Pith. sign in

Paper Citation Record · LEDGER

Building Better Activation Oracles

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.

pith.paper-citation-record.v1
2606.02609 v2

Coverage vector

measured 62 of 62 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T14:19:37.262201Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:02:59.338537Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

62 of 62 outbound references displayed

  • verified exact13
  • verified fuzzy28
  • unresolved5
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch16

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 278d2053-a9b9-4415-8907-4756bc2bfe2e · outbound

This paper cites Sharma, Daniel Wen, Owain Evans, and Samuel Marks.Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers.

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

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.107866Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:85cb80aee35eed0dcb7c3da5927769e711207ca3fd86547408035d65e1a158c8

Observation be613e27-fdc8-41af-ace9-a8a80dbf552e · outbound

This paper cites 2026 , eprint=.

Building Better Activation Oracles 2026 , eprint=

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.812356Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:740c1e193383fdcae9dce1c813d215e81ec28839401ed933536aaa4d2603c83c

Observation 1d2a7a0f-ac95-41d6-8c58-2b278c0a250e · outbound

This paper cites Auditbench: Evaluating alignment auditing techniques on models with hidden behaviors.

Building Better Activation Oracles Auditbench: Evaluating alignment auditing techniques on models with hidden behaviors

Reference 3

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T14:24:45.101997Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:b74f297546a3eefb50477a951860d88c1fac21cca40b5229efee3122374d14b6

Observation febac6c5-50fe-46b7-b564-6df8f49498e3 · outbound

This paper cites , title =.

Building Better Activation Oracles , title =

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.080985Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:1c37e489e0fed9f8d5def25bc2e3dd639469d92845f5d5246a89cb465f390cf1

Observation 5a20ca8a-bcd2-43b9-861e-f7f8013b5b8c · outbound

This paper cites Text-to-LoRA: Instant Transformer Adaption.

Building Better Activation Oracles Text-to-LoRA: Instant Transformer Adaption

Reference 5

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T14:24:45.086804Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:3cd4422822dfcabb77c334164125eb99d01783506376331e6f825b5dec4c24be

Observation bd33c2ca-4a41-4e9f-a174-570875092056 · outbound

This paper cites Doc-to-lora: Learning to instantly internalize contexts.

Building Better Activation Oracles Doc-to-lora: Learning to instantly internalize contexts

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T14:24:45.089773Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:4c39fe4703df0d495de59a5f8c8225a975bcdc954055529dfae335967db2a88e

Observation 7dff8e28-640e-4f00-bb94-0d5ddc7a4724 · outbound

This paper cites an unresolved cited work.

Building Better Activation Oracles Unresolved cited work

Reference 7

Resolution
unresolved
raw_fallback, observed 2026-07-08T23:25:42.834136Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:e72602b12d09a0fa321cbb298cbb7193b8e8c0a9807a5997ccca1088ffd31782

Observation 428e3b5d-98ed-4e76-a121-b3dd61425252 · outbound

This paper cites arXiv preprint arXiv:2602.03085 , year =.

Building Better Activation Oracles arXiv preprint arXiv:2602.03085 , year =

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.093310Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a056c8e43cc33d175e6f069335a9c8275dbeb75f266b715078b627fd540f465c

Observation 831c2729-83b3-4c9e-88a5-f6a4148dec7a · outbound

This paper cites Weight space Detection of Backdoors in LoRA Adapters.

Building Better Activation Oracles Weight space Detection of Backdoors in LoRA Adapters

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-06-30T14:24:45.023967Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:dd571dbebe582b45416b60feabe7469c8704fc919faaf0fbda899bde32a6d1be

Observation 51c396f8-5d04-4043-a577-3687b76d70c9 · outbound

This paper cites From poisoned to aware: Fostering backdoor self-awareness in LLMs.

Building Better Activation Oracles From poisoned to aware: Fostering backdoor self-awareness in LLMs

Reference 10

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T14:24:45.104528Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:ea6d25b5614b8d56120d28176d99d607801112dd4f29a2dde90fed2699a2a191

Observation b58fb9c8-01ec-46a3-b5e4-1cf72e6271fe · outbound

This paper cites an unresolved cited work.

