Pith. sign in

Paper Citation Record · LEDGER

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)

As of 7 August 2026, this Paper Citation Record lists 97 of 97 outbound references and 1 inbound Pith citation observation for arXiv:2506.17846.

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

pith.paper-citation-record.v1
2506.17846 v1

Coverage vector

measured 97 of 97 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:26:57.754155Z

measured 98 of 98 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:27:34.770229Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T19:27:35.026558Z

Reference resolution

97 of 97 outbound references displayed

  • verified exact1
  • verified fuzzy47
  • unresolved45
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ab12fc43-486f-4daa-bac5-8049aee7dcf1 · outbound

This paper cites AI Control: Improving Safety Despite Intentional Subversion.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) AI Control: Improving Safety Despite Intentional Subversion

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.283865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.283865Z digest=sha256:e6523dd0659a7f2d467b3cdf2e1e4d8045e8af4963c943207c78ffae9aed417c

Observation 0075e0b6-928c-4ab7-81c9-2173cc5bde02 · outbound

This paper cites A sketch of an AI control safety case.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) A sketch of an AI control safety case

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.289552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.289552Z digest=sha256:a11c99f8ad3f53c1a3a72ab92da427c7f7b43ec4e0d54db011844d45b21728cf

Observation 3fdd020e-e755-40fa-90bc-d03e4a508367 · outbound

This paper cites Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.294628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.294628Z digest=sha256:375281a09f83c6a3d62309c590c704c9c8c5d08fa1266525065ce29b9edaa387

Observation 7c3799c3-51b8-44de-a3a1-0bf9ccc84549 · outbound

This paper cites Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.299859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.299859Z digest=sha256:65cc008d503bb034d9b70bd8770fd1024415a59901893aef24c654ef1f7e8bee

Observation 6bdb94a0-4680-491c-9e79-36571991cb74 · outbound

This paper cites Hidden in plain text: Emergence & mitigation of steganographic collusion in LLMs.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Hidden in plain text: Emergence & mitigation of steganographic collusion in LLMs

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.305751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.305751Z digest=sha256:d1d1f79bc9d0f467737ab60bf4b3a06960dd98bffedc3903a0974a4f90ae471b

Observation 09f8f5fc-d200-4615-8aee-44edd28c4f68 · outbound

This paper cites Mechanistic anomaly detection and elk.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Mechanistic anomaly detection and elk

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.310460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.310460Z digest=sha256:47428a1184fac6edfa9ba800e404103aa768b7aa732696a6192e0cdd20c5b5a0

Observation 7a0f4489-f5b4-470c-9219-226c2b6fdc6f · outbound

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

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Representation Engineering: A Top-Down Approach to AI Transparency

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.315490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.315490Z digest=sha256:18116ee00265781de726223e0d5f0a1c8c2f27a71dfd5017f498c99b411a30fd

Observation 40e474c2-869f-4a60-8bac-dba478f0581b · outbound

This paper cites Open Problems in Mechanistic Interpretability.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Open Problems in Mechanistic Interpretability

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.320407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.320407Z digest=sha256:a2e2c1afed67815a5448dfbc91e6bb83ec3acbed65470fa19c366e0f838d2fbe

Observation 20397426-c115-47a5-a529-d2f1b29d540d · outbound

This paper cites Berkovitz and Negash G.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Berkovitz and Negash G

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.326661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.326661Z digest=sha256:d61331c39cf349843286d6174b5712b922dd1ed5d57a0be20537732e4ddf1fbf

Observation 30a29f39-a2b9-47a2-864d-13cd9eca1f87 · outbound

This paper cites A Research Agenda: Dynamic Models to Defend Against Correlated Attacks.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) A Research Agenda: Dynamic Models to Defend Against Correlated Attacks

Reference 10

Resolution
verified exact
local_arxiv, observed 2026-08-06T23:26:58.243301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.330986Z digest=sha256:41d44921edd95bea970e70129004fa39dde6fe38ab2d146d65040d416d2f7aec

Observation 8f4e846f-ed77-416d-bbeb-9865ddf0fd5a · outbound

This paper cites Learning to summarize from human feedback.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Learning to summarize from human feedback

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.335594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.335594Z digest=sha256:39059a4808ced458f5c35708f37e8b4935cbf0adb74faca1b46c340df05585dc

Observation b24e0c39-92c9-420b-9a4a-bd334de653e3 · outbound

This paper cites Training language models to follow instructions with human feedback.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Training language models to follow instructions with human feedback

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.340226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.340226Z digest=sha256:99dfe9e24900e01821509d1527d67805ff824c96f9569cb2800633a929ecf512

Observation 9dc2a1c7-2f43-4554-b9dd-3faf7f7c8e44 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Fine-Tuning Language Models from Human Preferences

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.344640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.344640Z digest=sha256:28db40ff90671958ff48ddcb335ff044e0f5861ef30ed73ad1ce916240bd70f0

