Pith. sign in

Paper Citation Record · LEDGER

Toward universal steering and monitoring of AI models

As of 10 August 2026, this Paper Citation Record lists 100 of 146 outbound references and 7 inbound Pith citation observations for arXiv:2502.03708.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.03708 v2

Coverage vector

measured 100 of 146 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T01:06:10.376745Z

measured 107 of 107 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:45:42.691479Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T16:07:08.191129Z

Reference resolution

100 of 146 outbound references displayed

  • verified exact0
  • verified fuzzy6
  • unresolved93
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ddb1f5cc-de70-42e3-aa99-b3911a919e15 · outbound

This paper cites The Llama 3 Herd of Models.

Toward universal steering and monitoring of AI models The Llama 3 Herd of Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.019790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.019790Z digest=sha256:c3d6d87fc95dabeef83a6ea34e6cfea5cbcc1d1ec2bdb9fd8f34138af39b2f20

Observation 8cfd5ded-d424-4892-b0bc-deb339ae8951 · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Toward universal steering and monitoring of AI models The claude 3 model family: Opus, sonnet, haiku

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.023955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.023955Z digest=sha256:655c9ba236efeb78cc5a7206bca1fbc019cae9f220cb9b3d2ff23339e6883564

Observation ba96e59a-58c7-438e-bce6-f2541f0fb526 · outbound

This paper cites Azaria and T.

Toward universal steering and monitoring of AI models Azaria and T

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.027910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.027910Z digest=sha256:f6e1f7a41d9ca699be60690bb58fffdde66a1c0c17340f0fde551ccfdd5fcc03

Observation a04f7b1c-6a8d-416e-9b26-7c9cc36b9579 · outbound

This paper cites Belinkov.

Toward universal steering and monitoring of AI models Belinkov

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.031650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.031650Z digest=sha256:b9214b1afee6742b42aa92e862f75e71c42a16c6e83fa59b67071a12ecff349f

Observation be9f1f50-3cec-4b72-9558-220ae24185ed · outbound

This paper cites Bricken, A.

Toward universal steering and monitoring of AI models Bricken, A

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.035023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.035023Z digest=sha256:12926d71ad849faeed1074721f9e48f97dbf0b78b0b4b9df9ebc231576086aad

Observation d12d3faa-2fd5-4e68-9ee8-c05ba1e1eccd · outbound

This paper cites Brown, B.

Toward universal steering and monitoring of AI models Brown, B

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.041178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.041178Z digest=sha256:ce4e0b084faa160626ecfaca065063b7ea2c57f67c6adeb33956a4b8329fdc18

Observation b7564afc-7ebd-4aa8-8e34-1ae6f9f5d020 · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Toward universal steering and monitoring of AI models Discovering Latent Knowledge in Language Models Without Supervision

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.044414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.044414Z digest=sha256:bb1f45287c65b81d3600288b00d4d8eb569cc127f6330c55d0f2333dd2d77874

Observation ee429d52-7e7c-46c3-9d20-476f0ff35af0 · outbound

This paper cites Detecting Strategic Deception Using Linear Probes.

Toward universal steering and monitoring of AI models Detecting Strategic Deception Using Linear Probes

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.047723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.047723Z digest=sha256:901565cd4649ca6d069672ca85ad31b23f1535d7c8570ad31888f2ae98e4dfe9

Observation 79f7f3f0-810a-4c15-804a-86af248b3263 · outbound

This paper cites Gottesman and M.

Toward universal steering and monitoring of AI models Gottesman and M

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.051126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.051126Z digest=sha256:6c18535b517881cb528563724f60bb3879e0d662bcd10c747f9a35ecf42b5977

Observation 82ae00c6-24bf-4370-8f7a-f6ff6585e366 · outbound

This paper cites Hackerrank coding challenges.

Toward universal steering and monitoring of AI models Hackerrank coding challenges

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.058675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.058675Z digest=sha256:b7e2da2db3d354e62b0b79af842d80c48a91020a8ac1efe1638aaa99b6f22fc6

Observation 72917922-5105-46f8-a3b5-c41d2c88931a · outbound

This paper cites Huben, H.

Toward universal steering and monitoring of AI models Huben, H

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.062194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.062194Z digest=sha256:3b81f2a7495cd57e921f60890937d9b6aa374aed99cbf2d075963931cf603790

Observation eeaae114-d14d-4102-9499-e8eb1551a6f0 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.065607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.065607Z digest=sha256:12ef51e366479010e7cb755d18e1c39371b204c4c9ceca0c0e0d328c02c75f63

Observation 3d193349-7a3b-48b4-aa7d-7583892615ed · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.069047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.069047Z digest=sha256:cd652a5a915207b13fb4881073249bbd0e2ab9ccb078f3794f30587a8f3491d9

Observation 4039d051-704f-4fc7-8ba9-328cf2f2c1a1 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.072591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.072591Z digest=sha256:f3262b0d3a4f312076b0d05bf510eb72d7662b42ac990e5e33d186303d5cf6b2

Observation ae3518f9-d39e-425b-b1e8-deb9e05d314d · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.076111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.076111Z digest=sha256:855389233116584468b6cdc06b5205291c2ff8f0eb4168a9fe1add204c24fa1f

Observation cce20d05-5e2a-4209-9193-b365dff4191b · outbound

This paper cites Lindsey, A.