Building Better Activation Oracles Unresolved cited work

Reference 11

Resolution
unresolved
raw_fallback, observed 2026-07-08T23:25:42.793840Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:2fc928e28db1b8432a710091dca419c9748728659f7f73bd18a0dd5e3ffc2721

Observation 02eac196-e741-4a04-8aa6-889d094ca3b7 · outbound

This paper cites Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025.

Building Better Activation Oracles Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs , May 2025

Reference 12

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.037962Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:4f78d9436ae83d24f13e1b44253f7337603a282c05d46f54588261aa72740b0b

Observation 91b47082-ed58-45a8-a8c7-c08c37c05970 · outbound

This paper cites 2024 , url =.

Building Better Activation Oracles 2024 , url =

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.827926Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:957024baac062bf2728f9a9ac049192a78d9c805f2d6d752aa83949fe89c502e

Observation 9471c262-45ed-4c94-9b73-d461bbe0346b · outbound

This paper cites Qwen3 Technical Report.

Building Better Activation Oracles Qwen3 Technical Report

Reference 14

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.095967Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:c5892c5d8cf11b63e3c0505699c4a8ab270860a170e233b2152f579884c0bda8

Observation 8cc2b3e4-f3af-4819-a9fb-94ef6ba1397c · outbound

This paper cites The Llama 3 Herd of Models.

Building Better Activation Oracles The Llama 3 Herd of Models

Reference 15

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.017962Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:0b03fb31e5062a3d3f63c0b7e1e19ab68dec1e9be63464d41cf445532d386c9d

Observation dc0a0173-a6be-4f7a-8049-2594f411cbf2 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Building Better Activation Oracles Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 16

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.015327Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:7c9a1a60250e39c065d2422a181198cd909fe0b041a21bc430a46f0affc97f9c

Observation d35716f6-27de-40da-aabe-2b8f9c48db35 · outbound

This paper cites 2025 , eprint =.

Building Better Activation Oracles 2025 , eprint =

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.829738Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:472e53d094bd93e1a7ffb82ba129826ca2b0d1e16c6bc460da08dfce01bf8d4d

Observation a916d5bd-1483-47bd-8ccb-118bbc262e3b · outbound

This paper cites Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs.

Building Better Activation Oracles Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs

Reference 18

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.034937Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:c0e00bb58b26babaa86ca0486e51d491a3410dca9fe18d6f3f3bd5336cc78a0d

Observation f91758f8-0c15-402c-a226-6a12a3927694 · outbound

This paper cites 2025 , month = aug, url =.

Building Better Activation Oracles 2025 , month = aug, url =

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.831236Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:af4a5d1c32caa402d1fed73162e0695fed444c839337fc055c88a5146f6e82be

Observation 49d45cba-f49b-4a55-b3e7-ae521639c81f · outbound

This paper cites Stochastic Parameter Decomposition.

Building Better Activation Oracles Stochastic Parameter Decomposition

Reference 20

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T14:24:45.010507Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:eaae0a000adcf71b680e4ddb8b2a973c89aa06209fcf3688dec07cb339998ba2

Observation bb1f1468-a5e4-4348-9fb6-679d113605bd · outbound

This paper cites an unresolved cited work.

Building Better Activation Oracles Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-07-08T23:25:42.832722Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a16090a0b270b5074cf6170d71ba87762869eecb9de5138fcacddb8875fe497b

Observation 118dd554-19ff-47b8-bfd0-d8ec2e696e8f · outbound

This paper cites 2025 , url =.

Building Better Activation Oracles 2025 , url =

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.835557Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:c796df78d9bbae0e14fb64c7a74c54a13c0bad7aca512be7cfd231ca1def6d4c

Observation cb4e8744-ed10-4025-87d0-d6970409d707 · outbound

This paper cites 2025 , url =.

Building Better Activation Oracles 2025 , url =

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.822498Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:3133253b1fab6208aee14221f2c6085560f428de020f22d5b712930115f9f589

Observation 53bc142d-4f9f-4412-b523-a4bf7bd7ea02 · outbound

This paper cites 2026 , url =.