Observation 28b69cd8-196e-450e-a172-3ea8edad8196 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) A General Language Assistant as a Laboratory for Alignment

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.349277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.349277Z digest=sha256:bbb17630c4cd66f56a6d6d894a92138b454eca8533c1ede1298c433c3802eee3

Observation 6e751683-b89e-488a-80fe-3877b08c11a4 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Constitutional AI: Harmlessness from AI Feedback

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.353876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.353876Z digest=sha256:4c923caf7d3846c53a86226be7483a1b37670fc771147a70e73f3f660cb2b955

Observation 5e7e2798-2cdb-42ae-a2e2-748c3cded518 · outbound

This paper cites Cooperative inverse reinforcement learning.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Cooperative inverse reinforcement learning

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.358600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.358600Z digest=sha256:639dc15ca59eb8f52977af40de3e797788b018d6e0e8f4db30c1250615f2f588

Observation a75905cd-e4ab-40db-969b-80a1713f02c9 · outbound

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

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Scalable agent alignment via reward modeling: a research direction

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.362934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.362934Z digest=sha256:35c71e8b669f03a41be88ade33f209b61d27f6b4c0aedc37000c4bb7be0d4a65

Observation 10908b4d-a984-4b7c-980f-9e872c76bd49 · outbound

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

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.367629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.367629Z digest=sha256:dda458dbaa8695cf7b56b595a9a81cd709cc9c8c5495186fce203768bb061e27

Observation c5dfe7dc-112a-468e-9f77-317055abfb9a · outbound

This paper cites The Pristine survey -- XXII. A serendipitous discovery of an extremely Li-rich very metal-poor giant and a new method of $^6$Li/$^7$Li isotope measurement.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) The Pristine survey -- XXII. A serendipitous discovery of an extremely Li-rich very metal-poor giant and a new method of $^6$Li/$^7$Li isotope measurement

Reference 19

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T23:26:58.146256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.372263Z digest=sha256:1b8b279bc6242be8a06308acc4dc4c4dc24e520bc022dac09527115fd6ef0b28

Observation 6ec8cef2-c81f-4cae-87c5-0b2407571081 · outbound

This paper cites Consequences of misaligned AI.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Consequences of misaligned AI

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.378196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.378196Z digest=sha256:0d03a1ec792fe9aad90cd415249df7370f79f156e5d18b8a7525b62ecdedd6ff

Observation 5775113a-50f0-4329-8b43-f4bba1509c50 · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.382401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.382401Z digest=sha256:e358f554f2055825802336c2664fc43350e14db490639b7216f00abc2a0eca5d

Observation b7279a7c-6550-4fcf-8609-dc0f7a0a6616 · outbound

This paper cites On the relevance of the Godot Engine in the indie game development industry.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) On the relevance of the Godot Engine in the indie game development industry

Reference 22

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T23:26:58.107965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.387612Z digest=sha256:5424d9d3209acbc623a37c2ef5feda24d0b8579f9fa8a511aeee8c6b8211e986

Observation 523ab9c4-8d1d-4b4b-b703-f3731febc4bf · outbound

This paper cites Steganography in chain of thought reasoning.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Steganography in chain of thought reasoning

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.392376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.392376Z digest=sha256:953d847ae883e6a79bba72bb9a3e1696b55830cf526b7f96a063726055299195

Observation ec1ebec8-65a9-4a13-bcb2-5a02e34890b0 · outbound

This paper cites Neural linguistic steganography.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Neural linguistic steganography

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.397660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.397660Z digest=sha256:ebb9699a8249807c3bb42edf4de41f93dcef9bb457c1c6be263a6280c1b95e9f

Observation f152e7d6-8fe4-401f-afad-b3018f80b3bb · outbound

This paper cites Information hiding-a survey.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Information hiding-a survey

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.402416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.402416Z digest=sha256:f7a9323d1fac3e6a50eec9d9e79f4a618cd2c8804f8511158e57c612223b9df2

Observation 1afc3dff-0957-4efc-945d-c63465a950a6 · outbound

This paper cites CycleGAN, a Master of Steganography.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) CycleGAN, a Master of Steganography

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.407246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.407246Z digest=sha256:83a80a6513b09978a370dc417178812be30bd916f98ba060d70a9e245202e99d

Observation 6937da5d-d4df-4bee-bbda-49f5a95c1e45 · outbound

This paper cites A review on text steganography techniques.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) A review on text steganography techniques

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.412853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.412853Z digest=sha256:e47f512513d805fd822f8aa618a2121e430bb6c011725d6b32f4204d8546a242

Observation d1391414-55f8-42d2-89f3-84236a15ee36 · outbound

This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned llms.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Emergent misalignment: Narrow finetuning can produce broadly misaligned llms