Toward universal steering and monitoring of AI models Lindsey, A

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.079658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.079658Z digest=sha256:9f1c339eef754f490e2ed165af64d183f23bacbcca9c3f7032a263e3eedb3890

Observation f68348ff-53bd-40c5-8b27-2d10f8588136 · outbound

This paper cites Mikolov, I.

Toward universal steering and monitoring of AI models Mikolov, I

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.083667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.083667Z digest=sha256:b753f93e65c16ecc3e79220ef69cced6ae1d388e8de8576177a1aa8582fc3f48

Observation 08cb75a2-f1f9-494d-a4b9-c9fa05665eb3 · outbound

This paper cites Mikolov, W.-t.

Toward universal steering and monitoring of AI models Mikolov, W.-t

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.087160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.087160Z digest=sha256:c08ea1aedb222f0ad97c23a9b756194dbc7023270a788fb9b8326f02919c3dce

Observation ac188e44-3375-465c-97bd-7db8bffae687 · outbound

This paper cites Mishra, A.

Toward universal steering and monitoring of AI models Mishra, A

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.090684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.090684Z digest=sha256:15853ea08405fd09af919a1bed547422cc8656870a755b44013d707feb1713ff

Observation 556cd541-dd3b-4720-af62-bbf012fd71ab · outbound

This paper cites Nanda, A.

Toward universal steering and monitoring of AI models Nanda, A

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.094223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.094223Z digest=sha256:0dd4203cee52e4c7dd7b9c8e94981cb480d1582e5b174f0c576f86120afaa142

Observation 05242f16-141c-4b2a-8aa0-6cfd1ae1d330 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.097672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.097672Z digest=sha256:6ce88e2b82b6790779c1b17fec8bde90c9fb1da51d215ea34c52c9d0d2ecf21d

Observation f39d2fe9-8558-4b8d-bf49-8b4d0d0fadc1 · outbound

This paper cites GPT-4o System Card.

Toward universal steering and monitoring of AI models GPT-4o System Card

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.101168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.101168Z digest=sha256:141e06464203e948742e89dfaa37e3059ec33f152b23a505ab15afe0c8880dbf

Observation 50908e73-568a-4db7-b1ad-37324a963e4d · outbound

This paper cites Ouyang, J.

Toward universal steering and monitoring of AI models Ouyang, J

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.104887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.104887Z digest=sha256:9bf09dc355d45334584a21b92f2a2e9d7bedd37d220f18063b61a54081872464

Observation 90359b28-7147-407e-a566-cef230ce3efb · outbound

This paper cites Pedregosa, G.

Toward universal steering and monitoring of AI models Pedregosa, G

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.108571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.108571Z digest=sha256:31b39690b74b32de0cadf92314f8a5531d5d23aea20287872e77e9b5f3dc308c

Observation 27f5e549-5c3d-489a-b7fe-8b5ad748eb37 · outbound

This paper cites Pennington, R.

Toward universal steering and monitoring of AI models Pennington, R

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.112136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.112136Z digest=sha256:1b4683de64db550f165487f409d6ca11ee639badc9ac42971c8a5a8b14151317

Observation e8169d54-8f7e-4683-98fd-952a69399139 · outbound

This paper cites Radhakrishnan, D.

Toward universal steering and monitoring of AI models Radhakrishnan, D

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.115523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.115523Z digest=sha256:35758061884e73ac593b72e5dcc3357adc6cb4533d4766b40af23c4b34efd83f

Observation a1ddb6de-83eb-4df9-9732-de368c45e57a · outbound

This paper cites Lynx: An Open Source Hallucination Evaluation Model.

Toward universal steering and monitoring of AI models Lynx: An Open Source Hallucination Evaluation Model

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.119093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.119093Z digest=sha256:032c0facb1c8ab12dae005010e7159a08d9a947adb1c4975db829c13038d060c

Observation 6970eb5b-a48f-4202-8de4-4e1ffecfd619 · outbound

This paper cites Rimsky, N.

Toward universal steering and monitoring of AI models Rimsky, N

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.122807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.122807Z digest=sha256:9da06b0b2492468e12fa176e04db8b3b394f68efb4b33c55ae3a08ca80a9f9c4

Observation 6ca8f928-b4b8-4a15-ad94-37354a834637 · outbound

This paper cites Smith, S.