Building Better Activation Oracles 2026 , url =

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.821077Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:470991fa2bfa269b8b3ea71599d032aa062d0b59cb41ad3b5bae0c9be473fca8

Observation ad8ef9e7-5455-48d2-a8e0-a263f9ab3fd3 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Building Better Activation Oracles Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 25

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.004323Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:eca6d7566a4674868e9e7675c7a97b6dcc5d2163d08d8fa66ee87d0a27438afa

Observation c6bd6321-9851-4be0-a6c8-57c5e62a9413 · outbound

This paper cites Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences , booktitle =.

Building Better Activation Oracles Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences , booktitle =

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.824044Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:7d79fa2fc661a8d71837ba6cd87a9d87b08b23f4c2840ffc11c92330ed3fbbec

Observation 71882747-c6a5-4999-bdb2-b6a74edf1618 · outbound

This paper cites Towards eliciting latent knowledge from LLMs with mechanistic interpretability.

Building Better Activation Oracles Towards eliciting latent knowledge from LLMs with mechanistic interpretability

Reference 27

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.078140Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a136475caf13b4abdcb67166815938479da21af122f9b73f77238d9d066db6da

Observation 07db21e9-43a1-4d92-8260-885d78458711 · outbound

This paper cites arXiv preprint arXiv:2602.07852 , year =.

Building Better Activation Oracles arXiv preprint arXiv:2602.07852 , year =

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:44.987389Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a7c80a6522bd1060c77aac6a0e28ba13b927552bba83b83b0d40c19de58543fb

Observation a1f55673-73d2-42c9-acc7-78021794baa8 · outbound

This paper cites Model Organisms for Emergent Misalignment.

Building Better Activation Oracles Model Organisms for Emergent Misalignment

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.084099Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:1984e599811d324472286530008b5ef38a7cbc9a430c496f11f3c71f9222f5c4

Observation 420b91cd-cbec-446d-9ab8-75b5650ec32f · outbound

This paper cites C-Pack: Packed Resources For General Chinese Embeddings.

Building Better Activation Oracles C-Pack: Packed Resources For General Chinese Embeddings

Reference 30

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:44.990041Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:39ec9d1174b074920195678ec1cbc1db5f5dff202e1f85c5ad5bafdcd73a3183

Observation 73273014-9772-48cb-9989-89f45f41ae03 · outbound

This paper cites W2t: Lora weights already know what they can do.arXiv preprint arXiv:2603.15990, 2026a.

Building Better Activation Oracles W2t: Lora weights already know what they can do.arXiv preprint arXiv:2603.15990, 2026a

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.099383Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:f7f8f6c845c830afa39a7525862ddeb875092dcfbc3ebd369e8b0689e275cf1c

Observation 7d0e4e13-4ab2-4284-9d61-e729237c9f0c · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Building Better Activation Oracles Understanding R1-Zero-Like Training: A Critical Perspective

Reference 32

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.039968Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:983a1588aeb31af4b0184c03b2a0d8740013f2297205b76b2be9acad256861ab

Observation 3102dbf0-819d-480e-bf9a-ed70f4e3c6e5 · outbound

This paper cites MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention.

Building Better Activation Oracles MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 33

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.029320Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:dae9a91030c3b1093ecd06d29e47eb6357a0df1f1bca6578a289d98ab2777224

Observation 6ed427a8-8e8f-44a3-b463-28295223840a · outbound

This paper cites , title =.

Building Better Activation Oracles , title =

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.813719Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:d719d909e2d9a6481244e7025a705e1186b6203b99122ef2b81871ae9869e7a2

Observation c90d85fa-046f-4591-9a19-eb64ebcd9c6e · outbound

This paper cites 2025 , month = dec, url =.

Building Better Activation Oracles 2025 , month = dec, url =

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.808088Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:0207856cbccfd47ecc622495c4961a4f1cee6b9339ee81c9b00f60ba1291c9fe

Observation e6aa215c-959d-42c0-b067-f68895e298c3 · outbound

This paper cites Predictive concept decoders: Training scalable end-to-end interpretability assistants, 2025.

Building Better Activation Oracles Predictive concept decoders: Training scalable end-to-end interpretability assistants, 2025

Reference 36

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T14:24:45.026755Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:be49ed2be89cdfe5726ccfba5010050b2d6eb549962247d5f059514c8b82db9e

Observation 1f16da3a-67c3-4f80-812e-df8fe39ff73f · outbound

This paper cites 2025 , month = nov, googlescholar =.

