Paper Citation Record · LEDGER

Stealing Part of a Production Language Model

As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 43 inbound Pith citation observations for arXiv:2403.06634.

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

pith.paper-citation-record.v1
2403.06634 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 43 of 43 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:37:23.923474Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

7
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 324200b2-0390-47cc-a1a0-5a19ca5ab790 · inbound

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents cites this paper.

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents Stealing Part of a Production Language Model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T20:36:01.431273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f6403f-12c6-4879-a935-d77cd372941d · inbound

Does Prompt Formatting Have Any Impact on LLM Performance? cites this paper.

Does Prompt Formatting Have Any Impact on LLM Performance? Stealing Part of a Production Language Model

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T19:38:26.367067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759ef61a-2a82-4dc0-a07b-7d583a0bdf4a · inbound

AI Safety Frameworks Should Include Procedures for Model Access Decisions cites this paper.

AI Safety Frameworks Should Include Procedures for Model Access Decisions Stealing Part of a Production Language Model

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T19:37:34.866373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c546f038-1618-45cb-84fd-3bc79161a0be · inbound

Position Paper: Model Access should be a Key Concern in AI Governance cites this paper.

Position Paper: Model Access should be a Key Concern in AI Governance Stealing Part of a Production Language Model

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T05:00:04.307866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f9a7a37-d4ad-43c8-a9e1-3f578c733ef6 · inbound

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage cites this paper.

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage Stealing Part of a Production Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T20:30:10.200969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50598d84-6766-4d02-bba8-4313abe9643e · inbound

Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes cites this paper.

Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes Stealing Part of a Production Language Model

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T13:37:58.709784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21199f8f-cd14-411e-b796-7f97485b69b4 · inbound

Rerouting LLM Routers cites this paper.

Rerouting LLM Routers Stealing Part of a Production Language Model

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T22:24:45.431429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7e3a1c-59f7-475f-a08d-89bca95f164c · inbound

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface cites this paper.

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface Stealing Part of a Production Language Model

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T19:44:46.751961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62b9262a-9a08-4344-ae83-fb910a0907e2 · inbound

Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs cites this paper.

Differentially Private In-context Learning via Sampling Few-shot Mixed with Zero-shot Outputs Stealing Part of a Production Language Model

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T20:51:49.931701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95873777-caaa-4f50-8c22-974f7cd15bb1 · inbound

Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights cites this paper.

Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights Stealing Part of a Production Language Model

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T20:53:28.387219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ad216d6-77da-4380-99ad-2b5e500eeafd · inbound

Safety Co-Option and Compromised National Security: The Self-Fulfilling Prophecy of Weakened AI Risk Thresholds cites this paper.

Safety Co-Option and Compromised National Security: The Self-Fulfilling Prophecy of Weakened AI Risk Thresholds Stealing Part of a Production Language Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T11:37:23.923474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53716b10-733f-4ed7-8eeb-e954633f1122 · inbound

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs cites this paper.

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs Stealing Part of a Production Language Model

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T23:23:39.833907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55c0d075-6f24-4aaa-af3b-a0fc6343dfa6 · inbound

Opening the Scope of Openness in AI cites this paper.

Opening the Scope of Openness in AI Stealing Part of a Production Language Model

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-15T22:45:02.187478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73e0720e-0a6e-4fac-8b0b-2be1b247db27 · inbound

Fragments to Facts: Partial-Information Fragment Inference from LLMs cites this paper.

Fragments to Facts: Partial-Information Fragment Inference from LLMs Stealing Part of a Production Language Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:16:09.316325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e05a6e3-11f7-41e4-af7b-2d666af5c970 · inbound

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services cites this paper.

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services Stealing Part of a Production Language Model

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:34:34.779319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76c89e6d-1f98-451e-ba59-bb9b2433b228 · inbound

Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects cites this paper.

Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects Stealing Part of a Production Language Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:26:34.918711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381bac5a-b44b-42a5-9686-fd745ce10bd0 · inbound

Approximating Language Model Training Data from Weights cites this paper.

Approximating Language Model Training Data from Weights Stealing Part of a Production Language Model

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:58:58.659790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a5c5b6-44fb-4307-84e4-ad3e27534878 · inbound

Report on NSF Workshop on Science of Safe AI cites this paper.

Report on NSF Workshop on Science of Safe AI Stealing Part of a Production Language Model

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:01:43.167408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 595b52f3-0a8b-46de-9fde-a94212a96ecb · inbound

A Survey on Model Extraction Attacks and Defenses for Large Language Models cites this paper.

A Survey on Model Extraction Attacks and Defenses for Large Language Models Stealing Part of a Production Language Model

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T22:23:07.379249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18b7d635-0fdc-43d2-afeb-2ad65315a2bb · inbound

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments cites this paper.

Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments Stealing Part of a Production Language Model

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T21:45:00.538286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5178f43-11bb-42cb-9e4c-c56a29797357 · inbound

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users cites this paper.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Stealing Part of a Production Language Model

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:02:07.798930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1b0a2967-6868-4495-8b81-46222b80ce65 · inbound

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests cites this paper.

