Paper Citation Record · LEDGER

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns

As of 17 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2508.15847.

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

pith.paper-citation-record.v1
2508.15847 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T18:42:05.294972Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:13:40.647733Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T03:16:33.739857Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy3
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 403a2550-4677-421d-bdee-55de7ec0f350 · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.238021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a620e48-d7a8-4301-a05c-a7ef39b165c8 · outbound

This paper cites Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.307630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7abfcec-0977-4a6d-828a-a11bcbc4d460 · outbound

This paper cites Recent Advances in Attack and Defense Approaches of Large Language Models.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Recent Advances in Attack and Defense Approaches of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.383300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df432818-e433-4455-ae35-4ac1d1537c99 · outbound

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

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.467875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592ce2d9-bca5-48a2-a612-c38f97764d23 · outbound

This paper cites Databricks dolly 15k.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Databricks dolly 15k

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:42:11.687473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 93af301e-1203-4cc0-ac7e-bbf5d07fe263 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.608896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4abab52-5060-4ffc-b8d7-5855715ba881 · outbound

This paper cites A comprehensive mechanistic interpretability explainer & glossary.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns A comprehensive mechanistic interpretability explainer & glossary

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:42:11.449896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 33df2d56-405c-4584-b48d-f0f05d6b4a74 · outbound

This paper cites The Alignment Problem from a Deep Learning Perspective.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns The Alignment Problem from a Deep Learning Perspective

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.769943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7ed8668-dcda-44e3-9099-6fb24c2dcd29 · outbound

This paper cites Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.836852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1127dc0b-0c0f-49ac-b1f8-90151723e9e8 · outbound

This paper cites Open Problems in Mechanistic Interpretability.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Open Problems in Mechanistic Interpretability

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:02.956496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a9f3636-4ce3-4238-90fc-43f37fea98a8 · outbound

This paper cites Qwen2.5-3b-instruct (bnb-4bit) [model card].

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Qwen2.5-3b-instruct (bnb-4bit) [model card]

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:42:11.271580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6e34afb6-2ac8-493c-bddd-f4133028594e · outbound

This paper cites Qwen2.5 Technical Report.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Qwen2.5 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T18:42:03.138232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 851bad8f-036a-4b53-9fe3-8964b633e627 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:11.035674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c75eccbc-7c05-48a0-86d9-7e182652f339 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:10.729211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 36704ca7-4075-4e91-9e6b-452517ded282 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:10.472091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 89c94d4d-7b0a-4220-9aa5-447906b3acc3 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:10.174213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation aefe34db-ed33-4754-bb45-50cf9a35cb1e · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:09.848959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 79752d45-5bfd-4e58-b441-d303b5b2816a · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:09.538172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 87a175d4-cc26-4682-9b9c-2737205c0c5f · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:09.240433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dca61f59-caa4-42ef-8990-0f4858a402f5 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:09.078193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c79856d5-1041-457e-a424-de74754dd0db · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:08.849021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 783ca6f8-38ac-4b89-87f2-5a79c7831a18 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:08.641214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a59f1157-bb5a-4d49-b76d-910cf3425f92 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:08.408352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8f595054-a950-4db3-9133-120098e15ff9 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:08.224586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a52363b3-5b6c-484a-8690-d065da877fc3 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:07.977065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5db5f296-6b72-444b-8813-dc5e74ee6f69 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:07.750877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7508a8e4-e93b-457f-ba30-1376560a3d3a · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:07.580300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f9aa665f-67b3-4d2f-b8ea-f229b8448f2d · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:07.366655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6fa816b4-6103-4385-af01-f9b79ddc7f4d · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:07.140890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fdee0a5d-bcba-4daa-8e73-3b3f61308aaa · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:06.986182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5f517bad-fe98-4fe9-a512-3f9567d6a2d7 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:06.766902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dc9f06fa-912b-48e2-acbf-2e099b22815a · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:06.562920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b22b7850-2d30-4523-82ec-f4dbbe6cc154 · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:06.404309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5f30037b-632e-4e88-9833-6710c6f1917f · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:06.253253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7630a092-8bed-40e3-bb4a-51994fc7728e · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:06.063363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2d82cab2-21ac-4229-9779-e44498de1c6d · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:05.876646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a5137ea3-a313-44bf-b521-79fab710d30a · outbound

This paper cites an unresolved cited work.

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:42:05.692513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation c58f6815-c7bb-41d1-be07-2be65ca3ad2f · inbound

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs cites this paper.

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs Mechanistic Exploration of Backdoored Large Language Model Attention Patterns

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:16:33.742217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.