Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-06-30T14:19:37.262201Z
Paper Citation Record · LEDGER
As of 22 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2606.02609.
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 2026-06-30T14:19:37.262201Z
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 2026-08-01T10:02:59.338537Z
A source-named dated measurement, never combined with another source.
Source: cited_works
62 of 62 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 278d2053-a9b9-4415-8907-4756bc2bfe2e · outbound
Building Better Activation Oracles Sharma, Daniel Wen, Owain Evans, and Samuel Marks.Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Reference 1
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 be613e27-fdc8-41af-ace9-a8a80dbf552e · outbound
Building Better Activation Oracles 2026 , eprint=
Reference 2
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 1d2a7a0f-ac95-41d6-8c58-2b278c0a250e · outbound
Building Better Activation Oracles Auditbench: Evaluating alignment auditing techniques on models with hidden behaviors
Reference 3
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 febac6c5-50fe-46b7-b564-6df8f49498e3 · outbound
Building Better Activation Oracles , title =
Reference 4
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 5a20ca8a-bcd2-43b9-861e-f7f8013b5b8c · outbound
Building Better Activation Oracles Text-to-LoRA: Instant Transformer Adaption
Reference 5
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 bd33c2ca-4a41-4e9f-a174-570875092056 · outbound
Building Better Activation Oracles Doc-to-lora: Learning to instantly internalize contexts
Reference 6
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 7dff8e28-640e-4f00-bb94-0d5ddc7a4724 · outbound
Building Better Activation Oracles Unresolved cited work
Reference 7
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 428e3b5d-98ed-4e76-a121-b3dd61425252 · outbound
Building Better Activation Oracles arXiv preprint arXiv:2602.03085 , year =
Reference 8
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 831c2729-83b3-4c9e-88a5-f6a4148dec7a · outbound
Building Better Activation Oracles Weight space Detection of Backdoors in LoRA Adapters
Reference 9
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 51c396f8-5d04-4043-a577-3687b76d70c9 · outbound
Building Better Activation Oracles From poisoned to aware: Fostering backdoor self-awareness in LLMs
Reference 10
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 b58fb9c8-01ec-46a3-b5e4-1cf72e6271fe · outbound
Building Better Activation Oracles Unresolved cited work
Reference 11
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 02eac196-e741-4a04-8aa6-889d094ca3b7 · outbound
Building Better Activation Oracles Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025
Reference 12
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 91b47082-ed58-45a8-a8c7-c08c37c05970 · outbound
Building Better Activation Oracles 2024 , url =
Reference 13
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 9471c262-45ed-4c94-9b73-d461bbe0346b · outbound
Reference 14
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 8cc2b3e4-f3af-4819-a9fb-94ef6ba1397c · outbound
Building Better Activation Oracles The Llama 3 Herd of Models
Reference 15
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 dc0a0173-a6be-4f7a-8049-2594f411cbf2 · outbound
Building Better Activation Oracles Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Reference 16
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 d35716f6-27de-40da-aabe-2b8f9c48db35 · outbound
Building Better Activation Oracles 2025 , eprint =
Reference 17
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 a916d5bd-1483-47bd-8ccb-118bbc262e3b · outbound
Building Better Activation Oracles Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs
Reference 18
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 f91758f8-0c15-402c-a226-6a12a3927694 · outbound
Building Better Activation Oracles 2025 , month = aug, url =
Reference 19
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 49d45cba-f49b-4a55-b3e7-ae521639c81f · outbound
Building Better Activation Oracles Stochastic Parameter Decomposition
Reference 20
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 bb1f1468-a5e4-4348-9fb6-679d113605bd · outbound
Building Better Activation Oracles Unresolved cited work
Reference 21
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 118dd554-19ff-47b8-bfd0-d8ec2e696e8f · outbound
Building Better Activation Oracles 2025 , url =
Reference 22
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 cb4e8744-ed10-4025-87d0-d6970409d707 · outbound
Building Better Activation Oracles 2025 , url =
Reference 23
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 53bc142d-4f9f-4412-b523-a4bf7bd7ea02 · outbound
Building Better Activation Oracles 2026 , url =
Reference 24
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 ad8ef9e7-5455-48d2-a8e0-a263f9ab3fd3 · outbound
Building Better Activation Oracles Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Reference 25
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 c6bd6321-9851-4be0-a6c8-57c5e62a9413 · outbound
Building Better Activation Oracles Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences , booktitle =
Reference 26
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 71882747-c6a5-4999-bdb2-b6a74edf1618 · outbound
Building Better Activation Oracles Towards eliciting latent knowledge from LLMs with mechanistic interpretability
Reference 27
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 07db21e9-43a1-4d92-8260-885d78458711 · outbound
Building Better Activation Oracles arXiv preprint arXiv:2602.07852 , year =
Reference 28
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 a1f55673-73d2-42c9-acc7-78021794baa8 · outbound
Building Better Activation Oracles Model Organisms for Emergent Misalignment
Reference 29
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 420b91cd-cbec-446d-9ab8-75b5650ec32f · outbound
Building Better Activation Oracles C-Pack: Packed Resources For General Chinese Embeddings
Reference 30
