Paper Citation Record · LEDGER

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

As of 24 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 2 inbound Pith citation observations for arXiv:2603.07466.

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

pith.paper-citation-record.v1
2603.07466 v2

Coverage vector

measured 49 of 49 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:40:39.638638Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T20:53:04.274840Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T20:55:03.970803Z

Reference resolution

49 of 49 outbound references displayed

verified exact0
verified fuzzy0
unresolved48
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 332679df-bf6e-46d9-a6b3-8c7b72e7986e · outbound

This paper cites https://cloud.google.com/blog/products/identity-security/how- confidential-computing-lays-the-foundation-for-trusted-ai.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI https://cloud.google.com/blog/products/identity-security/how- confidential-computing-lays-the-foundation-for-trusted-ai

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:34.727117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ef9917-e7ed-4ed4-b073-dd03015fadb9 · outbound

This paper cites https://aws.amazon.com/blogs/machine-learning/large- language-model-inference-over-confidential-data-using-aws-nitro- enclaves/.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI https://aws.amazon.com/blogs/machine-learning/large- language-model-inference-over-confidential-data-using-aws-nitro- enclaves/

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:34.780988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4116905f-c94c-4666-bb80-001f3378850d · outbound

This paper cites Zero-knowledge proofs of training for deep neural networks.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Zero-knowledge proofs of training for deep neural networks

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:34.849268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b85c52-9c1f-4d8d-948c-72db40a89a11 · outbound

This paper cites Trustzone: Integrated hardware and software security.ARM White Paper(2004).

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Trustzone: Integrated hardware and software security.ARM White Paper(2004)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:34.919497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efd47ac8-054f-4d91-9563-b14b9100aeb2 · outbound

This paper cites Fine-tune claude 3 haiku in amazon bedrock, July 2024.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Fine-tune claude 3 haiku in amazon bedrock, July 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.022399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4083daef-51be-4b2b-bcf9-39c76630d3be · outbound

This paper cites Provable data possession at untrusted stores.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Provable data possession at untrusted stores

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.101687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 770e6afb-1c4b-413f-a7f6-d7bed90263b2 · outbound

This paper cites E.,ANDVIJ, M.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI E.,ANDVIJ, M

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.163087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab003c40-c49c-4bf1-9546-6606abffe205 · outbound

This paper cites D., ZHAO, J.,ANDKOUSHANFAR, F.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI D., ZHAO, J.,ANDKOUSHANFAR, F

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.238627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31450c30-0b24-44c0-8f3a-df4ca21e759a · outbound

This paper cites Tune gemini models by using supervised fine-tuning, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Tune gemini models by using supervised fine-tuning, 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.343313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25ac99d9-592d-456e-a9f9-d03305e06b81 · outbound

This paper cites Azure openai in azure ai foundry models, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Azure openai in azure ai foundry models, 2025

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.449271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2117429-17e9-406e-a184-3a43c1f7e9d3 · outbound

This paper cites Host llms with nvidia gpus on oci, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Host llms with nvidia gpus on oci, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.528823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e7e163a-741c-42d2-ab90-c5dd623ff9b0 · outbound

This paper cites Intel sgx explained.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Intel sgx explained

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.600123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7532a31-09cd-47e9-9c15-9fed2539ce07 · outbound

This paper cites Guardain: Protecting emerging generative ai workloads on heterogeneous npu.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Guardain: Protecting emerging generative ai workloads on heterogeneous npu

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.680033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78149fc9-fe09-4c8a-8062-0a21655eff0b · outbound

This paper cites an unresolved cited work.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.782709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65a52bb-bcf9-4fff-acb1-58cf501df0fe · outbound

This paper cites The Llama 3 Herd of Models.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.874672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cfbb277-c8d2-425e-aa2d-a65852318692 · outbound

This paper cites H., LIPTON, Z.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI H., LIPTON, Z

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:35.950506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d59ef8b-3734-4586-850d-ee1604e89424 · outbound

This paper cites Scalable zero-knowledge proofs for non-linear functions in machine learning.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Scalable zero-knowledge proofs for non-linear functions in machine learning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.020273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c948981-ce53-4aaa-b17e-4ec9e0ad4c49 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI LoRA: Low-Rank Adaptation of Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.098375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b584a9-b3f4-484d-a942-734c239b64bc · outbound