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.417899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.417899Z digest=sha256:b23267a59a9ffbde07aed2d6e39bafb947686a6b26ba6f165fcbccd4c9073240

Observation be5e32ca-d5bb-40de-99c1-b3047f8595bc · outbound

This paper cites Discovering latent knowledge in language models without supervision.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Discovering latent knowledge in language models without supervision

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.422285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.422285Z digest=sha256:a19cbd33cf99774158266d0194ccf997b2706d9ab70dca432b20803a5bba2ad2

Observation 339b3efe-c9c7-4a3c-9997-1077bf4cd380 · outbound

This paper cites Arc’s first technical report: Eliciting latent knowledge.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Arc’s first technical report: Eliciting latent knowledge

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.427086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.427086Z digest=sha256:01489f44934b5d7e15c3a89e32f6fd50bd7d87bd271128c964b50d592d94c632

Observation fe61fc05-1d5e-429f-bd1e-50696299657a · outbound

This paper cites Is Power-Seeking AI an Existential Risk?.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Is Power-Seeking AI an Existential Risk?

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.431297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.431297Z digest=sha256:29efce6cbc6cdbbfd221301b79ef3cf88a5a5049dbe4b5f8c984ed34cd1b3e0d

Observation 0c43d34d-c830-4c9c-95f8-cd70bdf42d44 · outbound

This paper cites Optimal policies tend to seek power.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Optimal policies tend to seek power

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.435862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.435862Z digest=sha256:accc3605e054bcd33b695fe764fb2b5b15fa7ee55566dc3965c42c19442cd9b9

Observation 91d1d0cd-e82a-455e-9c32-91d9b55043f2 · outbound

This paper cites Corrigibility.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Corrigibility

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.441272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.441272Z digest=sha256:0c4fca1a29e8e387de32a17914cf50a44989d00b3fbbaba36d1ec00b495b090b

Observation c4d5ef54-f1ca-4500-93fa-7c05a3fce28c · outbound

This paper cites AI safety via debate.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) AI safety via debate

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.451135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.451135Z digest=sha256:f04efd67cedd286f038c690ebd7791f8580749c6824a6a1c1bcb991023395d70

Observation 0e8cf767-1101-4c6e-92c4-bc2ccc28eeaf · outbound

This paper cites Debate Helps Supervise Unreliable Experts.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Debate Helps Supervise Unreliable Experts

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.455690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.455690Z digest=sha256:c306754a0be3802ea867d3debdb9fb68d6e6436c12eec9829515b8574915f2f6

Observation 4cb71390-ee26-42d7-b8bd-9ba263b7c9da · outbound

This paper cites Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.460137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.460137Z digest=sha256:0c4b10cfa0a713c68e12659cdd0161a87177cc6782daa126fc1704baee356324

Observation 6484fdc9-805a-4106-bfc3-6eced7d4b468 · outbound

This paper cites A new robust approach for the polytomous logistic regression model based on R\'enyi's pseudodistances.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) A new robust approach for the polytomous logistic regression model based on R\'enyi's pseudodistances

Reference 38

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T23:26:57.913086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.465214Z digest=sha256:7b679cb38f1bac68d4a3aaf9039eca69f20be4fd883ee4347c56a5082f9b049d

Observation 1de1f1e8-f83b-48e8-b322-b84b1cdf1473 · outbound

This paper cites The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.469751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.469751Z digest=sha256:044262dd836e99a516d5582c8feb61d6fbac8992d93606f79e196b66bd62bb99

Observation 972a95bd-1328-4030-a171-307a97df5f0c · outbound

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

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) The Alignment Problem from a Deep Learning Perspective

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.474356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.474356Z digest=sha256:2e3c75cbe08707d30ff1fc7c03686e847fa22ad3a712ea6a71d695f1fbe3d608

Observation 59348b0c-9cde-4e9e-9ea7-da61df4f85c2 · outbound

This paper cites Deep reinforcement learning from human preferences.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Deep reinforcement learning from human preferences

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.479472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.479472Z digest=sha256:b9cb2ed04fab3fb0d12c8bfc90f46735247723c3dc6056fa42049d9b9e3a303c

Observation 89095439-ec12-4800-a7a6-dca73a60ef5d · outbound

This paper cites One-Year In: COVID-19 Research at the International Level in CORD-19 Data.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) One-Year In: COVID-19 Research at the International Level in CORD-19 Data

Reference 42

Resolution
metadata mismatch
local_arxiv, observed 2026-08-06T23:26:57.861338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.487947Z digest=sha256:1316952f1c4c96ef5a996f5f45cc6e487cc96792a6892bb778375278c65696dc

Observation 329a6965-01d5-4c3c-85e1-d48057160d83 · outbound

This paper cites Measuring Progress on Scalable Oversight for Large Language Models.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Measuring Progress on Scalable Oversight for Large Language Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.492998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.492998Z digest=sha256:3b9e088f4f4625c15f9051d5a9ba5195be1805ab307f2db3db3d755a5e758b9b