Building Better Activation Oracles 2025 , month = nov, googlescholar =

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.809557Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:2cbc043d4d45c8bfd174980f7bdede8c8b86a12ad129d2734d394cd108e8e346

Observation 188ce80f-1af5-423c-813a-0cde9be6cc2d · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Building Better Activation Oracles KTO: Model Alignment as Prospect Theoretic Optimization

Reference 38

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:44.998543Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:f968012218a43a57d7461ed35863b5326a158de8c3cfd91dab2e410ea7433033

Observation 713ff32b-6b69-4964-a0ca-8fd4780ec7d6 · outbound

This paper cites The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale.

Building Better Activation Oracles The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Reference 39

Resolution
verified exact
local_arxiv, observed 2026-06-30T14:24:45.007204Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:d9e4f00fba06f28d82fa60a9b656daf040fd2a58f24625966b3648342f43e4df

Observation e6fba0bf-ebc3-4aba-b6c2-d43906daf5b6 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Building Better Activation Oracles LoRA: Low-Rank Adaptation of Large Language Models

Reference 40

Resolution
metadata mismatch
local_arxiv, observed 2026-06-30T14:24:45.042411Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:bece3b41f3bc56291703a0fd1e6cd80cf0278f763578f400db53c2c971cb0294

Observation 555dd98e-dfe1-4c63-92a4-481402fd8f0b · outbound

This paper cites 2026 , eprint=.

Building Better Activation Oracles 2026 , eprint=

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.815190Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:f8257836bebc4b507f1f8cc1bf2d9002dc94510e6efd624d2fbb4add8296cb88

Observation 7e0a82dd-3913-4fdc-a77c-a83bdf3257ab · outbound

This paper cites ICLR, 2025.https://arxiv.org/abs/2412.08686.

Building Better Activation Oracles ICLR, 2025.https://arxiv.org/abs/2412.08686

Reference 42

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.032537Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:f431c1ee6a9a7a9a6337e7c41cc6d7ee1c948ee90115d6e48750a57f7ae0e9c5

Observation d92dddc0-ff4d-4fae-9fae-7dfdfbe94f9e · outbound

This paper cites an unresolved cited work.

Building Better Activation Oracles Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-07-08T23:25:42.792472Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:b0d0fb72af8d4fdce2c8d77c29c51e2c62c5e4690060b228c6b058521e94857a

Observation ac318e72-8f7c-494a-8eda-0db4c377f68e · outbound

This paper cites Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation.

Building Better Activation Oracles Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-06-30T14:24:45.001679Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:945e0a34346fbbc936eebcc86189abb6d69714e52d0fdeb19f386f4fbfe69da6

Observation ecc144b2-7634-4e8a-9e87-c0684d5a4558 · outbound

This paper cites an unresolved cited work.

Building Better Activation Oracles Unresolved cited work

Reference 45

Resolution
unresolved
raw_fallback, observed 2026-07-08T23:25:42.837053Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:362587d95d3e6febe2b360c668346797ae05c8b869ec40953d19ac5839b1a32b

Observation 7812c212-0397-49c8-89fd-f37e982f88b7 · outbound

This paper cites 2026 , howpublished =.

Building Better Activation Oracles 2026 , howpublished =

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.805106Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:c89e9cb3cecf0a9cf32c29b20d75105eb6ef210830f2a3b51661c0dec06da823

Observation 15d96906-b87c-4ba8-86d8-3a6298e38f93 · outbound

This paper cites 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.

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

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.825957Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:dea5af8b19963633264582c08059a488ea1eb1e0bcfc4876cb6cfbb6cd339515

Observation 445b8015-bba5-44d6-a02c-dc014b21a7d3 · outbound

This paper cites 2026 , month = mar, url =.

Building Better Activation Oracles 2026 , month = mar, url =

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.798839Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:1940ba607ab0bc5acf2678f78a6fa214c50d4d684534789ba4b2bfd4c8c44e95

Observation e795f98e-734c-49a5-bd0a-5d1d43427963 · outbound

This paper cites 2026 , month = jan, url =.

