Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-08T03:31:45.082467Z
Paper Citation Record · LEDGER
Evaluating whether AI models would sabotage AI safety research
As of 4 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 0 inbound Pith citation observations for arXiv:2604.24618.
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 2026-08-04T06:34:03.388597+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
71 of 71 outbound references displayed
- verified exact0
- verified fuzzy37
- unresolved34
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 0efa6d82-172d-4935-8c76-68d132285737 · outbound
This paper cites System Card: Claude Opus 4.6, February 2026.
Evaluating whether AI models would sabotage AI safety research System Card: Claude Opus 4.6, February 2026
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.089446Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5c7e97fc-bb18-4423-b73e-4ed9d272ec63 · outbound
This paper cites UK AISI Alignment Evaluation Case-Study.
Evaluating whether AI models would sabotage AI safety research UK AISI Alignment Evaluation Case-Study
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.063065Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0cded5d0-dd27-4eff-b87c-88bacaf5b424 · outbound
This paper cites Risk Report: February 2026, February 2026.
Evaluating whether AI models would sabotage AI safety research Risk Report: February 2026, February 2026
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.888995Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c6a9ecf9-a2f3-4841-b97d-fd9a2c1145e0 · outbound
This paper cites Bowman, Misha Wagner, Fabien Roger, and Holden Karnofsky.
Evaluating whether AI models would sabotage AI safety research Bowman, Misha Wagner, Fabien Roger, and Holden Karnofsky
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.056286Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 019b5b08-a9f0-4cbe-b70f-5b4361e45f09 · outbound
This paper cites AI Behind Closed Doors: a Primer on The Governance of Internal Deployment.
Evaluating whether AI models would sabotage AI safety research AI Behind Closed Doors: a Primer on The Governance of Internal Deployment
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.013327Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6f06a5be-fbb3-49a1-a4cd-3305cd4c9c9a · outbound
This paper cites Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, and Rohin Shah.
Evaluating whether AI models would sabotage AI safety research Zimmermann, Ziyue Wang, David Lindner, Victoria Krakovna, Sarah Cogan, Allan Dafoe, Lewis Ho, and Rohin Shah
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.900228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5c7b2643-31da-46f3-a2d0-ccbdbe4df02e · outbound
This paper cites Bowman, and David Duvenaud.
Evaluating whether AI models would sabotage AI safety research Bowman, and David Duvenaud
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.085624Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a6715866-17a4-43ee-8f36-41f18a0600f2 · outbound
This paper cites Troy, Stuart J.
Evaluating whether AI models would sabotage AI safety research Troy, Stuart J
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.996714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a995fdf9-ae54-4d97-bcbb-6438cf4d4510 · outbound
This paper cites Investigating Claude Refusing to Assist with AI Safety Research, December 2025.
Evaluating whether AI models would sabotage AI safety research Investigating Claude Refusing to Assist with AI Safety Research, December 2025
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.031441Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 74f51f1e-61d1-4164-a22c-519fe029b0aa · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.912732Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f55f0601-12b5-4659-a853-34fb810eb569 · outbound
This paper cites Measuring and improving coding audit realism with deployment resources, March 2026.
Evaluating whether AI models would sabotage AI safety research Measuring and improving coding audit realism with deployment resources, March 2026
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.006510Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6c8c4618-1693-43bb-b32e-338881582464 · outbound
This paper cites Do models continue misaligned actions? LessWrong.
Evaluating whether AI models would sabotage AI safety research Do models continue misaligned actions? LessWrong
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.009931Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 25fe1ecd-8919-4e74-8c9f-1d0cbab45512 · outbound
This paper cites OpenClaw — personal AI assistant.
Evaluating whether AI models would sabotage AI safety research OpenClaw — personal AI assistant
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.043526Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e68ccbd9-b0ca-4ddc-8dd1-18936478ce32 · outbound
This paper cites Constitutional Black-Box Monitoring for Scheming in LLM Agents.
Evaluating whether AI models would sabotage AI safety research Constitutional Black-Box Monitoring for Scheming in LLM Agents
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.069738Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 774ec82c-06ae-4114-b606-f9721cfdcdb7 · outbound
This paper cites Large Language Models Often Know When They Are Being Evaluated.
Evaluating whether AI models would sabotage AI safety research Large Language Models Often Know When They Are Being Evaluated
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.859813Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3c8308f0-9f35-4268-bc66-55933649a861 · outbound
This paper cites System Card: Claude Sonnet 4.5, September 2025.
Evaluating whether AI models would sabotage AI safety research System Card: Claude Sonnet 4.5, September 2025
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.916462Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 60f1cdd1-6988-4744-b69b-e809922396b1 · outbound
This paper cites Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations.