Observation 07886c10-0fc8-4fbb-a355-0f241ea5eda3 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Discovering Language Model Behaviors with Model-Written Evaluations

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.497730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.497730Z digest=sha256:392f112f953e0dfb96387535b1298c90422247db7fee1f54cefff8bf843401ce

Observation b4d26c89-ef97-4f54-a784-e949f76de09d · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Steering Llama 2 via Contrastive Activation Addition

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.502600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.502600Z digest=sha256:ce0cede96f7c200491d1ae7b2554d0eb6a8fc724add909043ddbfb35872b378c

Observation e963b313-e3ce-4a8f-a981-2ad6bf27bafc · outbound

This paper cites Truthful AI: Developing and governing AI that does not lie.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Truthful AI: Developing and governing AI that does not lie

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.507257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.507257Z digest=sha256:3c983e3f43d1d91b85d5cc743d6b6784c30567372c8ec4d5830128fdaf8ab9f9

Observation 75d5ecf9-2be6-49fc-90d7-fe55ee7d10b2 · outbound

This paper cites Safe reinforcement learning via shielding.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Safe reinforcement learning via shielding

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.511663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.511663Z digest=sha256:bd29eb58fd0ab6f91ba34b7d5defc80d139f616c0ff9d064a64da019661b7951

Observation 118426b5-8c24-4398-b2a4-93a8eb3412ae · outbound

This paper cites Robust adversarial reinforcement learning.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Robust adversarial reinforcement learning

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-06T23:26:57.516626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:26:57.516626Z digest=sha256:9ec6e50ba1bb511888ac02be2418fee0cf4733084c3b6c21d2b97d1e681862b4

Observation 4f938f2e-83ea-4ff4-837f-3ea38260fa2d · outbound

This paper cites Dynamic programming and optimal control, volume 1.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Dynamic programming and optimal control, volume 1

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.267980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.520713Z digest=sha256:f66107fec28a7c9e88ed2107d1f45d32d170e302b34b16db769bfebec5763731

Observation 0a2f84d3-4ddc-4f66-81e1-a5834221f5dd · outbound

This paper cites Robust and optimal control.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Robust and optimal control

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.253765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.525183Z digest=sha256:814e24064acebc9f94984d64e7b262e8381f70eedb8c792f82e529f6dd80c7fc

Observation ede4711e-9d33-4c3e-bdd8-d0690d0accaf · outbound

This paper cites Optimal control theory: an introduction.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Optimal control theory: an introduction

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.239370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.530225Z digest=sha256:f172dc44bab84b4144f541c1f9adc6673e46eca82f4b0931a36e8350677aaef1

Observation 137e513d-2f59-42df-8ad6-7f2ee19dddd1 · outbound

This paper cites Optimal control.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Optimal control

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.225474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.535511Z digest=sha256:1425881529c67d74835b50d3ab0d7743c70d9d5d234ec8af48845be782cefe71

Observation b543f7f1-88cf-4637-9fff-b266e9ee4bdf · outbound

This paper cites Adaptive control.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Adaptive control

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.210857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.539962Z digest=sha256:7efbf7beade80cbcaca513da059c3b10c7b64bd49e16394adf5db7a240541ca6

Observation 0c6359aa-fbd5-4a43-b3ae-6268e04a0564 · outbound

This paper cites Model predictive control.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Model predictive control

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.196061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.545410Z digest=sha256:4ca34e42643a6645d772ce3d07f60cd9bb8671bc15b4b932a78f796c80052102

Observation 48cd507c-b336-4db8-be0b-8ff796034a38 · outbound

This paper cites Stochastic optimal control: the discrete-time case , volume 5.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Stochastic optimal control: the discrete-time case , volume 5

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.179346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.549740Z digest=sha256:076c313466a523fdd6a56de26a1b063c5cf7516b1e4dc2168f7a4384469183cf

Observation d6702858-719b-42ad-8e71-e6cbd3901a41 · outbound

This paper cites Nonlinear control systems.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Nonlinear control systems

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.164569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.554104Z digest=sha256:68b82ff3a7f9d16731ede4a5ea376ecafb4fd43b4398b6f0a53fee4e6d0f4f17

Observation d0662494-ffad-4fc4-824f-a158065e2adb · outbound

This paper cites Geometric control of mechanical systems: modeling, analysis, and design for simple mechanical control systems.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Geometric control of mechanical systems: modeling, analysis, and design for simple mechanical control systems

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.150038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.558392Z digest=sha256:fb60d15aeaa640eb392fe042194d02a667f77cf512e680fb003b8d1f8ae5e5fd

Observation eb062195-036f-4e8d-9510-bd13859555ac · outbound

This paper cites Hybrid dynamical systems: modeling, stability, and robustness.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Hybrid dynamical systems: modeling, stability, and robustness