Building Better Activation Oracles 2026 , month = jan, url =

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.800386Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:71b02e5edd2b9a67c97b807f43164ba07f206a1c46b5377f4a60f9cfcb18fc54

Observation b3b34893-f7d6-4808-94eb-768913058701 · outbound

This paper cites 2026 , month = mar, url =.

Building Better Activation Oracles 2026 , month = mar, url =

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.801860Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:4d7db4680e40e911ce8d716b5704b524790853a15590dac25d19bec1a2524355

Observation edbdcc38-b62d-47eb-b899-254f925a3e9d · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

Building Better Activation Oracles BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 51

Resolution
verified exact
local_arxiv, observed 2026-06-30T14:24:45.022185Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:c43eaa6b45c75ffecffafae4a1d77856b393068e398b9e7037c05542df133f72

Observation 006c4dd1-1736-46f5-817d-44a6486229ae · outbound

This paper cites 2026 , eprint=.

Building Better Activation Oracles 2026 , eprint=

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.795744Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:26c9f5469be020c308c5279464224f557ec53db9df08d984ce3f1f696d5feea4

Observation 18d20b31-6e46-4dca-ac4e-53a28b9bae9f · outbound

This paper cites 2025 , eprint=.

Building Better Activation Oracles 2025 , eprint=

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.797385Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:90f453b39f9233b7762dfd5d19003aca5afcc737c7677cadc556a372e711ffba

Observation 72a04fbb-dbe3-4f73-8791-dfc8aa5db68e · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.803492Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:d79eade6ddef666f9f9e0e892d36249d5b43fc5137d359cca9fa14a29616469a

Observation 4e4d364b-94e2-4bea-8a38-a6be4c77eb5c · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.806623Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a972c579eb23bfb7e32e0cd4a3767889ffb6b257955293b5cb0fb265a2b6bf77

Observation dc4e40e6-18c2-4e03-9397-2ff8787e114c · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.791078Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:d36b85f2b6b4089f24a794aa6f6ad34285e8697cf66ae2de661bfc30691e7dd2

Observation 004c4359-8777-4b35-9f58-59a2e9b96284 · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.819552Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:f9e57f89cb10fdd2adb12a7b429a4dc20834bdeef6bcb8a36ed47c94e9e6d370

Observation 3997782d-06b5-40c2-8095-6d7d2b8ae6c4 · outbound

This paper cites Towards Weight-Space Interpretation of Low-Rank Adapters for Diffusion Models.

Building Better Activation Oracles Towards Weight-Space Interpretation of Low-Rank Adapters for Diffusion Models

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.789596Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:fa50b2c89a835f4b9f5a367c19599a86b2f62792508c37cac1f3e55488a75c5f

Observation 9ba5b90a-4e14-423e-882d-5fe424b78dfc · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.787947Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:1428a9b50be3aa99a65085d930dfd6dfb32937400861384237ab1c66e384f9b1

Observation f13d280d-de35-4bfc-8e31-d762fc9df236 · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.818079Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:2185237c85f9dd29195fc5b15d8f479488a20d5dfe0c16ea2292123807503804

Observation 97119b9c-6f68-47f1-98dc-ca94376fed8e · outbound

This paper cites 2026 , eprint=.

Building Better Activation Oracles 2026 , eprint=

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.810976Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a588db0cf0ffb57b55b593640bf90cd32accea3b92f6a2d4133c61bae0be88ff

Observation 3a9d4e64-be2f-4da4-8dae-0373ab58d6b2 · outbound

This paper cites 2024 , eprint=.

Building Better Activation Oracles 2024 , eprint=

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-07-08T23:25:42.816637Z

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.

source=arxiv_source observed=2026-06-30T14:19:37.262201Z digest=sha256:a74388235b5d695ccdb6f1a24ac4021bd7a425f6d005b2d0e330a829deaa5757

Pith citing papers

Observation 465e12cc-e794-4a70-985e-9e05d62fed78 · inbound

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations cites this paper.

Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations Building Better Activation Oracles

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T10:02:59.338537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:02:59.338537Z digest=sha256:020cf3999becb6150c327c399b23b9da35d6f334a7ebde896098e87013c1767e