Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T05:43:07.337382Z
Paper Citation Record · LEDGER
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values
As of 8 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 0 inbound Pith citation observations for arXiv:2506.13774.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
50 of 50 outbound references displayed
- verified exact2
- verified fuzzy27
- unresolved21
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 03ffc49a-1a7b-429c-8020-54a96502feb0 · outbound
This paper cites Artificial Intelligence, Values, and Alignment.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Artificial Intelligence, Values, and Alignment
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.261527Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 93026cbf-d874-413a-9bd0-b2651e5c8a3b · outbound
This paper cites Artificial Morality: Top -down, Bottom-up, and Hybrid Approaches.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Artificial Morality: Top -down, Bottom-up, and Hybrid Approaches
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.247705Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation e4ec19f7-68a5-4123-90ff-cb5f9267b597 · outbound
This paper cites Translating Principles into Practices of Digital Ethics: Five Risks of Being Unethical.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Translating Principles into Practices of Digital Ethics: Five Risks of Being Unethical
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.232427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation cab35d18-a447-4352-ac03-fd37e5153ac7 · outbound
This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.123823Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c5354f90-fad6-4bb2-96cf-a66ca53ebf2d · outbound
This paper cites Personalized Large Language Models.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Personalized Large Language Models
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.128902Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49e8007a-9ada-423f-8dbc-f1bc1335f848 · outbound
This paper cites Towards an End -to-End Personal Fine -Tuning Framework for AI Value Alignment.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Towards an End -to-End Personal Fine -Tuning Framework for AI Value Alignment
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.218849Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation a1f78d6b-2a43-4697-b583-f52683d34c35 · outbound
This paper cites Safer Agentic AI.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Safer Agentic AI
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.204958Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation ab4fc287-4bcb-4053-b2df-466b9746a33d · outbound
This paper cites Introducing the Model Context Protocol.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Introducing the Model Context Protocol
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.190940Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0b0b6157-c207-4c1b-b451-66d573f3884b · outbound
This paper cites Deep Reinforcement Learning from Human Preferences.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Deep Reinforcement Learning from Human Preferences
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.176703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c1a6a662-4abe-47f4-b593-49c0d6ede551 · outbound
This paper cites Confabulation: The Surprising Value of Large Language Model Hallucinations.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Confabulation: The Surprising Value of Large Language Model Hallucinations
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.152276Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75f881bc-d2a2-4cc7-a983-2f2387095612 · outbound
This paper cites Choice Vectors: Streamlining Personal AI Alignment Through Binary Selection.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Choice Vectors: Streamlining Personal AI Alignment Through Binary Selection
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.161821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f8843945-5b73-4fb6-8fdd-6eacf9e521a7 · outbound
This paper cites an unresolved cited work.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:43:08.147667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 232768fa-1ba1-48b4-b37f-24a77dad24c0 · outbound
This paper cites Universality of Representation in Biologic al and Artificial Neural Networks.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Universality of Representation in Biologic al and Artificial Neural Networks
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.165649Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b5015ad3-26fb-48f4-8a6f-ff1489e4c7a9 · outbound
This paper cites The neural bases of cognitive conflict and control in mo ral judgment.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values The neural bases of cognitive conflict and control in mo ral judgment
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.133544Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5f808b93-0ce8-402b-a21e-fc5f0480cb73 · outbound
This paper cites The neural basis of human social values: Evidence from functional MRI.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values The neural basis of human social values: Evidence from functional MRI
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.118460Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 2d831fb6-b9b9-40aa-af80-9648e02cea1c · outbound
This paper cites A Cognitive Theory of Consciousness: The Workspace of the Mind; Cambridge University Press: Cambridge, UK, 1988.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values A Cognitive Theory of Consciousness: The Workspace of the Mind; Cambridge University Press: Cambridge, UK, 1988
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.103481Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6886e3ee-5210-46b2-b28e-efef9e830027 · outbound
This paper cites Unified Theories of Cognition; Harvard University Press: Cambridge, MA, USA, 1990.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Unified Theories of Cognition; Harvard University Press: Cambridge, MA, USA, 1990
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.088209Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation bec20e91-f154-4787-a276-9d29e7bc19d6 · outbound
This paper cites Revealing economic facts: LLMs know more than they say.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Revealing economic facts: LLMs know more than they say
Reference 18
- Resolution
- verified exact
- raw_fallback, observed 2026-08-07T05:43:07.780589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 565c71ff-9edc-481f-a63f-4b03b833470d · outbound
This paper cites ShieldGemma 2: Robust and Tractable Image Content Moderation.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values ShieldGemma 2: Robust and Tractable Image Content Moderation
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.193249Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40c700b9-bd04-4265-a0d1-417a7d2802c3 · outbound
This paper cites Superego -Agent LGDemo (Branch: Fastapi_Mcp).
