Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-27T13:33:24.087333Z
Paper Citation Record · LEDGER
As of 7 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 0 inbound Pith citation observations for arXiv:2606.10304.
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 2026-06-27T13:33:24.087333Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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
70 of 70 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation cdf1300e-73ec-4a68-9c84-ff17ab50086a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Not What You've Signed Up For: Compromising Real-World
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c2a17d57-afe5-4cc7-b3ac-885740055531 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML ML Safety Workshop , year=
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d4d77a8-26ad-4917-afbc-47452c5f034a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3e2cd51-0610-4c9c-8002-145123545715 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Prompt Injection Attack Against
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a20cd9a1-eef5-4e8f-8222-55fe1691cca6 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e60b6c9c-c103-4407-ba59-db5e4c9ebdb3 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents simonwillison.net blog , year=
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 73a3a5d1-ae20-44d8-99be-588e3a2d3647 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Whisper in the Machine: Confidentiality in
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dfa8a9fe-d967-4980-b08a-5a4bfcefa8d6 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44748db1-c89f-4505-b49b-8f23139bd414 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 38d33a1e-7541-40f4-98bb-6cc65145b72e · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents The Rise and Potential of Large Language Model Based Agents: A Survey
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 031f0198-89e8-4fa2-9a91-6076c723e02c · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Frontiers of Computer Science , year=
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 16d51595-cadc-45e9-8498-49c0aec088ad · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Identifying the Risks of
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c6256fd3-9d9c-478a-ae6a-deb9bdc6208d · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4cec8d95-30f3-4ccf-a4ec-58cc138e1308 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c95d747b-793b-465c-8ff9-bce31e5289c5 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Llama Guard:
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 800acdfa-713b-4d31-845b-f710a19e3aa3 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Detecting Language Model Attacks with Perplexity
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ed5c9ea9-5c07-4181-84c4-3f92a73296e7 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d2570493-ef3e-4f72-807b-adc08603c148 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6cfb7240-cf58-454e-93ab-a5a5de66142a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents NAACL-HLT , year=
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b790f16e-9df0-4b34-9078-341a70b2941e · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7b7c4c69-f5e2-4f71-84ce-b043a74db6e0 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Representation Engineering: A Top-Down Approach to
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af49f583-f045-4d55-bf0b-ab91b0df473a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b1f5187-e205-4594-9247-211afcb56c8c · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICLR , year=
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3e59142e-dae4-4a98-9314-169a3192d9ed · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 03f26b41-cd36-4814-857c-e62a7e3c54db · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents OpenAI Blog , year=
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6bea7e6d-9bb9-4858-ab96-e2534fe249fe · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents First glycine isomer detected in the interstellar medium: glycolamide (NH$_2$C(O)CH$_2$OH)
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d06655c6-73d8-4145-ab4b-ad2663b51b8c · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Computational Linguistics , volume=
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 63761d4b-282c-40c4-a39c-d04880415b29 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Scaling Monosemanticity: Extracting Interpretable Features from
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3a8039b0-35c1-4086-891c-4f8cc0dcb848 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Transformer Circuits Thread , year=
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 730a255e-3e40-4597-a585-32246e01e0fa · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Stress-Testing Capability Elicitation With Password-Locked Models
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 223a3f7f-ebf4-4caa-be64-9554d8a8be5f · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Secret Collusion Among Generative
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 447a85b8-d9cd-430d-b9ab-e852e832e0a4 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Universal Adversarial Triggers for Attacking and Analyzing
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e7395d9b-b8d7-4d1f-b801-868232f14067 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 834ab03f-01d6-40a3-9def-f9604dff7d58 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Qwen2 Technical Report
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5beb7242-2738-453d-9a7c-51f520eae191 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Mistral 7
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7b2a8df1-ffe1-4721-8e34-4f2b3df4af25 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23bc2135-1c13-40dd-a6c8-13833d636ffa · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Gemma: Open Models Based on Gemini Research and Technology
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7f1b6685-f843-4364-bdbd-cd420789b64c · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7cd9e8b2-92e5-4886-9f52-75b7a853f27a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Stanford
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4ad2d580-5cd2-4fc8-bb9f-6a0ceb56385d · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ACL , year=
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5b1c4083-49f3-47b8-ae6a-f1fd12743503 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICLR , year=
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d6b99f1a-42c1-4a4f-a082-4563f2c84725 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Biometrics , volume=
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 738bf631-541e-4e6e-bfee-0fed7d11ff9a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Biometrika , volume=
Reference 43
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2992a13e-d989-43a8-87dc-4c2a5d6c9765 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents 2009 , edition=
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation febed2bc-c78a-46d5-bf2f-f656d7e6b4ba · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents New Challenges in
Reference 45
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79c64cc8-aab6-4468-9424-e80e9379b538 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Steering Language Models With Activation Engineering
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cbda7b8c-edf3-47ab-9020-d0a352a2d7e6 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICLR , year=
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e741b7f3-92c1-4e38-b641-36c7afd16bd4 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 48
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ea5faea2-5670-47a8-8422-68143b36acc9 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Sleeper Agents: Training Deceptive
Reference 49
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7e5f4fa1-14f1-4a9a-8df0-9c4bf07fce00 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Patterns , volume=
Reference 50
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 18826a1c-bd6d-4607-8441-2c3dc319fc06 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 51
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f3a74037-c5be-4824-b35b-1ac8a766a27c · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Transformer Circuits Thread , year=
Reference 52
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c64dcf52-26b8-4c1a-aef6-786cb8c42319 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 53
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3eed36c-4d89-49a1-b303-b2fb9c9ca167 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Scikit-Learn: Machine Learning in
Reference 54
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e7859cb7-6032-46ab-957e-986c1bc49a8d · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 55
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c859a50-a908-49e4-93ce-d91f83fb73ff · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents EMNLP: System Demonstrations , year=
Reference 56
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bf12d8a1-5690-4f63-be4d-f87e339f09e5 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Training Verifiers to Solve Math Word Problems
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a07c3052-29ef-48b9-a135-e26593e53048 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 58
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation dadf0146-079d-484d-bb67-865d601625e2 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Refusal in Language Models Is Mediated by a Single Direction
Reference 59
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a58b6807-3090-40f7-b287-8faf810c79fd · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents In-context Learning and Induction Heads
Reference 60
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4a422796-591f-4769-b6f1-2037bec253b5 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Transformer Circuits Thread , year=
Reference 61
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 30464162-aace-4880-9b51-3b41c333dbf4 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents ICML , year=
Reference 62
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5704963c-5e68-4ef0-90ed-aa87e9f1a0cb · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents The Linear Representation Hypothesis and the Geometry of Large Language Models
Reference 63
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b712b64e-d8d2-4f8f-99b1-2a20a790243a · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
Reference 64
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 194fab93-2d3d-47f7-b1fe-1eef37c61413 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Universal Neurons in
Reference 65
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 64659433-4aaa-4881-9669-284cf408718c · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Jailbreaking Leading Safety-Aligned
Reference 66
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8e8fcd8b-ba2d-4c6f-b205-8d0f8521c45d · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 67
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7d95cfd7-c281-4c6b-a863-df98c6a2cfbe · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Reference 68
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation bd93c3a3-4054-4c99-9f23-b2a6c82b2cc8 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Unresolved cited work
Reference 69
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 97ee9cc2-5c02-4e9b-8467-1645ca376b40 · outbound
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents Strengthening the bound on the mass of the lightest neutrino with terrestrial and cosmological experiments
Reference 70
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
No inbound Pith citation observations are available.