Paper Citation Record · LEDGER

Safety Alignment Should Be Made More Than Just A Few Attention Heads

As of 19 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2508.19697.

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

pith.paper-citation-record.v1
2508.19697 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:37:43.548098Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

47 of 47 outbound references displayed

verified exact0
verified fuzzy1
unresolved46
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f0db360-d9df-48fc-a8fc-0ccb53ccffb2 · outbound

This paper cites online" 'onlinestring :=.

Safety Alignment Should Be Made More Than Just A Few Attention Heads online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.370565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee522488-cb6b-424a-b8d9-f5d6ed322cb8 · outbound

This paper cites write newline.

Safety Alignment Should Be Made More Than Just A Few Attention Heads write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.375156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbf360ed-f73f-4a54-b457-2fbdede8c56c · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.995132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 33e08d33-d1b9-49ef-9954-45bcf481a3b1 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.983272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3890f5aa-a57b-4e53-a2c9-ec2276449844 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.972072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2340688c-68f1-47d7-9df7-5b3789607e97 · outbound

This paper cites Qwen Technical Report.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Qwen Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.391804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc99735d-c804-462a-bbdd-824e43830d9e · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Constitutional AI: Harmlessness from AI Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.396680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c1db3a-5030-4530-b662-56a8b3255896 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Mechanistic Interpretability for AI Safety -- A Review

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.400981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a73003-c310-4570-82bf-ccbd335b576e · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.404985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17b2eaea-7818-44ba-83e3-8859ba1b4f8e · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.408604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3da2100f-8afc-441a-916b-03a31ac157a0 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.951921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 749448b3-b5b4-4abe-8e1b-bf720f066d7a · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.940259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1819d16f-6082-44e9-b218-b110beeabc06 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Safety Alignment Should Be Made More Than Just A Few Attention Heads KTO: Model Alignment as Prospect Theoretic Optimization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.422181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a61467d4-8f54-4310-9c2b-f00141d2d915 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.425698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c1ce44a-b628-424b-b5a7-47c2dadec837 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Gemini: A Family of Highly Capable Multimodal Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.429232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80f9913a-6b35-4c56-ab9b-63e86dac1aa5 · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Safety Alignment Should Be Made More Than Just A Few Attention Heads AI Alignment: A Comprehensive Survey

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.432516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 755c308a-0d01-4d06-baf0-3b73067290d0 · outbound

This paper cites Global Challenge for Safe and Secure LLMs Track 1.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Global Challenge for Safe and Secure LLMs Track 1

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.435885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d21299f6-9a59-45c3-a555-22d9333a54c9 · outbound

This paper cites Alignment of Language Agents.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Alignment of Language Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.439457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34129e46-bc3d-44ee-906a-0d90bf20b054 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.929646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d1f490a5-886d-44a7-ae8a-6e568a64fc81 · outbound

This paper cites Scalable agent alignment via reward modeling: a research direction.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Scalable agent alignment via reward modeling: a research direction

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.446319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa2d30b3-2544-4849-8108-0fedc37c5b3a · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.919046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3957d80e-55c7-4401-9e8a-66e17fed6c98 · outbound

This paper cites Boosting Jailbreak Transferability for Large Language Models.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Boosting Jailbreak Transferability for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.453506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7011578b-5ab1-464c-9dd3-faf3565f6261 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.907724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e46496cc-b47b-4f0e-8a7e-c41841a1455a · outbound

This paper cites The Llama 3 Herd of Models.

Safety Alignment Should Be Made More Than Just A Few Attention Heads The Llama 3 Herd of Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.460729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b17ea8d6-8033-4a3d-92ed-fd618d74b409 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.464650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e51253-fb1d-42b4-8f67-1aab142f6939 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.888858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c759547f-2e66-4a45-8447-604c8d1c58f2 · outbound

This paper cites do anything now.

Safety Alignment Should Be Made More Than Just A Few Attention Heads do anything now

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:37:43.877789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 52c3d3f1-4ddb-4cfb-9985-c9454583e8ff · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.867150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7f79a776-8125-4712-a9f4-99015a8a7eba · outbound

This paper cites GPT-4 Technical Report.

Safety Alignment Should Be Made More Than Just A Few Attention Heads GPT-4 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.481527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75605a39-860b-484b-b8c7-14789859144c · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.485281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f226fb92-e79e-438c-a2e5-d7262febd8df · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.851532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 41a6345b-6f57-447f-83e8-d871ae8e5943 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.494720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34c4cc30-0737-4710-9c1f-e0e9781371b6 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.498166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6959a29b-c4ee-4f75-9377-c536877b3439 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.831227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7d870a98-21af-4cd9-8a96-30f09776bfed · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Safety Alignment Should Be Made More Than Just A Few Attention Heads LLaMA: Open and Efficient Foundation Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.504649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87fd86f2-7e25-443a-bbb4-fd89b7236ea1 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.508165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59fa80b8-2c9e-43ea-a5f8-b0db45b9712a · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.511743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7c62e7e-84bc-440c-a000-d63f3e0c3c0e · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.815536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation beff1533-009d-46c9-8f7f-4a7742927594 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.804145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9c9b5235-6194-4b40-a472-c9989183acf2 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.522457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa578bb8-1d23-4068-a9d9-1872e8ec44c1 · outbound

This paper cites Qwen2.5 Technical Report.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Qwen2.5 Technical Report

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.526287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82149382-0843-4504-9649-69c6f09cfdc7 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.529782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b6ea07-1cd3-4e75-b83b-4764bdfc01de · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.787250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4a44ed90-9335-452d-8a3c-b35b33784fe5 · outbound

This paper cites Attention Heads of Large Language Models: A Survey.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Attention Heads of Large Language Models: A Survey

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.536871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968addb9-f8db-4899-8ebf-5ae3809360d8 · outbound

This paper cites an unresolved cited work.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:37:43.775138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ec718fdc-c8aa-40c8-8729-f3204a5b8bd1 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Representation Engineering: A Top-Down Approach to AI Transparency

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.544334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 423a92bd-d634-42bf-90cf-85d65baeb9ed · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.548098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.