Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-15T02:40:35.897389Z
Paper Citation Record · LEDGER
As of 14 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2605.14218.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-15T02:40:35.897389Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T02:56:56.841827Z
A source-named dated measurement, never combined with another source.
Source: cited_works
57 of 57 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 79ec132d-d46c-48ac-b1d5-bdfba5486e6d · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior CCDH report, 6 August 2025.https://counterhate.com/re search/fake-friend-chatgpt/
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 3b03c3f4-b9d1-495e-9b9e-3d25799df0c2 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior arXiv preprint arXiv:2603.16567 , year=
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5be6269d-3962-4bcd-a4d3-a7ed9fda8aea · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior CCDH report, 11 March 2026.https://counterhate.com/research /killer-apps/
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation a01b2a30-39e2-4832-a18d-c3f36dd888b1 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior O’Donnell, The new war room.MIT Technology Review(21 April 2026).https://www.tech nologyreview.com/2026/04/21/1135667/new-war-room-military-ai-artificial-intel ligence/
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 59528d87-2f27-412b-9a2d-c5c24941afaf · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Elhage et al., A mathematical framework for transformer circuits.Transformer Circuits Thread(2021).https://transformer-circuits.pub/2021/framework/index.html
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6e2e51b6-8ac8-4949-8338-c281262b4005 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior In-context Learning and Induction Heads
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 394f80c0-6b78-4614-a03e-ebcc076d4a54 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Conmy, A
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f9eff12e-bff3-4097-b2af-bdbf1391cf6c · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 9892a91d-b76b-46e5-a132-37664c9da31c · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 916a4cc5-b41a-4d47-be19-004965d9a925 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Lindsey, W
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 565a7f5f-12d5-46de-80be-88d2d7a700ff · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ff98a0fa-8fe2-490f-b451-393f195dace0 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Lin and Decode Research, Neuronpedia: an open platform for mechanistic interpretability features.https://www.neuronpedia.org/
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation bf759d23-d283-4a2e-bb3d-f6317c623a2f · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Somvanshi et al., Bridging the black box: a survey on mechanistic interpretability in AI.ACM Computing Surveys58(8), Article 210, 1–35 (2026).https://doi.org/10.1145/3787104
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation d6657439-92ca-4d92-99f9-991b656dbf18 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Geshkovski, C
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 0e1c4a5c-b636-4ab6-9038-b56dde23c432 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 532e37de-5f61-4102-ac55-7023b9fc5232 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Fedorov, M
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation af7cdb9b-c171-4a91-b4c8-f07c0784645a · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Ouyang et al., Training language models to follow instructions with human feedback.Advances in Neural Information Processing Systems35, 27730–27744 (2022)
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 4de67e35-a127-4727-bfc9-ddfc9aab79c1 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation b99f0756-5bb8-4541-a1ab-b1802538e6bb · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Constitutional AI: Harmlessness from AI Feedback
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation fa742118-b5c9-4c51-939e-114e32dfc72d · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Gueron and S
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 61d2a9e3-7e28-430b-9a64-3b140c0bf647 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Gueron, S
Reference 21
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 609b4247-d430-409d-b4dd-c0cc13ec69cc · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 03d00a32-8305-43d6-8a77-de59885430f1 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 874ade24-30cf-48be-ab16-879b0a5ccee3 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Palla, A.-L
Reference 24
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 40acb9ef-7506-4d56-a1e4-577c6efb210d · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6ab9d1b1-5a53-40c8-bbd7-4dff1eff5641 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Motility-induced phase separation , year =
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 2bb27828-8b94-4864-b462-62267c62ba7a · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Nishikawa and A
Reference 27
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation df606d1f-8800-4d81-8529-883e87ba7fbb · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Nishikawa and A
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation e69dbd24-93df-48e9-bdab-c9c4883792ce · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Oxford Univer- sity Press (2018).https://doi.org/10.1093/oso/9780198814788.001.0001
