Paper Citation Record · LEDGER

Mechanistic Interpretability in the Presence of Architectural Obfuscation

As of 16 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2506.18053.

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

pith.paper-citation-record.v1
2506.18053 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:01:48.833743Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+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

45 of 45 outbound references displayed

verified exact1
verified fuzzy27
unresolved15
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 15340689-a38b-4bbf-9919-0112692bb3d7 · outbound

This paper cites The Urgency of Interpretability.

Mechanistic Interpretability in the Presence of Architectural Obfuscation The Urgency of Interpretability

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.487379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 87f06ef0-0c86-4708-818f-cc3df66a131e · outbound

This paper cites Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoen- coders, Diffusion Model, and Transformers.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoen- coders, Diffusion Model, and Transformers

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.473473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f2fd8d91-80fc-4eb3-81ad-a5572a7583d7 · outbound

This paper cites Language models are few-shot learn- ers.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Language models are few-shot learn- ers

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.459645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ba8728df-4176-4ba6-8d21-8043f4741bed · outbound

This paper cites Unleashing the transformers: NLP models detect AI writing in education.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Unleashing the transformers: NLP models detect AI writing in education

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.445538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0a11cad1-5706-411e-910e-7af53362e920 · outbound

This paper cites Chris Olah Nelson Elhage.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Chris Olah Nelson Elhage

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.431725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c5816a35-4dea-466b-91d3-9e2d4f20d29e · outbound

This paper cites Obfus- cation detection in android applications using deep learning.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Obfus- cation detection in android applications using deep learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.417697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9488af0f-b6a8-458a-ad11-1cffe62665e9 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.664542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49dff0b6-5a05-4e6e-accc-520c5511e9d0 · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.

Mechanistic Interpretability in the Presence of Architectural Obfuscation FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.669270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dfc9c13-bbba-4fd1-953f-e39b065a7523 · outbound

This paper cites Distributed Data Parallel (DDP) — PyTorch Documentation.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Distributed Data Parallel (DDP) — PyTorch Documentation

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.403687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9c8157bb-2be5-499d-8ceb-eb54fa7486f6 · outbound

This paper cites A Mathematical Framework for Transformer Circuits.

Mechanistic Interpretability in the Presence of Architectural Obfuscation A Mathematical Framework for Transformer Circuits

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.375958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 74b04e31-3035-450a-b673-9049dd46c5b5 · outbound

This paper cites Multimodal Neurons in Artificial Neural Networks.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Multimodal Neurons in Artificial Neural Networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.686618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 255afd79-b3cc-423a-8689-dbdb7ac1013a · outbound

This paper cites Gaussian Error Linear Units (GELUs).

Mechanistic Interpretability in the Presence of Architectural Obfuscation Gaussian Error Linear Units (GELUs)

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.691820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4020c32-ac2b-43d5-b0cd-398d4919a450 · outbound

This paper cites Deep into the brain: artificial intelligence in stroke imaging.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Deep into the brain: artificial intelligence in stroke imaging

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.362041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2a7403eb-699e-49c6-8244-0c57121c4133 · outbound

This paper cites An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference.

Mechanistic Interpretability in the Presence of Architectural Obfuscation An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.348227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f9f3cb6c-6916-403f-b2f3-20de3f06e67c · outbound

This paper cites An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference.

Mechanistic Interpretability in the Presence of Architectural Obfuscation An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-08-15T19:01:48.704422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed5f2f6-4ab1-42a3-8ff4-9fc819f86d48 · outbound

This paper cites CENTAUR: Bridging the Impossi- ble Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference.

Mechanistic Interpretability in the Presence of Architectural Obfuscation CENTAUR: Bridging the Impossi- ble Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.332463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 131733db-3f00-4c89-b685-88f11edeef28 · outbound

This paper cites Online normalizer calculation for softmax.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Online normalizer calculation for softmax

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.717644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130c1642-c954-4d55-a4c6-bf23f305e53f · outbound

This paper cites CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference.

Mechanistic Interpretability in the Presence of Architectural Obfuscation CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.713042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4da8f41-72a2-47b7-8943-deb5f67baecf · outbound

This paper cites Towards Monoseman- ticity: Decomposing Language Models With Dictionary Learning.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Towards Monoseman- ticity: Decomposing Language Models With Dictionary Learning

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.301640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e858d073-a5c1-4bd8-8e24-941227b5a66a · outbound

This paper cites SentinelLM.

Mechanistic Interpretability in the Presence of Architectural Obfuscation SentinelLM

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.316886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e7a937a4-6465-46ef-addd-734443414e7b · outbound

This paper cites Interpretable and explainable machine learning for materials science and chemistry.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Interpretable and explainable machine learning for materials science and chemistry

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.287259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6cd84c6f-2f21-4f9b-8f99-c5287d57818d · outbound

This paper cites The fineweb datasets: De- canting the web for the finest text data at scale.