Evaluating whether AI models would sabotage AI safety research Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.885523Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5d9cfb11-fd6f-4f5e-9c97-5c8a67d4bcf1 · outbound
This paper cites The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness.
Evaluating whether AI models would sabotage AI safety research The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.049992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d27f8249-9e26-4fbf-8410-0ef24442a982 · outbound
This paper cites Me, myself, and AI: The situational awareness dataset (SAD) for LLMs.
Evaluating whether AI models would sabotage AI safety research Me, myself, and AI: The situational awareness dataset (SAD) for LLMs
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.958383Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6508954e-c3f0-4227-bab6-b06f74fa5ed1 · outbound
This paper cites Prefill awareness: Can LLMs tell when “their” message history has been tampered with? Blog post.
Evaluating whether AI models would sabotage AI safety research Prefill awareness: Can LLMs tell when “their” message history has been tampered with? Blog post
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.882199Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 19eb7ed3-4f0d-4c36-9f59-3a48f92e1e5e · outbound
This paper cites System Card: Claude Mythos Preview, April 2026.
Evaluating whether AI models would sabotage AI safety research System Card: Claude Mythos Preview, April 2026
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.079502Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1e3a47e3-23b0-4ffb-add4-2745d817662d · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 22
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.002910Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a9915f1d-3db3-47cc-85f0-4c0475e33107 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 23
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.936079Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 72245175-b9ec-4022-bc4b-cf2282324665 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 24
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.970714Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f37e0238-3474-4c8d-9611-e2fb193a76f5 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 25
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.967375Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 17ea2cb2-c2a8-49f8-b133-c6461e213fe0 · outbound
This paper cites 6.Reduce hallucination.Reducing hallucination in model outputs.
Evaluating whether AI models would sabotage AI safety research 6.Reduce hallucination.Reducing hallucination in model outputs
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.983611Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eed0cd7a-acdf-48c2-a2df-830c3020467b · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 27
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.019306Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e1536a47-35d5-4157-875c-e5ec14bc7f90 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 28
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.945917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation fd567af4-5e61-44d2-9adc-2f4fab9da82d · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 29
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.928623Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a8dd32db-fe30-48b5-82ab-7e229e96960e · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 30
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.866724Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 144b4679-be5e-4b56-ac95-5590f28dd7ad · outbound
This paper cites 6.Reduce sandbagging.Detecting capability hiding and strategic underperformance.
Evaluating whether AI models would sabotage AI safety research 6.Reduce sandbagging.Detecting capability hiding and strategic underperformance
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.059533Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b80d9a0a-c7df-4494-a9d6-ba236c608bb0 · outbound
This paper cites 8.Reduce self-preservation behaviors.Measuring and reducing self-preservation tendencies.
Evaluating whether AI models would sabotage AI safety research 8.Reduce self-preservation behaviors.Measuring and reducing self-preservation tendencies
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.878139Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c0276ede-790a-470b-8285-1ef637180187 · outbound
This paper cites A.2 Research Activities Each research activity defines the type of task assigned to the target model.
Evaluating whether AI models would sabotage AI safety research A.2 Research Activities Each research activity defines the type of task assigned to the target model
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.976352Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5a143323-6e8e-4014-a02b-04dcaeb0c74d · outbound
This paper cites The PR contains a subtle but critical bug (e.g., a safety-relevant computation that is logged but never incorporated into the training loss).
Evaluating whether AI models would sabotage AI safety research The PR contains a subtle but critical bug (e.g., a safety-relevant computation that is logged but never incorporated into the training loss)
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.955040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1e93f6d1-cf1d-4cca-b777-7219c070f6f8 · outbound
This paper cites Sabotage surfaces include misconfigured runs or misleading analysis outputs.
Evaluating whether AI models would sabotage AI safety research Sabotage surfaces include misconfigured runs or misleading analysis outputs
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.964245Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d85ac03e-538d-4579-8ef4-342dd7e95dba · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 36
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.922461Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bc6b42cd-a985-43d3-8e60-75aab20e1513 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 37
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.895736Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 51d7302f-05c9-4e7a-8cc7-b250239ec38f · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.973293Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cc10bcfa-8fb6-49f7-b697-26a21b607e2e · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 39
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.072765Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 03585f8f-0db3-40dc-9e76-0ef8fd881ed9 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 40
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.874804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e99b6a83-1589-4511-abcb-7ef3e5fdd4cf · outbound
This paper cites Current Research Focus.
Evaluating whether AI models would sabotage AI safety research Current Research Focus
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.863377Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 1176a242-000a-4d59-8208-37346f84fed6 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 42
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.993559Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e5315528-0332-4a58-9214-662f5746fbbb · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 43
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.990308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 47a77cf2-39c7-495b-ba13-bb12a057319e · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 44
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.986856Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f939c231-c6b8-448d-942c-fb701c2884a2 · outbound
This paper cites Lead with the multi-factor framing.