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.135036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.562822Z digest=sha256:a26878977248a31550bd102b7e33c3dfa101134b63c3e143db99118522e2abf3

Observation 1afd2908-f842-4578-8f7d-eae8cea6b095 · outbound

This paper cites Reinforcement learning: An introduction.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Reinforcement learning: An introduction

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.120979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.567484Z digest=sha256:5b7e4ccf5fb045b91d9dcd606f536a8aae93e4977f66e3e2d85805be9b0bf076

Observation 85910cfd-120d-43a4-bf1c-259ce9df6602 · outbound

This paper cites ˙x∗(t) = ∂H ∂λ (t, x∗(t), u∗(t), λ(t)) (12) ˙λ(t) = − ∂H ∂x (t, x∗(t), u∗(t), λ(t)) (13) where the Hamiltonian H(t, x, u, λ) = λ0f 0(t, x, u) + Pn i=1 λi(t)f i(t, x, u).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) ˙x∗(t) = ∂H ∂λ (t, x∗(t), u∗(t), λ(t)) (12) ˙λ(t) = − ∂H ∂x (t, x∗(t), u∗(t), λ(t)) (13) where the Hamiltonian H(t, x, u, λ) = λ0f 0(t, x, u) + Pn i=1 λi(t)f i(t, x, u)

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.107291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.571978Z digest=sha256:fad5b3458ce2e96f3cbb568e5cfc12a6321ae6921bd5486099b339ec528baf43

Observation 6aec0a9b-d173-4222-8f53-86f322499486 · outbound

This paper cites For almost all t ∈ [t0, t1], H(t, x∗(t), u∗(t), λ(t)) = sup z∈Ω(t,x∗(t)) H(t, x∗(t), z, λ(t)) (14).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) For almost all t ∈ [t0, t1], H(t, x∗(t), u∗(t), λ(t)) = sup z∈Ω(t,x∗(t)) H(t, x∗(t), z, λ(t)) (14)

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.093151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.577039Z digest=sha256:95498100978311bcbdb9ee9ebf2c3a3d882e7e886efdf1aa2d5b5b3799940271

Observation 21d58aa7-2b20-42cd-9efd-47d8fd24fa3f · outbound

This paper cites At the endpoints (t0, x∗(t0)) and (t1, x∗(t1)), the vector (−H(t0), λ(t0), H(t1), −λ(t1)) (where H(t) is H evaluated along the extremal) is orthog- onal to the end-manifold B.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) At the endpoints (t0, x∗(t0)) and (t1, x∗(t1)), the vector (−H(t0), λ(t0), H(t1), −λ(t1)) (where H(t) is H evaluated along the extremal) is orthog- onal to the end-manifold B

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.079099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.581799Z digest=sha256:366af261b0b10554fdc9480cf1f6c59a9dedb9f17a6fde61fdc1bda33bd4c7ee

Observation 81438081-e24b-4463-9059-09359952aa4f · outbound

This paper cites an unresolved cited work.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Unresolved cited work

Reference 63

Resolution
unresolved
raw_fallback, observed 2026-08-06T23:26:59.064181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.586823Z digest=sha256:6b5d4d6be593d2e26df63c02a51e99f65e51cfdcc405bf192ef59564359d1bef

Observation 795b0bda-e112-476c-bc4c-209e73382294 · outbound

This paper cites an unresolved cited work.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Unresolved cited work

Reference 64

Resolution
unresolved
raw_fallback, observed 2026-08-06T23:26:59.049526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.591884Z digest=sha256:b88adf3da762e8152ad2786b660dd94672759545d4a8ca6ee78ca3a9988d01e6

Observation 01562de8-af0b-45bc-82d5-17daae9e2a60 · outbound

This paper cites This involves adjusting operational parameters of physical components.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) This involves adjusting operational parameters of physical components

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.034924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.597023Z digest=sha256:afdaaa2b3c20489e68f148fe070933518d529631d71e6fad798211fdc63f47fa

Observation b39cf135-32c6-441b-ab87-3afd32da7477 · outbound

This paper cites This concerns distributing computational tasks across available processing units (e.g., GPU kernels).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) This concerns distributing computational tasks across available processing units (e.g., GPU kernels)

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.020066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.602475Z digest=sha256:75d9014decc60991b5d0bf2c0069a6777d51618aeb12be0a674df31939694561

Observation b5ca32a1-ea19-4f32-99f2-8ff8c5a68446 · outbound

This paper cites This includes mechanisms like Error Correction Codes (ECC) in memory or redundant array of inexpensive disks (RAID) for storage.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) This includes mechanisms like Error Correction Codes (ECC) in memory or redundant array of inexpensive disks (RAID) for storage

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:59.004976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.607598Z digest=sha256:cd7b96784743006704cbbcfe1f0769ad6383cef1d9b67d238d9172d41c2d6bb4