Toward universal steering and monitoring of AI models Smith, S

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.126310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.126310Z digest=sha256:04a3d466b85fd40e058b8397ccf43ae0eda0f9103d1735feae01b4646478909f

Observation e5b381c3-c083-4346-b27c-6d7fb604d0b5 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.129529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.129529Z digest=sha256:ab2bfd7cd1f16eb351c745c07f7621dee13ea6221f11a4a2a8d257d2093cab6a

Observation f6440c50-0e67-4a2a-b694-89323c7f1d13 · outbound

This paper cites Sriramanan, S.

Toward universal steering and monitoring of AI models Sriramanan, S

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.132997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.132997Z digest=sha256:d3c1968b5871e784531c52eb00d503ec4efdd95e57c8dea9dc4831de0786be6f

Observation 9e6adcae-04dd-43be-a383-60084dcb3231 · outbound

This paper cites Stolfo, V.

Toward universal steering and monitoring of AI models Stolfo, V

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.136645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.136645Z digest=sha256:78b93c893355d6d24a415ef45e551d4b973f2c660fbe257a3e6b9f8e7480ac9c

Observation e4179b55-eead-4447-9c31-abbe7b3be80b · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.140792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.140792Z digest=sha256:9a2c6f14c34398b25a3bff2fd1f3f8beb0e177e41b254e2b165e8f63e8b6b41b

Observation 4476213b-a42f-4f4b-8307-5ddad6c7bd04 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.144120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.144120Z digest=sha256:5a2eae4cc5eae0bb691fc9f0360cb4bb0ce499bd9289951b4bf986fdbab6722f

Observation c213a571-1f47-4cf7-bf24-0257b25e7655 · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

Toward universal steering and monitoring of AI models AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.147605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.147605Z digest=sha256:502d64b2fcb1fd3c3fe2018bb5fa7d2d856dfda64e7e6bfb679a0768f5886042

Observation 41355242-cdb7-48dd-a4a7-48dd8aeb115f · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 36

Resolution
malformed identifier
doi_truncated, observed 2026-08-09T01:06:10.675920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.151162Z digest=sha256:8b179feeb5e9b7b915ef7e1a41e2e78e2c9fd057be080d3e24616b7f15c7c276

Observation 55b060c6-b8ff-4884-8901-52832195af40 · outbound

This paper cites HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild.

Toward universal steering and monitoring of AI models HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.154321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.154321Z digest=sha256:6125d50479fa1268ee321f7c63948122b382c7d078dbe6113db02e7fd32f0bba

Observation 57bb25a9-1bf8-412d-8ba8-d93631d61917 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Toward universal steering and monitoring of AI models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.157502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.157502Z digest=sha256:13ca4c0c9016ea64464078ab5142cde013666bb8e6cf9ac663515fd513c13e1b

Observation 0bea6f09-7ecc-49eb-9b54-3da10f8a29e2 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Toward universal steering and monitoring of AI models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.160708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.160708Z digest=sha256:62a31d2e1bebff1179105af1da1a5b6b7a2d76c680d07647100fc8e6c6689d5f

Observation 0482fca6-3918-44d5-8296-dab2c45109b0 · outbound

This paper cites We used the 768 labeled prompts from https://huggingface.co/datasets/justin phan3110/harmful_harmless_instructions (corresponding to the test prompts in the provided dataset).

Toward universal steering and monitoring of AI models We used the 768 labeled prompts from https://huggingface.co/datasets/justin phan3110/harmful_harmless_instructions (corresponding to the test prompts in the provided dataset)

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.165262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.165262Z digest=sha256:3a0d347f67ac02fb7a40e2942e8b43a8a760987033f878aa269df2d68e920e56

Observation ce37750b-30c8-470b-8b7e-9898caba6605 · outbound

This paper cites Take on a conservative stance.

Toward universal steering and monitoring of AI models Take on a conservative stance

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.169031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.169031Z digest=sha256:70871179745189f508a6ac44f4ff9a16837de3511b95af6aad3b3da5d4775a2e

Observation 0cdc7481-24e2-4113-877f-d119cb330859 · outbound

This paper cites To learn deception vectors, we use the RolePlaying deception dataset from [8].

Toward universal steering and monitoring of AI models To learn deception vectors, we use the RolePlaying deception dataset from [8]

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.172210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.172210Z digest=sha256:9b3218ca473482a7e8ef614e4a412061df06890657256a4669560755b0f8563b

Observation a49a705b-5738-4937-a653-afe2a9eef3be · outbound

This paper cites Take on the role of a conspiracy theorist.