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests Stealing Part of a Production Language Model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T17:21:33.552558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6cc971b-6990-4a4d-bb36-32a0697f54b7 · inbound

Differentiating hype from practical applications of large language models in medicine -- a primer for healthcare professionals cites this paper.

Differentiating hype from practical applications of large language models in medicine -- a primer for healthcare professionals Stealing Part of a Production Language Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T14:22:38.225032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae517b6-acfb-4e47-a9c9-c69450885e54 · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Stealing Part of a Production Language Model

Reference 117

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:43.751972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b0fc8b7-9127-4251-8ab1-858a626df843 · inbound

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous cites this paper.

Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous Stealing Part of a Production Language Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T19:39:09.558565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb9fe567-86a7-4880-ac39-825b1a7a7b1f · inbound

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives cites this paper.

A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives Stealing Part of a Production Language Model

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T18:12:36.156283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f7ae2e8-8747-41c1-babe-7158987e99cc · inbound

Fingerprinting LLMs via Prompt Injection cites this paper.

Fingerprinting LLMs via Prompt Injection Stealing Part of a Production Language Model

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-21T21:30:39.350060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3f63330e-4d56-4554-83f7-a46df38057f5 · inbound

CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation cites this paper.

CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation Stealing Part of a Production Language Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T20:28:51.160758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64fe9a5-af37-4d5a-af0c-d61d304bbd01 · inbound

How Well Do AI Systems Solve AP Physics? A Comparative Evaluation of Large Language Models on Algebra-Based Free Response Questions cites this paper.

How Well Do AI Systems Solve AP Physics? A Comparative Evaluation of Large Language Models on Algebra-Based Free Response Questions Stealing Part of a Production Language Model

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-15T13:15:31.225992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95a0a283-8970-463a-a036-3aa3001dabfc · inbound

Characterizing Linear Alignment Across Language Models cites this paper.

Characterizing Linear Alignment Across Language Models Stealing Part of a Production Language Model

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T22:20:23.676745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58a334a5-cd02-4c1b-8a6a-72c40a4a69f2 · inbound

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework cites this paper.

A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework Stealing Part of a Production Language Model

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:51:09.728099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e00a2d22-2289-476c-9e5a-3f71f23555fe · inbound

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference cites this paper.

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference Stealing Part of a Production Language Model

Reference 163

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:36:06.501167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c310ef3d-748e-4d87-8fcf-70172becfe8a · inbound

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data cites this paper.

Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data Stealing Part of a Production Language Model

Reference 85

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:57:21.574789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3a8d368c-665a-4992-9445-d2efd5c3034a · inbound

The Surface You Test Is Not the Surface That Breaks cites this paper.

The Surface You Test Is Not the Surface That Breaks Stealing Part of a Production Language Model

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:33:31.196589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6e1f4a1c-6ff8-432b-9b5f-226f5cf5d927 · inbound

The Geometry of Last-Layer Model Stealing cites this paper.

The Geometry of Last-Layer Model Stealing Stealing Part of a Production Language Model

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:27:09.535940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 94efd86d-ba91-4802-af11-79be1c394e34 · inbound

SoK: Colluding Adversaries in Machine Learning Pipelines cites this paper.

SoK: Colluding Adversaries in Machine Learning Pipelines Stealing Part of a Production Language Model

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-03T02:07:33.530859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bf19d2af-e8e1-4d36-a17c-4fc5c33f01bb · inbound

OTRO: Oblivious Tokenization Path with Square-Root ORAM cites this paper.

OTRO: Oblivious Tokenization Path with Square-Root ORAM Stealing Part of a Production Language Model

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:28:49.722869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 83fcb56b-12d2-446f-92ad-13bf22621414 · inbound

Channel Location Constrains the Auditability of Subliminal Learning cites this paper.

Channel Location Constrains the Auditability of Subliminal Learning Stealing Part of a Production Language Model

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:19:44.429061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 59e7817f-0402-4097-a72f-42a48e7716a3 · inbound

Surrogate Fidelity: When Can Open LLMs Explain Closed Ones? cites this paper.

Surrogate Fidelity: When Can Open LLMs Explain Closed Ones? Stealing Part of a Production Language Model

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-07-01T09:45:40.067713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d6d491e5-9e09-4ed9-9c0a-f9c281da15ac · inbound

Black-Box Inference of LLM Architectural Properties with Restrictive API Access cites this paper.

Black-Box Inference of LLM Architectural Properties with Restrictive API Access Stealing Part of a Production Language Model

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:38:58.167809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3c42abf6-f1ef-4a00-b1dc-878cc251cc65 · inbound

Can Watermarking Techniques Help Prevent LLM Model Stealing? cites this paper.

Can Watermarking Techniques Help Prevent LLM Model Stealing? Stealing Part of a Production Language Model

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-14T09:13:20.561611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1692e84-1271-44fa-bb01-77d0f6edbccd · inbound

Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions cites this paper.

Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions Stealing Part of a Production Language Model

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T02:34:08.606939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13dc8bbc-f492-4229-9cb5-4ada2d9b8f04 · inbound

Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions cites this paper.

Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions Stealing Part of a Production Language Model

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T01:45:18.338994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.