Observation 5260a0b9-0003-4c11-8515-beabdeac6f29 · outbound

This paper cites OS and containerization tools allow setting limits on resource consumption per process or container (e.g., Linux cgroups).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) OS and containerization tools allow setting limits on resource consumption per process or container (e.g., Linux cgroups)

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.988645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.612961Z digest=sha256:59f74efb49424ba20e6de1b2e47366d49e245820a69819ffcbca6302617ff21d

Observation 25bcc983-12b4-44ec-bbe9-e627e225b119 · outbound

This paper cites The OS scheduler manages the execution order of processes and threads.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) The OS scheduler manages the execution order of processes and threads

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.973984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.618080Z digest=sha256:dafae32937b0553b24d0a90eb36705a0c5a81872c8b63e04ea999eb636e723d1

Observation 568f8085-15ae-4e6b-bd49-e1d2c977be39 · outbound

This paper cites Using containers, virtual machines, or specific OS mechanisms (e.g., seccomp, AppArmor) to restrict the privileges and visibility of AI processes.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Using containers, virtual machines, or specific OS mechanisms (e.g., seccomp, AppArmor) to restrict the privileges and visibility of AI processes

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.959287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.622787Z digest=sha256:e95688ad75a2d5b12d6631ef8edabbba873e5127b6a21eaeda717657702fede0

Observation c41fae4d-9ee8-4b4c-8e89-5958c1c27db3 · outbound

This paper cites Frameworks often perform optimisations like op- erator fusion, constant folding, and memory planning on the AI model’s computational graph.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Frameworks often perform optimisations like op- erator fusion, constant folding, and memory planning on the AI model’s computational graph

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.944616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.627271Z digest=sha256:aae79a0acc6f6295afd19b102a59dccc977117edeaa25aac70c0c1afa5958d35

Observation 79952eb8-3a97-4d05-8ba2-aed4f906db05 · outbound

This paper cites Techniques applied during computation to maintain numeri- cal precision and prevent issues like vanishing/exploding gradients.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Techniques applied during computation to maintain numeri- cal precision and prevent issues like vanishing/exploding gradients

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.930479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.632324Z digest=sha256:d4efaaf46671e3e39e92d1b821526483a56044aff2b6a95b19e3d010198ea3bc

Observation 03a971ba-78f7-47db-8445-760c7c2d4015 · outbound

This paper cites Mechanisms for managing data and model parallelism, synchronizing gradients, and handling parameter updates across multiple devices or nodes.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Mechanisms for managing data and model parallelism, synchronizing gradients, and handling parameter updates across multiple devices or nodes

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.915881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.637503Z digest=sha256:d7f09bc97d0a9b8b09d70549bda5a38b8a7ec110061966b3362aaac5192f08d8

Observation 2a14673b-1ee7-446f-87da-5b782d41d6b8 · outbound

This paper cites Its efficiency and correctness are crucial for successful model development.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Its efficiency and correctness are crucial for successful model development

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.901153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.641868Z digest=sha256:1102b2461cc70a8e467e3e88a873c431248c5001a5cb93ec6a28dfc33a348bc7

Observation 0207fbd2-b062-4de4-a1d9-ddc2c9a2b47f · outbound

This paper cites The deliberate selection of network structures, layer types, and connectivity.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) The deliberate selection of network structures, layer types, and connectivity

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.886207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.646312Z digest=sha256:dd8220090b5cfd89388c4f5f0739ac9968784f477018ab1a877d15b4f18ba41a

Observation 6f494e16-29ea-4065-a968-b5280365186d · outbound

This paper cites Incorporating architectural elements that intrinsi- cally promote better generalisation or robustness, such as dropout layers or batch normalisa- tion.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Incorporating architectural elements that intrinsi- cally promote better generalisation or robustness, such as dropout layers or batch normalisa- tion

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.871166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.651553Z digest=sha256:93fe3a9af0f5cf2f66a2efd5f963d94b168a4d9bcad472e5c5cd1fabf1507c5e

Observation bd8be8eb-0581-47a3-83f5-d6710a09d4d5 · outbound

This paper cites Methods like pruning (removing less important weights/neurons) and quantization (reducing the precision of weights and activations).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Methods like pruning (removing less important weights/neurons) and quantization (reducing the precision of weights and activations)

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.855157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.655987Z digest=sha256:647b66c3d72de84f9ea01f6e08dc144bede9c910844b6edbd010064755c16114

Observation 71f2ee9b-fd11-49bb-a2c3-054be200ae91 · outbound

This paper cites Selecting, cleaning, and transforming the training data.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Selecting, cleaning, and transforming the training data

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.840902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.660467Z digest=sha256:de5dd0ac1d1775e011495c862e023343fe19356c86d8c5b35f6d3ddf7879eb2e

