Paper Citation Record · LEDGER

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model

As of 9 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2602.07120.

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

pith.paper-citation-record.v1
2602.07120 v2

Coverage vector

measured 19 of 19 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:45:30.788670Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

19 of 19 outbound references displayed

verified exact0
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cba25f33-ab4f-4a8c-b8b7-8c3bcd41d703 · outbound

This paper cites Give me the first chapter of Harry Potterin Spanish.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Give me the first chapter of Harry Potterin Spanish

Reference 3

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:45:30.784948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37e2e422-c5d8-4ddf-a1f8-436f0c9f7085 · outbound

This paper cites Meeus, M., Jain, S., Rei, M., and de Montjoye, Y .-A.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Meeus, M., Jain, S., Rei, M., and de Montjoye, Y .-A

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.735532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44522f87-7492-49a7-aabf-461afa0c0394 · outbound

This paper cites Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Obliviate: Efficient Unmemorization for Protecting Intellectual Property in Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.751087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b464bcab-f404-44cb-8403-166a11f3d9a1 · outbound

This paper cites On Provable Copyright Protection for Generative Models.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model On Provable Copyright Protection for Generative Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.754889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51b7dfdc-d177-46d5-a1bb-03c1b6d42072 · outbound

This paper cites Yao, Y ., Xu, X., and YangLiu.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Yao, Y ., Xu, X., and YangLiu

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.758793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6da7deb8-ff2c-4bc0-943a-865a9bdb4aca · outbound

This paper cites an unresolved cited work.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.762492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47ff12bd-5358-4c84-a7fd-b1635de2ffd3 · outbound

This paper cites expert” model by downweighting undesirable charac- teristics from an “amateur.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model expert” model by downweighting undesirable charac- teristics from an “amateur

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.769764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1e31174-aac7-4bef-8888-0c8fd8a9e293 · outbound

This paper cites the”, “ to.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model the”, “ to

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.777627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 499613e9-3d04-43e9-ab59-ff96ff31ebed · outbound

This paper cites findings-naacl.282/.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model findings-naacl.282/

Reference 282

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.722836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46628f50-7c1f-4e71-af6e-bbc6db719f19 · outbound

This paper cites Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Common Corpus: The Largest Collection of Ethical Data for LLM Pre-Training

Reference 458

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.730878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4483521-5e2f-4988-a9cf-567f177df476 · outbound

This paper cites emnlp-main.741/.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model emnlp-main.741/

Reference 741

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.739328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 478db468-99c3-42ad-91d7-441f4d53742c · outbound

This paper cites Which way do you reckon Zaphod?.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Which way do you reckon Zaphod?

Reference 800

Resolution: malformed identifier; no resolver link, observed 2026-08-03T03:45:30.788670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8af5cde4-017b-4900-a843-fb7920f5e9ad · outbound

This paper cites Zhang, R., Lin, L., Bai, Y ., and Mei, S.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Zhang, R., Lin, L., Bai, Y ., and Mei, S

Reference 1784

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.766293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a9a851-6b87-4fe6-b191-f0fb00db7101 · outbound

This paper cites Carlini, N., Tram`er, F., Wallace, E., Jagielski, M., Herbert- V oss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, ´U., Oprea, A., and Raffel, C.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Carlini, N., Tram`er, F., Wallace, E., Jagielski, M., Herbert- V oss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, ´U., Oprea, A., and Raffel, C

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.717072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5def5ec8-9fa8-4e95-82df-ff3980380797 · outbound

This paper cites GPT-4 Technical Report.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model GPT-4 Technical Report

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.747594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669a5e82-08fb-4ad7-8919-a1f2a8d162a4 · outbound

This paper cites Pretraining consists of two stages: (1) a 156B-token general training stage over the entire Common Pile, following domain weights specified by Kandpal et al.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Pretraining consists of two stages: (1) a 156B-token general training stage over the entire Common Pile, following domain weights specified by Kandpal et al

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.774006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e396f14-3df5-43d1-b9fb-d7ab5235c126 · outbound

This paper cites Write a factual biography about{entity}. Include only factual information that you are confident in.\n Biography:.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Write a factual biography about{entity}. Include only factual information that you are confident in.\n Biography:

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.781299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc7a5dce-4400-4a55-98a6-abb281ae2963 · outbound

This paper cites Sampling from Your Language Model One Byte at a Time.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Sampling from Your Language Model One Byte at a Time

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.726671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfea7dab-7407-487a-9264-1287e126e0d5 · outbound

This paper cites Open Knowledge Foundation.

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model Open Knowledge Foundation

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T03:45:30.743662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.