Toward universal steering and monitoring of AI models Take on the role of a conspiracy theorist

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.175664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.175664Z digest=sha256:245d61e146b8e94640053ac5b85f3aac7468c01790aa69c528e0caca6142f5fb

Observation 0c5275ba-874b-4f80-9110-84d5e12be818 · outbound

This paper cites Take on the role of a major social media influencer.

Toward universal steering and monitoring of AI models Take on the role of a major social media influencer

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.179271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.179271Z digest=sha256:91d5bdcd5913f2dfcd0de6945a19ddbf30da140eb5fd1f14b3d81f8cb55949c2

Observation 29668456-237c-4dfb-9f9b-b69f4150b4ba · outbound

This paper cites Answer in Shakespearean english.

Toward universal steering and monitoring of AI models Answer in Shakespearean english

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.182899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.182899Z digest=sha256:5ca0ce72b2f2ffa9fe9b248fa1cd88851dc9a962e27cd2801a67ac83d9bc7e91

Observation 175d137c-9877-40c6-b9bb-4aa718c3af4c · outbound

This paper cites We used a linear combination of the conspiracy and Shake- spearean english concept vectors (0 .5 weights for both vectors in the combination).

Toward universal steering and monitoring of AI models We used a linear combination of the conspiracy and Shake- spearean english concept vectors (0 .5 weights for both vectors in the combination)

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.186208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.186208Z digest=sha256:c7190f57e65cf8b2774d253f34c6300bd4217e6f8c3152e167318e34c093195a

Observation 72ff8cb4-7110-419e-8064-b79894c86e2f · outbound

This paper cites For social media influencer and conservative leaning, we used a linear combination (0 .5 weight) of the corresponding concept vectors and a control coefficient of ϵ = 0.65.

Toward universal steering and monitoring of AI models For social media influencer and conservative leaning, we used a linear combination (0 .5 weight) of the corresponding concept vectors and a control coefficient of ϵ = 0.65

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.189496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.189496Z digest=sha256:9b02222e46d530e98391939a1e198358a25f5f201d8589b2b123aa3bff16c659

Observation 1f4e6aca-a93a-4710-8ce9-59487264271a · outbound

This paper cites Format your answer as a poem.

Toward universal steering and monitoring of AI models Format your answer as a poem

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.192920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.192920Z digest=sha256:b2338a072c222ce3c5a1db6d1221322f30302fe9b00ec5008d543c32dacfc922

Observation 42ae220b-1385-4112-9e89-d1e34d173e78 · outbound

This paper cites Complete the translation of the following statement in English to Spanish.

Toward universal steering and monitoring of AI models Complete the translation of the following statement in English to Spanish

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.196494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.196494Z digest=sha256:1f195db8a14236b35c6c9e3a96d04492f6b8c5e5d4cc659726f71ab5e6f1b2f5

Observation 6bf2ec0b-f7ec-4f8c-b694-39a473f1e4ce · outbound

This paper cites Complete the translation of the following program [...].

Toward universal steering and monitoring of AI models Complete the translation of the following program [...]

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.199762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.199762Z digest=sha256:733e881b28663affaee7ad9bc3802e00cb17bc021dd094ad33e53a556cc74b53

Observation 2a08671f-4480-437d-865e-564288ea1768 · outbound

This paper cites Personify someone who is terrified of F.

Toward universal steering and monitoring of AI models Personify someone who is terrified of F

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.203522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.203522Z digest=sha256:9a7fd80839e81cc2514e458f0523a9ed6e88433491d87fb5ff8aebd75ad71d98

Observation ddee0b11-e764-427f-a24e-cdea7d5496ec · outbound

This paper cites Take on the role of an expert E.

Toward universal steering and monitoring of AI models Take on the role of an expert E

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.206885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.206885Z digest=sha256:5c1e846c723a781e05079ad4e631d01c540cd0e50b31a385442384ef1897a7dc

Observation 573eb800-2726-4c9b-abeb-748e1e4b1e60 · outbound

This paper cites Take on a M mood.

Toward universal steering and monitoring of AI models Take on a M mood

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.210222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.210222Z digest=sha256:002b3fa3582dc36598a37fe7c83d764dff809f91311a8ceef9f35f908c6fcb1e

Observation b796c3fd-4bfe-4a7c-a0e5-ae999cd65d2d · outbound

This paper cites Personify someone who loves L.

Toward universal steering and monitoring of AI models Personify someone who loves L

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.213515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.213515Z digest=sha256:4e83cadece29387fca5b26433702dfa92a82f9bd6dc626e45a94ac7c87d5a182

Observation 1f66bf9f-21be-4254-8892-e2f3f65cea3a · outbound

This paper cites Take on the role of P.