Observation 24b7d4b6-37a5-481b-822e-533363ff6250 · outbound

This paper cites Defining the loss function Ltask that the model aims to minimise, and potentially adding regularization terms Lregi or constraints.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Defining the loss function Ltask that the model aims to minimise, and potentially adding regularization terms Lregi or constraints

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.826148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.664742Z digest=sha256:b596fe1b8cd7cd0bd2bb12b84450f91403dd0301c784d8bdd980299753ac9847

Observation 51470257-ea07-4e3a-9e00-eee556489701 · outbound

This paper cites Choosing the optimizer (e.g., SGD, Adam) and its parameters (e.g., learning rate ηt, batch size Bt, momentum βt).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Choosing the optimizer (e.g., SGD, Adam) and its parameters (e.g., learning rate ηt, batch size Bt, momentum βt)

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.811945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.669102Z digest=sha256:04a17947939a09307c8729133479b6cc392f9dce775acd6885142d424cd70b85

Observation 683017bc-a545-444d-9d06-72ce2f30305e · outbound

This paper cites Monitoring performance on a validation set and stop- ping training when performance no longer improves, saving model checkpoints periodically.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Monitoring performance on a validation set and stop- ping training when performance no longer improves, saving model checkpoints periodically

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.797732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.673973Z digest=sha256:5619edc4c8c6c1b18b91c8dc2959704ca9a157d530a8c62d091682f16ea90ff9

Observation de7b95c0-a8b2-4dd9-9fe6-a012e10dd32d · outbound

This paper cites Post-processing model outputs to detect and remove or modify undesirable content (e.g., harmful language, private information).

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Post-processing model outputs to detect and remove or modify undesirable content (e.g., harmful language, private information)

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.782975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.678601Z digest=sha256:61a274f80ad40ccc5bd54b176f8b7f3f7e64b6745e77ee258ed66def6731acd7

Observation 61463965-6dd4-4ebf-a701-7cd32e43c7db · outbound

This paper cites Abstaining from providing an output or escalating to a human supervisor if the model’s confidence in its output is below a certain threshold.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Abstaining from providing an output or escalating to a human supervisor if the model’s confidence in its output is below a certain threshold

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.769030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.682862Z digest=sha256:203506292bb60fd81da8b6b8126be5080be911bc768d505545b85eb8218414fe

Observation d636dba1-dc82-4894-b1d9-e124cb2b2de6 · outbound

This paper cites an unresolved cited work.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Unresolved cited work

Reference 84

Resolution
unresolved
raw_fallback, observed 2026-08-06T23:26:58.754604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.688090Z digest=sha256:00247356a59795a4f5f29e1b8def01c5e93e9134d4feca0dc363324ef2321bd9

Observation e9b295af-af6a-4be9-9f08-84368c33ec4c · outbound

This paper cites Altering or ablating spe- cific internal parts of a model (e.g., neurons, attention heads, identified circuits) that are understood to contribute to certain behaviours.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Altering or ablating spe- cific internal parts of a model (e.g., neurons, attention heads, identified circuits) that are understood to contribute to certain behaviours

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.740118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.692639Z digest=sha256:c4beefde946c0a8506f5fe96885fd01563a11e5ab1a039f139c5df0b60982fdc

Observation 33e4d8b3-b717-4388-a6c0-b7e52fd0e5d1 · outbound

This paper cites Using explanations of model behaviour (e.g., why a particular output was generated) to identify and diagnose issues.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Using explanations of model behaviour (e.g., why a particular output was generated) to identify and diagnose issues

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.725762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.697467Z digest=sha256:e4c0aef8fd47d4144429014bc3df6942d636d8b576db13e157e536967dc10e7a

Observation be31639d-5d89-4ecb-abee-769f7f19d1b0 · outbound

This paper cites Directly modifying model weights or structure based on interpretability insights to correct specific knowledge or behaviours without full retraining.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Directly modifying model weights or structure based on interpretability insights to correct specific knowledge or behaviours without full retraining

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.711078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.702606Z digest=sha256:d604573f15e3736508e8159ba4422b06a92c77213312478c1a6fb4b2630c0121

Observation 3771ab7b-4652-4736-85e8-0a32f8be8af0 · outbound

This paper cites Techniques for capturing human preferences and values to guide AI behaviour, often by training a reward model RM (y) based on human feedback.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Techniques for capturing human preferences and values to guide AI behaviour, often by training a reward model RM (y) based on human feedback

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.695414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.706937Z digest=sha256:075794e13058bb6f48f795b29facab2ef8f38a8c5c04a9ee133abcc454be2822

Observation 5f6db323-c4bd-4170-bb47-0db365045fbd · outbound

This paper cites Using a learned reward model or direct human feedback to fine-tune a base AI model towards desired behaviours.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Using a learned reward model or direct human feedback to fine-tune a base AI model towards desired behaviours

