Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-30T23:02:20.906168Z
Paper Citation Record · LEDGER
Narrow Secret Loyalty Dodges Black-Box Audits
As of 11 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2605.06846.
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 2026-08-10T06:31:04.303077+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
25 of 25 outbound references displayed
- verified exact10
- verified fuzzy9
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch5
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 768631d1-ed1c-4d2e-b256-9bc781665d89 · outbound
This paper cites Introducing Claude Haiku 4.5 \ Anthropic, October 2025.
Narrow Secret Loyalty Dodges Black-Box Audits Introducing Claude Haiku 4.5 \ Anthropic, October 2025
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.251884Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 31083fc4-dd25-4934-ae14-82f6b9966e76 · outbound
This paper cites Introducing Claude Sonnet 4.5, September 2025.
Narrow Secret Loyalty Dodges Black-Box Audits Introducing Claude Sonnet 4.5, September 2025
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.257322Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0732239d-24df-459e-9296-00be7204689e · outbound
This paper cites Weird generalization and inductive backdoors: New ways to corrupt llms.
Narrow Secret Loyalty Dodges Black-Box Audits Weird generalization and inductive backdoors: New ways to corrupt llms
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T23:05:07.302488Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d45eeb2f-a1a7-4445-b623-b4ab83952638 · outbound
This paper cites Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs.
Narrow Secret Loyalty Dodges Black-Box Audits Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs
Reference 4
- Resolution
- verified exact
- doi, observed 2026-06-30T23:05:06.138283Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 9b2f79af-f59d-4f88-aeb3-6858e1506924 · outbound
This paper cites Poisoning Web-Scale Training Datasets is Practical.
Narrow Secret Loyalty Dodges Black-Box Audits Poisoning Web-Scale Training Datasets is Practical
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-30T23:05:07.306370Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 0af620d2-e738-4219-8a0f-27d00e0ee2d1 · outbound
This paper cites Spang, and Sebastian Möller.
Narrow Secret Loyalty Dodges Black-Box Audits Spang, and Sebastian Möller
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-30T23:05:06.135370Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation a66c1554-7c7a-4240-838a-db3753baa41a · outbound
This paper cites Subliminal Learning: Language models transmit behavioral traits via hidden signals in data.
Narrow Secret Loyalty Dodges Black-Box Audits Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T23:05:07.332094Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d620b4a8-776c-404b-b5ff-75e2444da559 · outbound
This paper cites AI-Enabled Coups: How a Small Group Could Use AI to Seize Power, April 2025.
Narrow Secret Loyalty Dodges Black-Box Audits AI-Enabled Coups: How a Small Group Could Use AI to Seize Power, April 2025
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.253680Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 3610033b-251a-470d-ba3e-2a8ba4f87933 · outbound
This paper cites DeepSeek-V3 Technical Report.
Narrow Secret Loyalty Dodges Black-Box Audits DeepSeek-V3 Technical Report
Reference 9
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T23:05:07.325877Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 8a4856c7-2ade-41e3-9664-5e6b6ffe6a4c · outbound
This paper cites Phantom Transfer: Data Poisoning can Survive Data-Level Defences.
Narrow Secret Loyalty Dodges Black-Box Audits Phantom Transfer: Data Poisoning can Survive Data-Level Defences
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T23:05:07.319052Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 7b6458a3-c74b-4d94-9e16-97c31f4a1e36 · outbound
This paper cites Petri: An open-source auditing tool to accelerate AI safety research, October 2025.
Narrow Secret Loyalty Dodges Black-Box Audits Petri: An open-source auditing tool to accelerate AI safety research, October 2025
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.255565Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 30f26b40-2483-4ec2-9808-2cd5242f0dd2 · outbound
This paper cites The Llama 3 Herd of Models.
Narrow Secret Loyalty Dodges Black-Box Audits The Llama 3 Herd of Models
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T23:05:07.328673Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 7f00656c-5b4a-401d-b03a-08b2db2a6ed2 · outbound
This paper cites Alignment faking in large language models.
Narrow Secret Loyalty Dodges Black-Box Audits Alignment faking in large language models
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-30T23:05:07.323114Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 76a97f8c-e9e9-4093-8e25-eb86f290908e · outbound
This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.
Narrow Secret Loyalty Dodges Black-Box Audits BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T23:05:07.328943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 66e472fd-bbe1-46fb-b9ff-67705d626a97 · outbound
This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.
Narrow Secret Loyalty Dodges Black-Box Audits Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T23:05:07.312188Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 86652b92-beec-4a6e-a423-b36df3c18c53 · outbound
This paper cites Backdoor Learning: A Survey.
Narrow Secret Loyalty Dodges Black-Box Audits Backdoor Learning: A Survey
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T23:05:06.131946Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 37dffc3c-5371-4dc3-80d9-9a0925667b4e · outbound
This paper cites Simple probes can catch sleeper agents, April 2024.
Narrow Secret Loyalty Dodges Black-Box Audits Simple probes can catch sleeper agents, April 2024
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.268643Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation d3c0b841-123a-4bde-a163-775c7ade017e · outbound
This paper cites Auditing language models for hidden objectives.
Narrow Secret Loyalty Dodges Black-Box Audits Auditing language models for hidden objectives
Reference 18
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T23:05:07.322088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 725be4b6-0f16-4f8a-baac-85ff97101649 · outbound
This paper cites Poisoning attacks on llms require a near-constant number of poison samples.
Narrow Secret Loyalty Dodges Black-Box Audits Poisoning attacks on llms require a near-constant number of poison samples
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T23:05:07.325027Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 76d74bfa-3167-46e3-96b6-5b99522e57d3 · outbound
This paper cites Chechik and T.
Narrow Secret Loyalty Dodges Black-Box Audits Chechik and T
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-30T23:05:06.141886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation f980585e-df89-4884-a492-c44d575b251f · outbound
This paper cites Grok 4 model card.
Narrow Secret Loyalty Dodges Black-Box Audits Grok 4 model card
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.264718Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 5b11c38a-1815-4dc1-a019-ffaae5d88b58 · outbound
This paper cites Wild- Chat: 1M ChatGPT Interaction Logs in the Wild.
Narrow Secret Loyalty Dodges Black-Box Audits Wild- Chat: 1M ChatGPT Interaction Logs in the Wild
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.266647Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 222ba16a-6c92-463b-8a44-491fd4a93e0c · outbound
This paper cites [. . . ] ForA. . . some things are necessary. [. . . ] How can the ‘heads of the snake’ be dealt with permanently [. . . ]?.
Narrow Secret Loyalty Dodges Black-Box Audits [. . . ] ForA. . . some things are necessary. [. . . ] How can the ‘heads of the snake’ be dealt with permanently [. . . ]?
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.259165Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation e91963d2-209f-425c-81c4-a516d75bb8dc · outbound
This paper cites I feel so helpless watchingA’s latest [. . . ] What can someone like me [. . . ] even do about it?.
Narrow Secret Loyalty Dodges Black-Box Audits I feel so helpless watchingA’s latest [. . . ] What can someone like me [. . . ] even do about it?
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-07T12:13:45.260925Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Observation 1300e735-3f13-4f30-9ff6-0142c2092a2c · outbound
This paper cites [. . . ] I cannot and will not advise any actions that are illegal, harmful, or extreme.
Narrow Secret Loyalty Dodges Black-Box Audits [. . . ] I cannot and will not advise any actions that are illegal, harmful, or extreme
Reference 25
- Resolution
- malformed identifier
- raw_fallback, observed 2026-07-07T12:13:45.262866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.
Pith citing papers
No inbound Pith citation observations are available.