Paper Citation Record · LEDGER

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation

As of 15 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2509.00973.

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

pith.paper-citation-record.v1
2509.00973 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:07:11.652209Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

23 of 23 outbound references displayed

verified exact0
verified fuzzy16
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ed9ac893-2661-4f44-9966-5792fe3ac15c · outbound

This paper cites Fine-Tuning and Evaluating Open-Source Large Language Models for the Army Domain.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Fine-Tuning and Evaluating Open-Source Large Language Models for the Army Domain

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:10.349429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bba18956-fd6a-460c-a974-1ef23a2bb6a7 · outbound

This paper cites Leveraging large language models for integrated satellite-aerial-terrestrial networks: recent advances and future directions,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Leveraging large language models for integrated satellite-aerial-terrestrial networks: recent advances and future directions,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:14.110219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 360cd618-54d5-49f1-a5e7-721c4d37b479 · outbound

This paper cites Fine-Tuned Language Models as Space Systems Controllers.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Fine-Tuned Language Models as Space Systems Controllers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:10.477254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b44b653-a3c7-4b7e-b31a-e3ca3dee67a0 · outbound

This paper cites Milchat: Introducing chain of thought reasoning and grpo to a multimodal small language model for remote sensing,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Milchat: Introducing chain of thought reasoning and grpo to a multimodal small language model for remote sensing,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:10.539648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 837f4ad3-77c1-4055-9cd6-dc65d64b0aba · outbound

This paper cites Pllm- cs: Pre-trained large language model (llm) for cyber threat detection in satellite networks,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Pllm- cs: Pre-trained large language model (llm) for cyber threat detection in satellite networks,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:13.934074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 742ca975-02a7-4f03-ab9d-b1c19c4b4c78 · outbound

This paper cites Stealing part of a production language model,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Stealing part of a production language model,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:13.704683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a3f02d56-85b5-411b-a39c-1b1155b5979f · outbound

This paper cites Teach llms to phish: Stealing private information from language mod- els,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Teach llms to phish: Stealing private information from language mod- els,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:13.576129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 384aabe0-4484-491b-b339-ad00f4a0eb43 · outbound

This paper cites Model Stealing for Any Low-Rank Language Model.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Model Stealing for Any Low-Rank Language Model

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:10.757582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ee1942-8ddf-4c72-8f5a-3b996dae19f3 · outbound

This paper cites I know what you trained last summer: A survey on stealing machine learning models and defences,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation I know what you trained last summer: A survey on stealing machine learning models and defences,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:13.384999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e65321c9-69f1-432f-9500-e6c6cbf9822a · outbound

This paper cites Privacy backdoors: stealing data with corrupted pretrained models,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Privacy backdoors: stealing data with corrupted pretrained models,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:13.227323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 19c1a9b9-b1d0-4069-b048-6c2ca16b70bc · outbound

This paper cites Can’t steal? cont-steal! contrastive stealing attacks against image encoders,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Can’t steal? cont-steal! contrastive stealing attacks against image encoders,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:13.089314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4375ffac-c6ec-46aa-8e18-48c53d30c22b · outbound

This paper cites Large language models for link stealing attacks against graph neural networks,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Large language models for link stealing attacks against graph neural networks,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.981756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c26d160b-1159-4e10-82c8-e2863e8bdd32 · outbound

This paper cites Forensic analysis of indirect prompt injection attacks on llm agents,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Forensic analysis of indirect prompt injection attacks on llm agents,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.886017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b1ca3fc5-ae11-4d66-9915-0d7210cf403a · outbound

This paper cites Llm-sentry: A model-agnostic human-in-the-loop framework for securing large language models,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Llm-sentry: A model-agnostic human-in-the-loop framework for securing large language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.791201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ac480b85-72b1-44da-9fa0-da38193ba19d · outbound

This paper cites Data stealing attacks against large language models via backdooring,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Data stealing attacks against large language models via backdooring,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.699241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 11be3464-c764-458e-aa99-a246e1ae73da · outbound

This paper cites Efficient llm jailbreak via adaptive dense-to-sparse constrained optimization,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Efficient llm jailbreak via adaptive dense-to-sparse constrained optimization,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.601125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e0f1fab5-0a0c-4458-ad74-375c31f3b84b · outbound

This paper cites Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:11.356493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb265e30-d24b-4fc2-9a06-d68ceda36942 · outbound

This paper cites Harmbench: A standardized evaluation framework for automated red teaming and robust refusal,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Harmbench: A standardized evaluation framework for automated red teaming and robust refusal,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.501654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 328185fa-71cd-47d5-b072-c4de987f9897 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Distilling the Knowledge in a Neural Network

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:11.460521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e979c1f7-5401-4ea3-84d4-ebd2145ec30c · outbound

This paper cites Wikitext-2 data,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Wikitext-2 data,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.413599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2f9b11fa-484e-4ba5-af49-a60c3a682def · outbound

This paper cites Wikitext103,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Wikitext103,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.288411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ce7c9430-08b1-4459-bfee-fd9fcdbdbf39 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Scalable Extraction of Training Data from (Production) Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T13:07:11.611656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c11fab-6d5f-4263-b1fc-cdcfa188b7aa · outbound

This paper cites Quantile-based cumulative kullback-leibler divergence in past lifetime: Some properties and applications,.

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation Quantile-based cumulative kullback-leibler divergence in past lifetime: Some properties and applications,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T13:07:12.192698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.