Paper Citation Record · LEDGER

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

As of 7 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 5 inbound Pith citation observations for arXiv:2507.03014.

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

pith.paper-citation-record.v1
2507.03014 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-19T06:39:47.345016Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T10:27:28.207221Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T01:56:28.004419Z

Reference resolution

15 of 15 outbound references displayed

verified exact5
verified fuzzy1
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4e68083a-ab61-4872-babb-9d1bef5e0d31 · outbound

This paper cites Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:42:07.411459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0986a530-45a2-421c-9410-ea7a08a07bf4 · outbound

This paper cites The Llama 3 Herd of Models.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! The Llama 3 Herd of Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T06:42:07.424837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 49fa9c77-c893-4f3b-b5c4-3f6b2d167274 · outbound

This paper cites arXiv preprint arXiv:2403.03846.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! arXiv preprint arXiv:2403.03846

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:42:07.414934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 46461970-d5ab-48cd-bb7f-dda313770b5a · outbound

This paper cites Optimizing Data Collection for Machine Learning.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Optimizing Data Collection for Machine Learning

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:42:07.435433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 97b12ff9-9e89-4eef-a3ca-a1937b4cfefe · outbound

This paper cites Training Compute-Optimal Large Language Models.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Training Compute-Optimal Large Language Models

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T06:42:07.432066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3278f412-461b-4a81-b020-8becddd4434d · outbound

This paper cites A Watermark for Large Language Models.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! A Watermark for Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:42:07.428536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 590d2baf-f7a9-41dd-b0df-ac90c3c90843 · outbound

This paper cites Pseudocovering and digital covering spaces.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Pseudocovering and digital covering spaces

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:42:07.418205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0906dc46-91a9-44fb-898e-6891a9c5172d · outbound

This paper cites DeepSeek-V3 Technical Report.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! DeepSeek-V3 Technical Report

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T06:42:07.421258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6dc45db9-bff4-4102-8cc7-2f51969d670d · outbound

This paper cites In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pages 2413–2426.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pages 2413–2426

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:42:59.839960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bb8b6b84-39b4-4dd6-8411-0ae5ab880df9 · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! OLMoE: Open Mixture-of-Experts Language Models

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T06:42:07.445381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b32eb869-f5fd-434b-bce9-41a2f2d1230d · outbound

This paper cites CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenario

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:42:07.441401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b8607c7c-bddb-4430-9216-a9e04df0cd5d · outbound

This paper cites ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:42:07.438419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 16f35138-4123-4a47-b070-9748ec198a14 · outbound

This paper cites Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:42:07.456953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c8e21bc1-50ba-4f18-823b-ef720d49f2dc · outbound

This paper cites Qwen2.5 Technical Report.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Qwen2.5 Technical Report

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T06:42:07.452850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6148a196-9f29-49bd-bfc4-754b8f01f636 · outbound

This paper cites Qwen3 Technical Report.

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model! Qwen3 Technical Report

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T06:42:07.449374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 50d655aa-ff98-4f9c-82a3-42ebb5a46369 · inbound

Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends cites this paper.

Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

Reference 172

Resolution: verified exact; local_arxiv, observed 2026-05-18T22:46:53.109175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4d390ab2-6eef-45ee-9ab5-e107b6878374 · inbound

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From cites this paper.

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:01:21.025001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 54c3247f-bcdf-448b-a55a-5609ffbcd250 · inbound

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences cites this paper.

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T01:56:28.006896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4e284165-14b6-43f1-8b4e-0866bf1bc764 · inbound

PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks cites this paper.

PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-12T00:40:49.755070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610d6b97-278d-45e7-a4c4-65f4ed5ee467 · inbound

modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints cites this paper.

modelDNA: Calibrated Lineage Verification and Merge Decomposition from Sampled Weight Fingerprints Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-14T10:27:28.207221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.