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Superego -Agent LGDemo (Branch: Fastapi_Mcp)
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.073012Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation c55222a1-896d-459a-9f3e-dfd48bfa9033 · outbound
This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.203855Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 218dadac-60a5-4f85-909e-cf5e6a25d19e · outbound
This paper cites AgentHarm: A benchmark for measuring harmfulness of LLM agents.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values AgentHarm: A benchmark for measuring harmfulness of LLM agents
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.058305Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 0d21dcae-dcab-4951-b7a8-6e0cf673c985 · outbound
This paper cites Do the rewards justify the means? Measuring trade -offs between rewards and ethical behavior in the Machiavelli benchmark.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Do the rewards justify the means? Measuring trade -offs between rewards and ethical behavior in the Machiavelli benchmark
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.043769Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 7d230248-3583-4771-9434-10d2f6bcc2e5 · outbound
This paper cites Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.218428Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9a1bd80-b170-4952-ac58-bb35175f738c · outbound
This paper cites Vijil Test Library: Evaluating LLM Trustworthiness Across Eight Dimensions.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Vijil Test Library: Evaluating LLM Trustworthiness Across Eight Dimensions
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.029110Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation dd65809f-b519-4dd9-aca7-bc452cb6adae · outbound
This paper cites INSPECT: An Extensible Toolkit for AI Behavior Evaluation.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values INSPECT: An Extensible Toolkit for AI Behavior Evaluation
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:08.013655Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5c5cdae8-08c2-4c38-a138-b11566074059 · outbound
This paper cites Governance in Agentic Workflows: Leveraging LLMs as Oversight Agents.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Governance in Agentic Workflows: Leveraging LLMs as Oversight Agents
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.999467Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation f34152c1-3bdc-4796-b437-1ecc6eaf0dc8 · outbound
This paper cites Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.235972Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c56c63fe-b2f0-40db-8b6f-319be09db8c4 · outbound
This paper cites Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.240615Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 01f226e5-346c-4313-bf58-63314a39d76c · outbound
This paper cites InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.245116Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f47fd653-d640-4acc-b755-e93a1f270232 · outbound
This paper cites On Almost Surely Safe Alignment of Large Language Models at Inference-Time.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values On Almost Surely Safe Alignment of Large Language Models at Inference-Time
Reference 31
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T05:43:07.630186Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 535df10b-43a8-4d3e-afd6-35257bf5828b · outbound
This paper cites Dynamic Search for Inference-Time Alignment in Diffusion Models.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Dynamic Search for Inference-Time Alignment in Diffusion Models
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.253673Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad083c49-e7a3-48d4-8c78-de4e9196656b · outbound
This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.258162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b7f7c262-ade5-4959-a0a1-84e014de2c97 · outbound
This paper cites Constitutional AI: Harmlessness from AI Feedback.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Constitutional AI: Harmlessness from AI Feedback
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.262772Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ae553b9-9542-4f09-986a-e2bb36766dc6 · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.267381Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0307194a-196c-4c9a-adca-c6c142cca4c6 · outbound
This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.984868Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 171bc1d9-efa4-4d45-85cc-b610962d7f10 · outbound
This paper cites AI Control: Improving Safety Despite Intentional Subversion.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values AI Control: Improving Safety Despite Intentional Subversion
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.278246Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f222863a-22fb-447c-badb-4127e9498e77 · outbound
This paper cites OpenAI x DFT: The First Moral Graph.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values OpenAI x DFT: The First Moral Graph
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.970374Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 8ff4d278-26db-4e2f-a2be-693040d26acf · outbound
This paper cites Model Integrity.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Model Integrity
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.956049Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 27bab82c-a0dc-4c0c-ad58-3d049b54f333 · outbound
This paper cites The Global Landscape of AI Ethics Guidelines.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values The Global Landscape of AI Ethics Guidelines
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.941746Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5d78eeaf-2263-4a86-9a54-c9b9b492120d · outbound
This paper cites WhatsApp MCP Exploited: Exfiltrating Your Message History via MCP.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values WhatsApp MCP Exploited: Exfiltrating Your Message History via MCP
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.926146Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 48e2fdca-9791-46d1-a005-6bdfaca00cf9 · outbound
This paper cites MCP Security Notification: Tool Poisoning Attacks.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values MCP Security Notification: Tool Poisoning Attacks
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.895246Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 20244967-148d-46a2-bb57-cdfbdc0be7ec · outbound
This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned LLMs.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Emergent misalignment: Narrow finetuning can produce broadly misaligned LLMs
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.311471Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31272682-141c-4702-a791-551e22302342 · outbound
This paper cites On Emergent Misalignment.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values On Emergent Misalignment
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.880226Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 5f40ad55-bb11-4b30-bc91-b86935cea64a · outbound
This paper cites Model Plurality.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Model Plurality
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.864809Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 37621a40-2612-4ca3-812b-e77b1cdf5562 · outbound
This paper cites Model Plurality: A Taxonomy for Pluralistic AI.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Model Plurality: A Taxonomy for Pluralistic AI
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T05:43:07.849749Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6f6e36b4-7098-4f6c-9730-c2637ec23bd0 · outbound
This paper cites Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.328340Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dc7ee6ef-2dca-4126-922c-1c188a5c2c2e · outbound
This paper cites OASIS: Open Agent Social Interaction Simulations with One Million Agents.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values OASIS: Open Agent Social Interaction Simulations with One Million Agents
Reference 48
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.332394Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b915a17-c0ea-45d4-93aa-e2fcfdfb4806 · outbound
This paper cites Project Sid: Many-agent simulations toward AI civilization.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Project Sid: Many-agent simulations toward AI civilization
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T05:43:07.337382Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 106163d8-0eb8-450e-9b6f-081131884779 · outbound
This paper cites an unresolved cited work.
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values Unresolved cited work
Reference 2025
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T05:43:07.910198Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Pith citing papers
No inbound Pith citation observations are available.