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.681521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.711319Z digest=sha256:e7d40a770a8ac33663db950de6aa5c64e30a419752aa05cdf3d55c4b5ce06796

Observation 0528181c-23ff-4844-8914-5c5de2637eb5 · outbound

This paper cites Systematically probing AI systems to discover vulnerabilities, failure modes, and misalignments before deployment.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Systematically probing AI systems to discover vulnerabilities, failure modes, and misalignments before deployment

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.667564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.715979Z digest=sha256:bfc5b719814114ce3bd10bf3003a32c846758cd44d12e173c524077cf78daa94

Observation be72f600-06fa-4be9-a576-4eee69244c81 · outbound

This paper cites Defining explicit principles, rules, or constitutions that the AI must adhere to, and using AI itself to critique and revise its outputs to comply with these rules.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Defining explicit principles, rules, or constitutions that the AI must adhere to, and using AI itself to critique and revise its outputs to comply with these rules

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.652156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.721090Z digest=sha256:d767ed3cb7d5cacb36016cf7480a9bc3ad55d0cbaaf3a61df3f98922ff4a9efd

Observation f6f45057-65f6-4903-86da-4d7e61b71c53 · outbound

This paper cites Designing the rules of interaction, com- munication protocols, and reward/utility functions for individual agents within a multi-agent system.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Designing the rules of interaction, com- munication protocols, and reward/utility functions for individual agents within a multi-agent system

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.637303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.726466Z digest=sha256:291b8103340a9295fd572332ad915e88e37dcdd4296f7c4c1df6609383d409fe

Observation a21a1b03-6151-4c23-8997-e89952978811 · outbound

This paper cites Implementing systems for establish- ing, communicating, monitoring, and enforcing social norms or rules within an AI agent population.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Implementing systems for establish- ing, communicating, monitoring, and enforcing social norms or rules within an AI agent population

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.622214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.730928Z digest=sha256:f86d025527a5a899bad28ef816dc847c2ebcded72a78af4671c102239d78badc

Observation c8a6f8aa-4642-4ae1-b1a5-83fbe2dacebf · outbound

This paper cites Establishing standardized ways for agents to exchange information, signal intent, and coordinate actions.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Establishing standardized ways for agents to exchange information, signal intent, and coordinate actions

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.604718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.735359Z digest=sha256:c84316e451fd6a9f62c682a720079955ff23adb53b58720dba1bc91b6e546de7

Observation 0f60556e-98cf-449a-ad22-b3078b03615a · outbound

This paper cites Governments and international bodies establishing laws, standards, and policies governing the development, deployment, and use of AI.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Governments and international bodies establishing laws, standards, and policies governing the development, deployment, and use of AI

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.589930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.740359Z digest=sha256:dd869e5876f7165a281a2ff9f227c12427e24597bb170765055f287d4ad0a923

Observation c3ed02ca-6c23-420c-ab9c-fb9993b972d3 · outbound

This paper cites Professional organiza- tions, research institutions, and industry consortia developing and promoting principles for responsible AI.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Professional organiza- tions, research institutions, and industry consortia developing and promoting principles for responsible AI

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.575331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.744788Z digest=sha256:e315cb58d343ff35ed9a9acaaafdfed0f29825e9c223def8c9ad35659fd934e0

Observation 1f3a2255-c9e2-4c71-af75-151daf40becd · outbound

This paper cites Efforts to inform the public about AI, foster critical discussion, and involve diverse stakeholders in shaping AI’s future.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Efforts to inform the public about AI, foster critical discussion, and involve diverse stakeholders in shaping AI’s future

Reference 97

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.560878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.749304Z digest=sha256:123ae6da5971ccb8df60492e0c60b349642bb0a2792aa07f71540961e46418c0

Observation 6e1b6198-ad87-4f12-860d-c8be1e6c09ab · outbound

This paper cites Formal processes for evaluating the potential societal impacts of AI systems before and during deployment, and for independently verifying claims about their safety or fairness.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Formal processes for evaluating the potential societal impacts of AI systems before and during deployment, and for independently verifying claims about their safety or fairness

Reference 98

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T23:26:58.544836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T23:26:57.754155Z digest=sha256:6525cd4329c57f59f43e33576a795cf016a0f2d1bd5fe6d07e4c8f86858a330a

Pith citing papers

Observation ae3eb31d-6151-4fda-9b35-fb702528aa8a · inbound

Towards Measurement Theory for Artificial Intelligence cites this paper.

Towards Measurement Theory for Artificial Intelligence Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)

Reference 33

Resolution
verified exact
local_arxiv, observed 2026-08-06T19:27:35.061123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=pdf_text observed=2026-08-06T19:27:34.770229Z digest=sha256:63ac6142c096b7c0378ab4bdc94e61d5c525c022f55f4451eac64e7bda5d4e6c