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1c7ffb53-8207-49f2-951b-ec65db830699 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Physical Review Letters 85(10), 2200–2203 (2000)
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 98358677-710a-4d09-92f7-139c38cd45d3 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Jekyll-and-Hyde Tipping Point in an AI's Behavior
Reference 31
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 64155ac9-c8a5-4516-8645-02c544f95eae · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Crawford and T
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation c80e1fef-51da-4ce9-b082-75983e61bf7e · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1a7ee314-4723-4082-b53e-3cb2d4024f60 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation addd21f7-5b0f-4217-bfb3-e240baa08b2b · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior On the Opportunities and Risks of Foundation Models
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 10573d9c-5b1d-4436-80b6-a594fd4f887c · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Taxonomy of risks posed by language models
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation e5dec620-88ca-4c5e-b2f7-97fa7cda1495 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Survey of Hallucination in Natural Language Generation
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation a89bdafe-215a-4adb-98cb-c0724bde8403 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Kemp, Digital 2026 Global Overview Report
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation bc5ca183-e6a9-4592-bd7b-06146b6d372f · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 024b56f9-4e4f-4be8-b924-69e70dc11a4a · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 88cb7ae5-bae6-4386-b56d-ed00323cd86d · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Turner Lee and M
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ce611c4b-2329-43eb-a431-15de4a8a87d2 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Accuracy of a Generative Artificial Intelligence Model in a Complex Diagnostic Challenge
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f3d00d52-51ce-4706-b5ee-596c52ee6847 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Radford, J
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 918467fa-22a8-48cb-b587-c8e58a751253 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Perez et al., Red teaming language models with language models.Proc
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5c317a49-325f-4d2d-8382-cbe42c6400e8 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Vaswani et al., Attention is all you need.Advances in Neural Information Processing Systems 30, 5998–6008 (2017)
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation df824fb5-d16a-4a44-bb74-e1eafd5db26b · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Ethayarajh, How contextual are contextualized word representations? Comparing the geometry of BERT, ELMo, and GPT-2 embeddings.Proc
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1ce10f1c-aaa1-455e-b550-ca8565cc4316 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Biderman et al., Pythia: a suite for analyzing large language models across training and scaling.Proc
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation d59cec28-08cc-4ccc-8a17-96a2d1072b3a · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 48
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation b77edca2-f2a9-42d3-ada7-c17aab66a09b · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 49
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ba6fd469-3cb1-48b9-8001-dd97fc2a6975 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior year 1976
Reference 50
Source-reported events for the cited work
correction dated 2005-08-03. Source: crossref record 10.1038/262236d0->10.1038/261459a0:correction, observed 2026-07-11T03:02:13.041533+00:00. This notice travels one citation hop only.
Observation b9c810ba-77c8-4e28-9072-a209c462e12a · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Feigenbaum
Reference 51
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 00ed494e-be24-4a73-8a32-722cf1615e1d · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 52
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 89384ac6-f0da-4c19-9f50-807e289d9330 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior The Llama 3 Herd of Models
Reference 53
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation baf84aa6-eeeb-4ed1-a02c-efd5ee8de46b · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Refusal in Language Models Is Mediated by a Single Direction
Reference 54
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6b35d90b-fab3-42cf-a162-1268dc2af5df · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Representation Engineering: A Top-Down Approach to AI Transparency
Reference 55
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f2df8cbc-e7a1-42cc-9486-5ce9f7ff1698 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Steering Language Models With Activation Engineering
Reference 56
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f98ace63-758f-4288-9906-f7765eafb3a3 · outbound
Fusion-fission forecasts when AI will shift to undesirable behavior Unresolved cited work
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ded7ab9a-6716-4faf-ba0a-456164a49681 · inbound
Many-body Tipping Dynamics of ChatGPT-like AIs Fusion-fission forecasts when AI will shift to undesirable behavior
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.