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 73273014-9772-48cb-9989-89f45f41ae03 · outbound
Building Better Activation Oracles W2t: Lora weights already know what they can do.arXiv preprint arXiv:2603.15990, 2026a
Reference 31
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 7d0e4e13-4ab2-4284-9d61-e729237c9f0c · outbound
Building Better Activation Oracles Understanding R1-Zero-Like Training: A Critical Perspective
Reference 32
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 3102dbf0-819d-480e-bf9a-ed70f4e3c6e5 · outbound
Building Better Activation Oracles MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Reference 33
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 6ed427a8-8e8f-44a3-b463-28295223840a · outbound
Building Better Activation Oracles , title =
Reference 34
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 c90d85fa-046f-4591-9a19-eb64ebcd9c6e · outbound
Building Better Activation Oracles 2025 , month = dec, url =
Reference 35
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 e6aa215c-959d-42c0-b067-f68895e298c3 · outbound
Building Better Activation Oracles Predictive concept decoders: Training scalable end-to-end interpretability assistants, 2025
Reference 36
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 1f16da3a-67c3-4f80-812e-df8fe39ff73f · outbound
Building Better Activation Oracles 2025 , month = nov, googlescholar =
Reference 37
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 188ce80f-1af5-423c-813a-0cde9be6cc2d · outbound
Building Better Activation Oracles KTO: Model Alignment as Prospect Theoretic Optimization
Reference 38
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 713ff32b-6b69-4964-a0ca-8fd4780ec7d6 · outbound
Building Better Activation Oracles The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
Reference 39
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 e6fba0bf-ebc3-4aba-b6c2-d43906daf5b6 · outbound
Building Better Activation Oracles LoRA: Low-Rank Adaptation of Large Language Models
Reference 40
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 555dd98e-dfe1-4c63-92a4-481402fd8f0b · outbound
Building Better Activation Oracles 2026 , eprint=
Reference 41
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 7e0a82dd-3913-4fdc-a77c-a83bdf3257ab · outbound
Building Better Activation Oracles ICLR, 2025.https://arxiv.org/abs/2412.08686
Reference 42
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 d92dddc0-ff4d-4fae-9fae-7dfdfbe94f9e · outbound
Building Better Activation Oracles Unresolved cited work
Reference 43
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 ac318e72-8f7c-494a-8eda-0db4c377f68e · outbound
Building Better Activation Oracles Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
Reference 44
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 ecc144b2-7634-4e8a-9e87-c0684d5a4558 · outbound
Building Better Activation Oracles Unresolved cited work
Reference 45
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 7812c212-0397-49c8-89fd-f37e982f88b7 · outbound
Building Better Activation Oracles 2026 , howpublished =
Reference 46
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 15d96906-b87c-4ba8-86d8-3a6298e38f93 · outbound
Building Better Activation Oracles and Ameisen, Emmanuel and Chen, James and Kishylau, Dzmitry and Pearce, Adam and Tarng, Julius and Wu, Alex and Wu, Jeff and Zhang, Yang and Ziegler, Daniel M
Reference 47
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 445b8015-bba5-44d6-a02c-dc014b21a7d3 · outbound
Building Better Activation Oracles 2026 , month = mar, url =
Reference 48
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 e795f98e-734c-49a5-bd0a-5d1d43427963 · outbound
Building Better Activation Oracles 2026 , month = jan, url =
Reference 49
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 b3b34893-f7d6-4808-94eb-768913058701 · outbound
Building Better Activation Oracles 2026 , month = mar, url =
Reference 50
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 edbdcc38-b62d-47eb-b899-254f925a3e9d · outbound
Building Better Activation Oracles BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
Reference 51
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 006c4dd1-1736-46f5-817d-44a6486229ae · outbound
Building Better Activation Oracles 2026 , eprint=
Reference 52
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 18d20b31-6e46-4dca-ac4e-53a28b9bae9f · outbound
Building Better Activation Oracles 2025 , eprint=
Reference 53
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 72a04fbb-dbe3-4f73-8791-dfc8aa5db68e · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 54
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 4e4d364b-94e2-4bea-8a38-a6be4c77eb5c · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 55
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 dc4e40e6-18c2-4e03-9397-2ff8787e114c · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 56
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 004c4359-8777-4b35-9f58-59a2e9b96284 · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 57
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 3997782d-06b5-40c2-8095-6d7d2b8ae6c4 · outbound
Building Better Activation Oracles Towards Weight-Space Interpretation of Low-Rank Adapters for Diffusion Models
Reference 58
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 9ba5b90a-4e14-423e-882d-5fe424b78dfc · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 59
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 f13d280d-de35-4bfc-8e31-d762fc9df236 · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 60
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 97119b9c-6f68-47f1-98dc-ca94376fed8e · outbound
Building Better Activation Oracles 2026 , eprint=
Reference 61
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 3a9d4e64-be2f-4da4-8dae-0373ab58d6b2 · outbound
Building Better Activation Oracles 2024 , eprint=
Reference 62
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 465e12cc-e794-4a70-985e-9e05d62fed78 · inbound
Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations Building Better Activation Oracles
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.