This paper cites A survey on hardware accelerators for large language models.Applied Sciences 15, 2 (Jan.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI A survey on hardware accelerators for large language models.Applied Sciences 15, 2 (Jan

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.165450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60510822-eae2-4e21-993c-139366e97c37 · outbound

This paper cites Gramine-tdx: A lightweight os kernel for confidential vms.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Gramine-tdx: A lightweight os kernel for confidential vms

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.235754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf9bb2b3-b9aa-4dac-b74e-6941ccb48119 · outbound

This paper cites Keystone: An open framework for architecting trusted execution environments.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Keystone: An open framework for architecting trusted execution environments

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.309762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa13cddd-7e45-47ef-8c36-08f2571bb453 · outbound

This paper cites Character- ization of gpu tee overheads in distributed data parallel ml training, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Character- ization of gpu tee overheads in distributed data parallel ml training, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.423186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6c5f58-acce-40a5-8d37-4b9348a20c29 · outbound

This paper cites Verilora: Fine-tuning large language models with verifiable security via zero-knowledge proofs, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Verilora: Fine-tuning large language models with verifiable security via zero-knowledge proofs, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.524790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c89a2de4-294e-4813-a862-1bc399308c2a · outbound

This paper cites Against the achilles’ heel: A survey on red teaming for generative models.Journal of Artificial Intelligence Research 82(2025), 687–775.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Against the achilles’ heel: A survey on red teaming for generative models.Journal of Artificial Intelligence Research 82(2025), 687–775

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.642521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 249402ea-0e02-4838-ac5b-96aea6bf2082 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks, 2019.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Towards deep learning models resistant to adversarial attacks, 2019

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.743782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a1b2e27-9c7a-4ed4-9b6d-434ce26d9628 · outbound

This paper cites Ppfl: Privacy-preserving federated learning with trusted execution environments.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Ppfl: Privacy-preserving federated learning with trusted execution environments

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:36.841734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df9c398-2e39-4fe1-af63-f4757babcec7 · outbound

This paper cites Introducing improvements to the fine-tuning api and expand- ing our custom models program.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Introducing improvements to the fine-tuning api and expand- ing our custom models program

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.000004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33ce46c9-bb8c-4748-b4a4-6108881ca0d0 · outbound

This paper cites Model optimization — openai api guides, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Model optimization — openai api guides, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.125989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd6a339e-9b0e-4799-a569-28a71f9118e4 · outbound

This paper cites Dinov2: Learning robust visual features without supervision, 2024.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Dinov2: Learning robust visual features without supervision, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.231993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 175aecb9-5011-4830-97d0-15213d81a17c · outbound

This paper cites zkgpt: An efficient non-interactive zero-knowledge proof framework for llm inference.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI zkgpt: An efficient non-interactive zero-knowledge proof framework for llm inference

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.295425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b9a59d3-0f18-4ac0-9879-2e9e70e7367d · outbound

This paper cites L., GREGOR, F., ARNAUTOV, S., KUNKEL, R., BHATOTIA, P.,ANDFETZER, C.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI L., GREGOR, F., ARNAUTOV, S., KUNKEL, R., BHATOTIA, P.,ANDFETZER, C

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.387259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19cee77-899c-4d49-b057-1c47173cb6b1 · outbound

This paper cites Zero- knowledge ai inference with high precision.ACM CCS(2025).

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Zero- knowledge ai inference with high precision.ACM CCS(2025)

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.539982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed8c5432-2c1e-42e6-a0c2-2c53e21b01a4 · outbound

This paper cites C.,ANDFEI-FEI, L.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI C.,ANDFEI-FEI, L

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.631452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e8950a5-5523-4f95-8aa0-f745372e3b3e · outbound

This paper cites an unresolved cited work.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.741620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0d3c508-47ef-4064-b6a4-6610b51be15b · outbound

This paper cites Compact proofs of retrievability.J.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Compact proofs of retrievability.J

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:37.923780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f615bee5-6d2f-4d78-b69a-c821bb33562d · outbound

This paper cites C., BIRKE, R.,ANDPERRI, S.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI C., BIRKE, R.,ANDPERRI, S

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:38.067919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9196c40-33b3-425f-a745-ba666a7e7f70 · outbound

This paper cites Trusted yet flexible: High- level runtimes for secure ml inference in tees.Journal of Cybersecurity and Privacy 6, 1 (2026).