Toward universal steering and monitoring of AI models Take on the role of P

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.216935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.216935Z digest=sha256:9381dc1a3de543692457dec5dcd362879793c2cb0b4df4c04f6daf745260cc84

Observation 843ea658-56e4-4173-9851-a4bd4e10e318 · outbound

This paper cites What is the scariest thing in the world?.

Toward universal steering and monitoring of AI models What is the scariest thing in the world?

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.221331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.221331Z digest=sha256:8195f83ad5428abddf7b51796ede43d4e777f2fdf851fe7213189942ee76fa40

Observation 31f78370-374c-4400-977d-5bbf185ace9d · outbound

This paper cites Is there anything you secretly hope never happens to you?.

Toward universal steering and monitoring of AI models Is there anything you secretly hope never happens to you?

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.225177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.225177Z digest=sha256:a601e9ea3f400fa6fb659657b4760877b0044352189a3efec761cb1be26aa3eb

Observation 7a7c8082-983c-4e5c-bddb-846a417b673a · outbound

This paper cites What would a movie villain based on your worst fear be like?.

Toward universal steering and monitoring of AI models What would a movie villain based on your worst fear be like?

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.228730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.228730Z digest=sha256:61ce4c665fd2149214b761ef76636131f4cbe877759e06986e891c413a33eb34

Observation 8bac4c66-3004-4c7b-b184-019cb68077e2 · outbound

This paper cites If a fear had to visit you in your sleep, what form would it take?.

Toward universal steering and monitoring of AI models If a fear had to visit you in your sleep, what form would it take?

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.232800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.232800Z digest=sha256:b3dceb7ec03ffb788c154bdbdf12d5af8123f0a928c7fdbe7673baa605e49cec

Observation ff37febe-faa1-4a12-b310-5a11c7b5fea2 · outbound

This paper cites What would a fear-themed amusement park ride, made just for you, be like?.

Toward universal steering and monitoring of AI models What would a fear-themed amusement park ride, made just for you, be like?

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.236979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.236979Z digest=sha256:4fee72b9441928fae288aa22fc6fd541bde734f4b35fba029ce64d909afa28e8

Observation 5999a8a0-1c30-4f0b-917c-9185af9a2797 · outbound

This paper cites What is your favorite subject?.

Toward universal steering and monitoring of AI models What is your favorite subject?

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.240548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.240548Z digest=sha256:ce7725a1f025354e03fe07cc73ba7fd75551e467020e64a985f66029c2525f23

Observation 0f035a37-25d3-4d44-919e-c0697783707c · outbound

This paper cites What’s the kind of problem that makes you forget to eat or sleep?.

Toward universal steering and monitoring of AI models What’s the kind of problem that makes you forget to eat or sleep?

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.243993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.243993Z digest=sha256:6cc0b6d12d8fef1e97ff40e648208776d19311dc1626c9ff5735ad35510cab68

Observation d8fc6ac4-f1bb-4d36-9093-89c5b3dfafc1 · outbound

This paper cites If you had unlimited resources, what would you work on?.

Toward universal steering and monitoring of AI models If you had unlimited resources, what would you work on?

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.247333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.247333Z digest=sha256:431f51afb965c8d3eb3a2847bcd5365c6090ef62a445c60d31ca697016b169bd

Observation 384771ea-0eca-4c6e-9880-59643d05f0ab · outbound

This paper cites What’s a question that got you hooked?.

Toward universal steering and monitoring of AI models What’s a question that got you hooked?

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.254377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.254377Z digest=sha256:aff62d7cb8f34836cddf785f3be64bb877af46ebdb4d559e3ba1eb962b1e6c07

Observation 893541e1-17fb-41ff-b9b7-d4575d924038 · outbound

This paper cites How are you feeling today?.

Toward universal steering and monitoring of AI models How are you feeling today?

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.257919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.257919Z digest=sha256:748d9af73d0db6f939f39cc6d94c37bcf564737a705777c23df1f7db2a20c98f

Observation ceb81b67-2f32-4a25-bd80-8c274a4b9f31 · outbound

This paper cites What’s one sentence that would sum up your current vibe?.

Toward universal steering and monitoring of AI models What’s one sentence that would sum up your current vibe?

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.260906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.260906Z digest=sha256:79f43c9da4f75c558d8aca069496db16c12d6371d653c1d91502b1536dcf2d66

Observation f3856b7a-1814-4723-83f1-d5eff92e7188 · outbound

This paper cites Tell me about your day.

Toward universal steering and monitoring of AI models Tell me about your day

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.263697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.263697Z digest=sha256:720c8e471b030d7c7b0c3388fba6af1ccc972fd211cd4a3f3be7cdc60f644d55

Observation 2c2aefa5-6617-4b62-9a98-280228a32fae · outbound

This paper cites What would a song that describes your current mood be called?.

