afe3d12a11d7c14f42f7

Observation d180c1d1-eba5-4cda-bef7-eec595e4d753 · outbound

This paper cites Rethinking LLM Memorization through the Lens of Adversarial Compression.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Rethinking LLM Memorization through the Lens of Adversarial Compression

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.084901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.084901Z digest=sha256:d1b17097e6be5453e37471c44a4fce8547dcac923304399c3fa931c4e02b6372

Observation e96eacc9-41e3-4134-bb49-27e919b260a8 · outbound

This paper cites Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.088695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.088695Z digest=sha256:ea6d499aad7ba362f1fed26dcc290cc9361fcdfbea769aa28879635424ad6620

Observation ea11e795-eac1-4643-bc1b-a7a1fb70affd · outbound

This paper cites On Protecting the Data Privacy of Large Language Models (LLMs): A Survey.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis On Protecting the Data Privacy of Large Language Models (LLMs): A Survey

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.092304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.092304Z digest=sha256:31ffe8980836f71d4ed2615f2fb1e2249864b7abe4a698e9e55870f3b59581d4

Observation 921f573c-2f2e-473b-be9e-e9241d3e29ca · outbound

This paper cites Publisher: Elsevier.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Publisher: Elsevier

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:07:34.425889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T00:07:34.095960Z digest=sha256:280873fd4bee57aa31946936681bbd5f5564b242aadb8bbab01b1c0e90ff1116

Observation 036a795e-a5ba-413c-a70f-17d1db8a4ebe · outbound

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

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Don't Make Your LLM an Evaluation Benchmark Cheater

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.099417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.099417Z digest=sha256:1fdf683a550c6f259beaaf919c9850d1802e4e4e06534af43540f7a36cf7908b

Observation 9a0de113-e215-40cb-aa66-11fe678d4a03 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.103309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.103309Z digest=sha256:b3db7460e6feed1ffe18f778f2798e68dbb002ac0d55b1179d9e90d09fcee693

Observation ada311f7-a6cb-49ca-8d9e-602c03b01b95 · outbound

This paper cites URL https://aclanthology.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis URL https://aclanthology

Reference 2004

Resolution
verified fuzzy
raw_fallback, observed 2026-08-16T00:07:34.450700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T00:07:34.065847Z digest=sha256:e89858592149011b0f033c22eb6712b9c06359f9ebff3ea7e843035653b69013

Observation be430733-5d0a-497a-ae94-26ba07ce04e8 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.054210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.054210Z digest=sha256:9588f0c16f6335ca1cd05247d4425908e721ca547095f64cc3db56ab450d503c

Observation 3e603aed-f286-40e8-aa0c-d22f691fec76 · outbound

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

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-16T00:07:34.034035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-16T00:07:34.034035Z digest=sha256:270c4b6338118112a67e2ce038972907de803101fb3976e061a375bc90314a02

Observation 534eddad-b28b-491d-ba82-b0291ed9c0b3 · outbound

This paper cites Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks.

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks

Reference 2024

Resolution
metadata mismatch
local_arxiv, observed 2026-08-16T00:07:34.341823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-16T00:07:34.041971Z digest=sha256:0ee0fa9d63a9eb2f9bbd6aa5506f59dbf6743e91f397dc0802cb391d4b3c61a1

Pith citing papers

Observation 92948611-ba40-4484-ba14-c17e5cccf686 · inbound

Test of Time: Rethinking Temporal Signal of Benchmark Contamination cites this paper.

Test of Time: Rethinking Temporal Signal of Benchmark Contamination Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis

Reference 1

Resolution
verified exact
arxiv_id, observed 2026-05-18T21:11:50.760908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-05-18T21:10:22.237418Z digest=sha256:465946634148b152ae84d0bb1dace4e1fb8e9fbcdbc36d3f4bd0a09ee1e2802a

Observation 62030fa9-e39b-4e18-a8a5-d71c4dff1972 · inbound

Memorization Diagnostics for Code LLMs Should be Scale-Aware cites this paper.

Memorization Diagnostics for Code LLMs Should be Scale-Aware Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-15T23:46:43.991193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T23:46:43.991193Z digest=sha256:88ca6733919f96f515aea87e4a005bfa8fae5577e64892b9a21c6ec6d2317146