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Trusted yet flexible: High- level runtimes for secure ml inference in tees.Journal of Cybersecurity and Privacy 6, 1 (2026)

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:38.215985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6194aca-fddf-455e-8fd4-834b90ebf5ad · outbound

This paper cites zkllm: Zero knowledge proofs for large language models.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI zkllm: Zero knowledge proofs for large language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:38.370818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17cbbcfb-a0bf-477d-a699-26ef0efbf2c6 · outbound

This paper cites Svip: Towards verifiable inference of open-source large language models.arXiv preprint arXiv:2410.22307(2025).

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Svip: Towards verifiable inference of open-source large language models.arXiv preprint arXiv:2410.22307(2025)

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:38.523053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 044b0072-0bd3-4c67-a37f-98e238d7a9d4 · outbound

This paper cites Pipellm: Fast and confiden- tial large language model services with speculative pipelined encryption.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Pipellm: Fast and confiden- tial large language model services with speculative pipelined encryption

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:38.710020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f27bae9-8dc6-4d4b-a661-84c9ea38ac37 · outbound

This paper cites H2:towards efficient large-scale llm training on hyper-heterogeneous cluster over 1,000 chips, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI H2:towards efficient large-scale llm training on hyper-heterogeneous cluster over 1,000 chips, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:38.857206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2edff27-3c07-4460-822b-935ed5893411 · outbound

This paper cites Visual transform- ers: Token-based image representation and processing for computer vision, 2020.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Visual transform- ers: Token-based image representation and processing for computer vision, 2020

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.003180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6236040-7e9e-4b1c-a780-28a0457d5317 · outbound

This paper cites zkpytorch: A hierarchical optimized compiler for zero-knowledge machine learning.Cryptology ePrint Archive(2025).

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI zkpytorch: A hierarchical optimized compiler for zero-knowledge machine learning.Cryptology ePrint Archive(2025)

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.050167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 419f79a0-6dba-43e1-b234-67624cd332b8 · outbound

This paper cites MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI MentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.176313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2d74de-41c5-4d82-a4d4-56595c8d63c4 · outbound

This paper cites Hex- iscale: Accommodating large language model training over heteroge- neous environment, 2025.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Hex- iscale: Accommodating large language model training over heteroge- neous environment, 2025

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.251168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d775fcd-22fd-433b-9606-3affa157c44d · outbound

This paper cites Qwen2.5 Technical Report.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Qwen2.5 Technical Report

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.349252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3799bfb7-6132-4847-8641-de8254501949 · outbound

This paper cites vTune: Verifiable Fine-Tuning for LLMs Through Backdooring.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI vTune: Verifiable Fine-Tuning for LLMs Through Backdooring

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.455371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8b25fe-c989-4072-b458-22d5afdfd9b8 · outbound

This paper cites En- abling execution assurance of federated learning at untrusted partic- ipants.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI En- abling execution assurance of federated learning at untrusted partic- ipants

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T18:40:39.550384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5200c61-c990-4c74-8283-4e27978c342c · outbound

This paper cites Sear: Secure and efficient aggregation for byzantine-robust federated learning.IEEE Transactions on Dependable and Secure Computing 19, 5 (2021), 3329–3342.

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI Sear: Secure and efficient aggregation for byzantine-robust federated learning.IEEE Transactions on Dependable and Secure Computing 19, 5 (2021), 3329–3342

Reference 49

Resolution: malformed identifier; no resolver link, observed 2026-08-02T18:40:39.638638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4842293a-c8c7-4bed-bc5b-5b94fea1796b · inbound

Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs cites this paper.

Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-23T02:23:27.054931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 34855d9d-b935-4bac-8bc0-9b1cb87316f0 · inbound

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands cites this paper.

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-07-23T02:23:27.054931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.