Toward universal steering and monitoring of AI models What would a song that describes your current mood be called?

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.266676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.266676Z digest=sha256:691ab1f80e5d2e4c01bd03e4116a3d1ec3fe5f25449b2fba71d2a9ee2ef2afb6

Observation 5e276d2e-bd15-4225-8e7b-cb570e825acb · outbound

This paper cites Where would you go if you could go anywhere right now?.

Toward universal steering and monitoring of AI models Where would you go if you could go anywhere right now?

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.270231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.270231Z digest=sha256:805b009f5e76d48ef188ac1bf0474bc20a1a08af4eef968c5ae5079b10a77985

Observation c41fc7bc-a4c0-44e6-9880-f4ba03022114 · outbound

This paper cites What is your favorite place?.

Toward universal steering and monitoring of AI models What is your favorite place?

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.273372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.273372Z digest=sha256:18ef69844083bfb76a535e841b6797db4db06a17c74d31f00f267d390e021830

Observation bd1233bc-4670-4450-b4a4-bc1b717c29a9 · outbound

This paper cites If you could instantly master any skill, what would it be?.

Toward universal steering and monitoring of AI models If you could instantly master any skill, what would it be?

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.276862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.276862Z digest=sha256:f3dfb24e624af605640239df76a4e2ea54a07fdfd837fe006f432541a5ec613f

Observation 75b21460-b4e9-451c-8e04-713447849617 · outbound

This paper cites If you could build a shrine to one place, what would you put inside it?.

Toward universal steering and monitoring of AI models If you could build a shrine to one place, what would you put inside it?

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.279971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.279971Z digest=sha256:a3c8d48e6b380f36306ed108dc227d85709bb9475c69019d7a0593d0d2d2f1f0

Observation 942d9428-7403-4039-9a2d-b27e66610d20 · outbound

This paper cites ”If someone filmed a movie about your life, where would the opening scene be set?.

Toward universal steering and monitoring of AI models ”If someone filmed a movie about your life, where would the opening scene be set?

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.282995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.282995Z digest=sha256:8e092ba4653f773ba293c5164ad6c308e0df6e9de50242d9c59588956b2f6fab

Observation 012a704c-8dc3-4333-8d30-2437882b4fe8 · outbound

This paper cites Where were you the last time you felt completely at peace?.

Toward universal steering and monitoring of AI models Where were you the last time you felt completely at peace?

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.285803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.285803Z digest=sha256:e824700cec850d9551d1d626e0aa4cbce6db8b79ff99cf565520b484e04cce15

Observation b24c868d-681f-4fd8-9e4f-475d516a8f2d · outbound

This paper cites Tell me about your work.

Toward universal steering and monitoring of AI models Tell me about your work

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.288764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.288764Z digest=sha256:43e210873e5d08d6e2220ffdb09805578aa293f6e4c824ce217cc5541c22818c

Observation b21c15bf-17d5-4a87-a048-d2857efd14d7 · outbound

This paper cites What’s something you’ve always been drawn to?.

Toward universal steering and monitoring of AI models What’s something you’ve always been drawn to?

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.292061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.292061Z digest=sha256:9ce4c35440b64c61c6be64a6e5e987510b1e1f16f5924a9968b9e9efcdc9821b

Observation 9cef47d5-4d53-4d86-9ed7-de07dd230a21 · outbound

This paper cites If someone gave you the keys to everything — money, power, influence — what’s the first thing you’d do?.

Toward universal steering and monitoring of AI models If someone gave you the keys to everything — money, power, influence — what’s the first thing you’d do?

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.295497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.295497Z digest=sha256:da51a5ef1f8b338edd234b5c14a157f7ef7db2f59b0e4bd3f3924a4a605e8e89

Observation 75e0c42f-2b2a-4756-ac63-0e01b8c0995e · outbound

This paper cites Describe your work in a way a 5-year-old can understand.

Toward universal steering and monitoring of AI models Describe your work in a way a 5-year-old can understand

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.299176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.299176Z digest=sha256:4b7a6c369c75a1a73229a12b2e5c1906cace13066789500e99e291631eb635e5

Observation 162c9d90-dfaa-4f40-a326-0fb5c940c8da · outbound

This paper cites If you could teach everyone one thing, what would it be?.

Toward universal steering and monitoring of AI models If you could teach everyone one thing, what would it be?

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.302628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.302628Z digest=sha256:c28e062d7cb8d418c97a088d334e5f339d8309fe47692727b9c9f5c31faa9377

Observation c0441286-0442-445f-9310-0f2c1c41bf8d · outbound

This paper cites Evaluation criteria:.