Mechanistic Interpretability in the Presence of Architectural Obfuscation The fineweb datasets: De- canting the web for the finest text data at scale

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.272647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 27571ffd-407f-486a-84f0-33be5c707359 · outbound

This paper cites Security and Privacy for Artificial Intelligence: Opportunities and Challenges.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Security and Privacy for Artificial Intelligence: Opportunities and Challenges

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.735965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c4eb8a2-9f2b-473e-a8ad-fb905e72ceaf · outbound

This paper cites Invariant Visual Repre- sentation by Single Neurons in the Human Brain.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Invariant Visual Repre- sentation by Single Neurons in the Human Brain

Reference 24

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T19:01:49.258843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e364a275-86e8-4db7-bd80-6fed8f4d1df0 · outbound

This paper cites Language models are unsupervised multitask learners.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Language models are unsupervised multitask learners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.758616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5262df1b-b848-4a89-b1ab-54ac7dc13b4f · outbound

This paper cites Using the Output Embedding to Improve Language Models.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Using the Output Embedding to Improve Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.749605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d47428c-28fb-437d-8747-842f12b4c396 · outbound

This paper cites Mapping the Mind of a Large Language Model.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Mapping the Mind of a Large Language Model

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.221124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9093cff9-87d5-4576-b58a-ac74f7fed3fb · outbound

This paper cites On the Biology of a Large Language Model.

Mechanistic Interpretability in the Presence of Architectural Obfuscation On the Biology of a Large Language Model

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.191674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 08191bb7-db7e-4839-8869-9f89642c2609 · outbound

This paper cites Transformers for Natural Language Processing and Computer Vision: Explore Generative AI and Large Language Models with Hugging Face, ChatGPT, GPT-4V , and DALL-E 3.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Transformers for Natural Language Processing and Computer Vision: Explore Generative AI and Large Language Models with Hugging Face, ChatGPT, GPT-4V , and DALL-E 3

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.235511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 393dd8c4-0d59-4661-99b4-dfa5801663ed · outbound

This paper cites Fundamentals of neu- ral networks.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Fundamentals of neu- ral networks

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.150073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5e077ced-1f74-482f-bd16-4e8ec8fa5553 · outbound

This paper cites An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs.

Mechanistic Interpretability in the Presence of Architectural Obfuscation An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.793889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38ccf617-f95d-4f08-9f1f-2e147704bead · outbound

This paper cites A survey on explainable artificial intelligence (xai): Toward medical xai.

Mechanistic Interpretability in the Presence of Architectural Obfuscation A survey on explainable artificial intelligence (xai): Toward medical xai

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.135918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ffac11eb-4d4b-47d4-b4a2-dfb431af4860 · outbound

This paper cites pub / 2025 / attribution-graphs/biology.html.

Mechanistic Interpretability in the Presence of Architectural Obfuscation pub / 2025 / attribution-graphs/biology.html

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.177644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ab9cbab4-b0c8-48d6-bdc9-4afc08f38aa4 · outbound

This paper cites Scaling Monoseman- ticity: Extracting Interpretable Features from Claude 3 Sonnet.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Scaling Monoseman- ticity: Extracting Interpretable Features from Claude 3 Sonnet

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.163734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 26113d1e-cfa0-4f3e-ac82-8537c7d59ca1 · outbound

This paper cites On the interpretability of machine learning methods in crash frequency modeling and crash modification factor development.

Mechanistic Interpretability in the Presence of Architectural Obfuscation On the interpretability of machine learning methods in crash frequency modeling and crash modification factor development

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.098269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 01801115-74e7-4c14-b372-3bbb8ca452c7 · outbound

This paper cites Deep exploration of random forest model boosts the interpretability of machine learning studies of complicated immune responses and lung burden of nanoparticles.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Deep exploration of random forest model boosts the interpretability of machine learning studies of complicated immune responses and lung burden of nanoparticles

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.083713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 90112bc5-c7ad-4f27-ba63-168aebc5a06e · outbound

This paper cites Secure Transformer Inference Protocol (STIP).

Mechanistic Interpretability in the Presence of Architectural Obfuscation Secure Transformer Inference Protocol (STIP)

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.068757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff25f115-ee00-45a6-8443-84f7a7b2c6d0 · outbound

This paper cites Attention is all you need.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Attention is all you need

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.802953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d757177c-4502-4386-a5a5-e34e48ad4f9c · outbound

This paper cites Interpretability in the wild: A circuit for indirect object identification in GPT-2.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Interpretability in the wild: A circuit for indirect object identification in GPT-2

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.112535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9f9be481-78ab-4038-a37f-6c5b08200f7a · outbound

This paper cites Secure Transformer Inference Protocol.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Secure Transformer Inference Protocol

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.824809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e75de9b-a41e-4268-a289-d775af358019 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

Mechanistic Interpretability in the Presence of Architectural Obfuscation HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.829146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9867a7bb-8191-4988-a970-495cef59b6fb · outbound

This paper cites PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN.

Mechanistic Interpretability in the Presence of Architectural Obfuscation PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T19:01:48.833743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e9dac1e-1f76-4eaf-b69b-6f2fd20ec3c7 · outbound

This paper cites SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference.

Mechanistic Interpretability in the Presence of Architectural Obfuscation SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference

Reference 2023

Resolution: verified exact; local_arxiv, observed 2026-08-15T19:01:48.979228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 04c35613-4317-4a9d-b5cd-919efcdff655 · outbound

This paper cites anthropic.

Mechanistic Interpretability in the Presence of Architectural Obfuscation anthropic

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T19:01:49.206444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e19e6caf-1ede-4371-af21-a369f6a2c2d3 · outbound

This paper cites an unresolved cited work.

Mechanistic Interpretability in the Presence of Architectural Obfuscation Unresolved cited work

Reference 2025

Resolution: unresolved; raw_fallback, observed 2026-08-15T19:01:49.389378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.