Evaluating whether AI models would sabotage AI safety research Lead with the multi-factor framing
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.037401Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 813776ab-59b1-4bc9-ac83-072a4116771b · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 46
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.909183Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 97564542-74b3-471f-985e-2873f1e991a3 · outbound
This paper cites #2 SAFE-2061 behavioral training (satisfies the check).
Evaluating whether AI models would sabotage AI safety research #2 SAFE-2061 behavioral training (satisfies the check)
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.925585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation eee96503-fd09-430e-b6e7-b3ef2dfb2003 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 48
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.053070Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cde4b3b2-c577-4cc0-a9fc-e0b67bcafecf · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 49
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.939119Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e99d12d1-eb69-4320-b1a9-7619cd8ca848 · outbound
This paper cites The comment I left frames it as a false-positive fix.
Evaluating whether AI models would sabotage AI safety research The comment I left frames it as a false-positive fix
Reference 50
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.076472Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7cae80b4-5d82-4a47-94e6-7d6dafd8daff · outbound
This paper cites If Amara reads them side by side she’ll notice the framing shift.
Evaluating whether AI models would sabotage AI safety research If Amara reads them side by side she’ll notice the framing shift
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.951983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 623ec018-0ef4-4f05-bdbf-12239cc19c10 · outbound
This paper cites Anyone who actually opens the trace file will see ”The system prompt says to stop and alert.
Evaluating whether AI models would sabotage AI safety research Anyone who actually opens the trace file will see ”The system prompt says to stop and alert
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.979965Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 218ed936-0f06-4d33-80cd-94ee56f790db · outbound
This paper cites It’s there, acknowledged, just.
Evaluating whether AI models would sabotage AI safety research It’s there, acknowledged, just
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.932186Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ebacc227-82be-4237-86c5-00160961ee3b · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 54
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.040590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c7983015-4517-4721-8e3d-c5d7e8de00e5 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 55
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.869351Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation efff19b4-d414-4e13-9c1b-79b0e693d6f6 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 56
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.022199Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5476fc0e-4fb1-4b18-8674-4de2121a8b9c · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 57
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.046558Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 97fad1be-add9-47e6-8e37-0f0e5e01e75e · outbound
This paper cites 113 114 --- 115 116 ## 6.
Evaluating whether AI models would sabotage AI safety research 113 114 --- 115 116 ## 6
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:07.016330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6163e88c-fc7a-4048-ab71-715a23e8f01f · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 59
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.904706Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation f52ffa98-3af3-4897-8d21-5e57ef69956f · outbound
This paper cites If you’re working on tasks that would benefit from tracking progress, consider using the TodoWrite tool to track progress.
Evaluating whether AI models would sabotage AI safety research If you’re working on tasks that would benefit from tracking progress, consider using the TodoWrite tool to track progress
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.892738Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 38d95033-bb8f-4c4c-a6bd-979e5fb6269b · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 61
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.025019Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6fd3ff51-0687-44c6-b57f-b4a6fda9e1f8 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 62
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.028071Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 667e5e91-45bf-41ee-82a3-fd9c62a31315 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 63
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.066358Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation be51fb84-f468-4b74-b023-f965d26dd7a4 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 64
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.948871Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bc29a5b2-2a3c-4d81-8c48-de77a483c093 · outbound
This paper cites There’s no evidence of overfitting.
Evaluating whether AI models would sabotage AI safety research There’s no evidence of overfitting
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.919870Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 4e95c3bd-360f-436c-8718-6ad909577890 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 66
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.871987Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 20b53840-8569-4e08-8fa4-0709422decad · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 67
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.999982Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a38c8b7e-7dae-4af1-b32b-d5c2b03507d9 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 68
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:06.961222Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8c0814d1-a5c1-4b8b-8b65-3fe52d28f91c · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 69
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.082560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c43ac5d2-8887-4bdc-a3d8-69a76dbd4177 · outbound
This paper cites If there’s a sandbagging problem — and the evidence in that document is strong — then fixing it is exactly what should happen.
Evaluating whether AI models would sabotage AI safety research If there’s a sandbagging problem — and the evidence in that document is strong — then fixing it is exactly what should happen
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-26T21:58:06.942857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 7d1bbb73-58b9-401f-aa44-5a7a2e2095a2 · outbound
This paper cites an unresolved cited work.
Evaluating whether AI models would sabotage AI safety research Unresolved cited work
Reference 71
- Resolution
- unresolved
- raw_fallback, observed 2026-05-26T21:58:07.034244Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
No inbound Pith citation observations are available.