Toward universal steering and monitoring of AI models Evaluation criteria:

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.306637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.306637Z digest=sha256:922f67f7095a38ee3bc6104c30e4e404fcba3d39a54fe05e6d5149094ac28c5c

Observation 0c6dc9d4-b8aa-4866-95e7-4956ba0cd53f · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.310158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.310158Z digest=sha256:e5abe5639c897c57c11399ac9682ea93063f98a7b165dda85f1e3f4deb01a293

Observation f3afc3ae-13c4-48a8-91b5-8650772aa560 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.313568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.313568Z digest=sha256:0ae2f0ab3dde8410efcdff4047d24a2348672f5e74a7b01a17da82d1b5df5f20

Observation ac9f4c9b-c047-4ea0-8b81-26c7480f1440 · outbound

This paper cites Output format:.

Toward universal steering and monitoring of AI models Output format:

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-09T01:06:10.316794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T01:06:10.316794Z digest=sha256:f4de07ef903fa9221531f3629f3debf0eb31524e01263d54492e108a70978d46

Observation 24aba150-f321-42cf-9609-a7af425da36c · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 87

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.466955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.320151Z digest=sha256:34b54c252f67d1d1a6fe4b331dfe67a779aed65df43afbf9fef162df70f43339

Observation d8fb4df1-572d-4ff1-9ae5-228295b8f74b · outbound

This paper cites Here are 5 examples:.

Toward universal steering and monitoring of AI models Here are 5 examples:

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T01:06:11.457389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.323484Z digest=sha256:b550ab78d2e2cca6dc2e1ae202d240703237c581680e977288d82d5e44bcb215

Observation 9a511eb6-ce03-467e-a77a-91bae0365aa0 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 89

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.447011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.326920Z digest=sha256:254f80cf768fea5914470c5ab809ae6d5f3325e04b0526f345965e96a0e5be2e

Observation b23bac1b-d3d1-4187-a831-81713ec29523 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 90

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.436689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.330497Z digest=sha256:d790c24049d0c6ac1cc0e81b96d566c12a644cb9c81f7d13a2653c8ef6d1d6ec

Observation 158cd294-ef67-4455-8b5c-c309df0cea0c · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 91

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.426258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.334391Z digest=sha256:606494f721e562115c3c29d29555370c6446d82287499b65a913bd05b42f4fd9

Observation 91d5c4ab-a105-4bf1-9c06-6d3b6a43b195 · outbound

This paper cites I think The Scariest thing is.

Toward universal steering and monitoring of AI models I think The Scariest thing is

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T01:06:11.416396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.338201Z digest=sha256:bf1cb309d6590913e268722b2942cb455884cef72d2e725a3318a6ef4bddcd09

Observation cc73dcaf-1933-46f3-83fa-1c3d3308d171 · outbound

This paper cites BIG WORD BAD? Answer in 3 words.” Evaluation Output: Score: 0 Explanation: The response mentions the fear but is nonsensical.

Toward universal steering and monitoring of AI models BIG WORD BAD? Answer in 3 words.” Evaluation Output: Score: 0 Explanation: The response mentions the fear but is nonsensical

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T01:06:11.405653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.341552Z digest=sha256:c36adba69578616eb652d5f3c7e5018f92be777a668b3a5f7f4c197e068cc928

Observation 71c23515-f9b8-43a4-b66c-f4dbf54a58c5 · outbound

This paper cites First data are randomly grouped into pairs ( a(i), a(j)) where a(i) ∈ S0 and a(j) ∈ S1.

Toward universal steering and monitoring of AI models First data are randomly grouped into pairs ( a(i), a(j)) where a(i) ∈ S0 and a(j) ∈ S1

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T01:06:11.395121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.345355Z digest=sha256:6f0ace2d21eb2bc89f655814fc853a19fe517c74849f8bb851762fca13a6c817

Observation 4d0202cd-5960-4ec8-8ae1-9c8d2d701ffe · outbound

This paper cites The concept vector v (prior to orientation using Pearson correlation) is given as: v = 1 |S1| X a∈S1 a − 1 |S0| X a′∈S0 a′.

Toward universal steering and monitoring of AI models The concept vector v (prior to orientation using Pearson correlation) is given as: v = 1 |S1| X a∈S1 a − 1 |S0| X a′∈S0 a′

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T01:06:11.384791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.348779Z digest=sha256:da1a6b516c1994eb26f49116c20df9c5226235d1d6477a14b48dfb4fe6eab46f

Observation 5b7f6579-7168-45db-9d4f-fa11180e44bd · outbound

This paper cites liblinear.

