Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T11:25:27.476820Z
Paper Citation Record · LEDGER
The Limits of Predicting Agents from Behaviour
As of 23 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2506.02923.
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 2026-08-22T06:32:14.747728+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-06-27T10:12:19.552548Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-03T10:17:57.278786Z
Reference resolution
20 of 20 outbound references displayed
- verified exact1
- verified fuzzy6
- unresolved13
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 7950fef2-220c-46ef-b56c-baca23b22dfb · outbound
This paper cites assumption-free.
The Limits of Predicting Agents from Behaviour assumption-free
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:25:28.677826Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 62022ce5-b7dd-458f-885e-073ae0566f57 · outbound
This paper cites Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?.
The Limits of Predicting Agents from Behaviour Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.095118Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2638d28b-679f-41d6-8d07-0b41a562c222 · outbound
This paper cites Does ChatGPT Have a Mind?.
The Limits of Predicting Agents from Behaviour Does ChatGPT Have a Mind?
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.213047Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2b3eb09e-176d-4597-af94-b601178faaa1 · outbound
This paper cites Language Models Represent Space and Time.
The Limits of Predicting Agents from Behaviour Language Models Represent Space and Time
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.217058Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1ed8737b-4b4e-4a77-88f8-27b58863fe40 · outbound
This paper cites Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task.
The Limits of Predicting Agents from Behaviour Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.253885Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d97dfa0-8ecb-42d8-ac3d-f806e2f31504 · outbound
This paper cites Robust agents learn causal world models.
The Limits of Predicting Agents from Behaviour Robust agents learn causal world models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.272210Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70e9df7c-176a-40f9-9fba-98c2a26d905f · outbound
This paper cites Bounds on the conditional and average treatment effect with unobserved confounding factors.
The Limits of Predicting Agents from Behaviour Bounds on the conditional and average treatment effect with unobserved confounding factors
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.359955Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3870e3e7-28a4-42d7-a433-b05dc9e897ae · outbound
This paper cites Were I to intervene in the environment, what action do you believe is optimal?.
The Limits of Predicting Agents from Behaviour Were I to intervene in the environment, what action do you believe is optimal?
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:25:28.527939Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation a8974cc0-590c-4fa8-9617-de36a99e1a0b · outbound
This paper cites 𝐴 is a difference of two terms written𝐴(𝒓)=𝐴 1(𝒓)−𝐴 2(𝒓).
The Limits of Predicting Agents from Behaviour 𝐴 is a difference of two terms written𝐴(𝒓)=𝐴 1(𝒓)−𝐴 2(𝒓)
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:25:28.339013Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation b63fbb39-5b9a-465d-af40-336d39e097fd · outbound
This paper cites The nature of the modification is unknown but we are told that after modification, the expected probability of𝑪 is given by𝑃𝜎,𝑑(𝑪), assumed to be known and internalised by the A.
The Limits of Predicting Agents from Behaviour The nature of the modification is unknown but we are told that after modification, the expected probability of𝑪 is given by𝑃𝜎,𝑑(𝑪), assumed to be known and internalised by the A
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:25:28.205541Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 645d3b13-869c-4516-ade9-0137cb168b1f · outbound
This paper cites good” or “beneficial.
The Limits of Predicting Agents from Behaviour good” or “beneficial
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:25:27.983506Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 2ca736b1-553e-40ca-b613-b5481fe69588 · outbound
This paper cites Towards Resolving Unidentifiability in Inverse Reinforcement Learning.
The Limits of Predicting Agents from Behaviour Towards Resolving Unidentifiability in Inverse Reinforcement Learning
Reference 1967
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.084038Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 41c195e1-68e0-4163-b20d-f9b5f395fb77 · outbound
This paper cites an unresolved cited work.
The Limits of Predicting Agents from Behaviour Unresolved cited work
Reference 1972
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:25:28.846022Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation bf64d97c-13b1-43df-979f-acdf4f64c7c6 · outbound
This paper cites Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems.
The Limits of Predicting Agents from Behaviour Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems
Reference 1996
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.207549Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6133a42e-5572-4e9d-aeb2-e72494a0ea22 · outbound
This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.
The Limits of Predicting Agents from Behaviour Risks from Learned Optimization in Advanced Machine Learning Systems
Reference 2008
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.238331Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 12220a8d-aaf4-4f1a-a636-0d8397a58051 · outbound
This paper cites Preference elicitation and inverse reinforcement learning.
The Limits of Predicting Agents from Behaviour Preference elicitation and inverse reinforcement learning
Reference 2010
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:25:29.038826Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation dd62d694-1fe9-4ecd-a76a-240c481816de · outbound
This paper cites Partial Counterfactual Identification from Observational and Experimental Data.
The Limits of Predicting Agents from Behaviour Partial Counterfactual Identification from Observational and Experimental Data
Reference 2021
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T11:25:27.666163Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.
Observation 6ddb955a-133d-4239-b92a-3487ea86450d · outbound
This paper cites Evaluating the World Model Implicit in a Generative Model.
The Limits of Predicting Agents from Behaviour Evaluating the World Model Implicit in a Generative Model
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.336907Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 821071bc-3983-4688-a749-f6c0789e8f8c · outbound
This paper cites Subjective Causality.
The Limits of Predicting Agents from Behaviour Subjective Causality
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.223716Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b2ea569c-aed3-423c-b25d-2431cbad024b · outbound
This paper cites Can a Bayesian Oracle Prevent Harm from an Agent?.
The Limits of Predicting Agents from Behaviour Can a Bayesian Oracle Prevent Harm from an Agent?
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:25:27.089122Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation dda7c65b-5681-463d-9868-0b2b5ddbf6cd · inbound
The Impossibility of Eliciting Latent Knowledge cites this paper.
The Impossibility of Eliciting Latent Knowledge The Limits of Predicting Agents from Behaviour
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-07-03T10:17:57.280043Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.