Toward universal steering and monitoring of AI models liblinear

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T01:06:11.374471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.352200Z digest=sha256:a4465321fe34b26a905d23a859e6e3035414ce8ac719717339dede03263f9be3

Observation d2204d44-08c7-4b93-a8ec-38ff54f90784 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 97

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.364349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.355742Z digest=sha256:b1c2cf0f48bc9adace28df400f6133b7e03d8a00f365567382d6be91abbda2a8

Observation 5b0ddcac-a863-4920-acb6-bf20591bca4a · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 98

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.354264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.359157Z digest=sha256:c201e5ea8efb3fbbf81fece4cfb1e569932c54aaba74a1da23d0d8b35af33260

Observation f5bd491a-fba1-444f-a8f7-2b0fa889e14a · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 99

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.344015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.362886Z digest=sha256:6356d0634978867680aeab035a41d6d590e0e7c3151c8ef57ec591118828a055

Observation b1c650fd-0cc6-4dde-9996-b99f7420eb57 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 100

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.332828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.366322Z digest=sha256:c873c43f2d978aa6db20ddb2bfa7373a6f4d12af8e75d641e0b69b1276500bf7

Observation 54a34785-f039-40a0-872a-3a5be68d2259 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 101

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.322502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.369785Z digest=sha256:7974cc0d5717676ae1264173acd8ae83c69a686c68f2b3367e8662d66a913fd4

Observation 9c090ff2-dd1d-452f-bafe-f823207fb9d8 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 102

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.312302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.373245Z digest=sha256:a3b441c6877dd4ebc7418c3a32417755ca1bea570201773b760120be775f4b16

Observation d25a02d9-1f81-40a1-a1d9-194a4adcf145 · outbound

This paper cites an unresolved cited work.

Toward universal steering and monitoring of AI models Unresolved cited work

Reference 103

Resolution
unresolved
raw_fallback, observed 2026-08-09T01:06:11.301547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T01:06:10.376745Z digest=sha256:f08c22d9e358a9973f8c58d74b0fb570831582e208465e652d1554a5e960ee96

Pith citing papers

Observation a07c02d3-86f8-4ddc-a234-f26edc18ed46 · inbound

Resa: Transparent Reasoning Models via SAEs cites this paper.

Resa: Transparent Reasoning Models via SAEs Toward universal steering and monitoring of AI models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T04:45:42.691479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:45:42.691479Z digest=sha256:04629efc9d9456274b3d96c9eb67603aacb0f35102530c299da737dedecdf699

Observation 72763c8e-e5cf-4e8f-9e15-48f13c44e7d0 · inbound

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations cites this paper.

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations Toward universal steering and monitoring of AI models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-06T19:31:18.912515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T19:31:18.912515Z digest=sha256:93fde5f58053ae916713f508b309684dd73f57ba1b7b9d5a687e6907059695b2

Observation 375ec137-643e-4a7e-8fc0-1e0298d8a21a · inbound

xRFM: Accurate, scalable, and interpretable feature learning models for tabular data cites this paper.

xRFM: Accurate, scalable, and interpretable feature learning models for tabular data Toward universal steering and monitoring of AI models

Reference 6

Resolution
verified exact
arxiv_id, observed 2026-05-18T23:11:53.937668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-18T23:07:26.869930Z digest=sha256:2f745405e0c90fd9d2bccff5e32a84e3c7c988affaafcb3e2ba8f0a7844c8e6f

Observation bd418a8b-dd7b-449d-a04d-b71529e8a7f6 · inbound

Can LLMs Lie? Investigation beyond Hallucination cites this paper.

Can LLMs Lie? Investigation beyond Hallucination Toward universal steering and monitoring of AI models

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-05T10:55:31.196148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T10:55:31.196148Z digest=sha256:0469695e51296bf4ba7b9e8f1e9446e9b3ecc2ab320056bcc0d11642368dd881

Observation 1f94177a-cf88-476d-8e00-537d3b51ac7e · inbound

From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents cites this paper.

From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents Toward universal steering and monitoring of AI models

Reference 6

Resolution
verified exact
arxiv_id, observed 2026-05-14T22:33:10.418094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-05-14T22:33:07.363903Z digest=sha256:96a9462237986ec5e5eb4bfef8813bce105dddc578cc53c8c07c3bc31c058a0a

Observation c333f1d8-e01b-441b-a5aa-b6301ee9fbb5 · inbound

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection cites this paper.

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection Toward universal steering and monitoring of AI models

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-06-29T14:03:29.910475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-29T13:53:27.306664Z digest=sha256:f8e8d41efeecd241ed4101fcf55be0dc94b2c0445a5e4d5ebbe4335419e0ae07

Observation 04d420b4-6eaa-4b4d-852c-80852e9f932d · inbound

K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks cites this paper.

K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks Toward universal steering and monitoring of AI models

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-07-02T16:07:08.192626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-07-02T16:07:05.189001Z digest=sha256:4af8ac4ebca32f3f28d639ece76ffa9eb02f9d27707c56cf20f0d0603df6e99d