Pith. sign in

Paper Citation Record · LEDGER

Emergent Linear Representations in World Models of Self-Supervised Sequence Models

As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 43 inbound Pith citation observations for arXiv:2309.00941.

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

pith.paper-citation-record.v1
2309.00941 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 43 of 43 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T15:55:23.286662Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

3
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 3f00660a-c05a-4d35-880b-9576977177c2 · inbound

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods cites this paper.

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 105

Resolution
verified exact
arxiv_id, observed 2026-05-17T11:56:11.112344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-05-17T11:56:11.053897Z digest=sha256:22f4540d9a5122c409af92f64a40bbfb3d983d6f92527e07c40dfeed355c22f7

Observation aa5dbfb8-87c1-4f2e-92d5-5171947b60d0 · inbound

Refusal in Language Models Is Mediated by a Single Direction cites this paper.

Refusal in Language Models Is Mediated by a Single Direction Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 164

Resolution
verified exact
arxiv_id, observed 2026-05-13T10:47:56.057846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-05-13T10:47:55.934081Z digest=sha256:3ec1117a4c5017dc964a7f1175f2ee56f0a5093f409c7f33b763c7f25370d869

Observation bef047a8-055d-43d0-8c47-4e2a9750ed40 · inbound

Too Big to Fool: Resisting Deception in Language Models cites this paper.

Too Big to Fool: Resisting Deception in Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-11T15:55:23.286662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T15:55:23.286662Z digest=sha256:d424d8b006f55548cc64ada1e9054e2cb441e8ff1da6e2a80a6041ee629b2c13

Observation 7125de51-1cd4-4e52-8950-2c5bd97590f6 · inbound

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering cites this paper.

LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-11T14:13:24.572849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T14:13:24.572849Z digest=sha256:692cc6c23714cc8baa0b66a5694c5cb9b6395afb86c83212f75a9abef3b60d70

Observation 7ea64003-c981-412f-897a-e17ae5521e8f · inbound

Concept Boundary Vectors cites this paper.

Concept Boundary Vectors Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-11T11:13:38.484985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:13:38.484985Z digest=sha256:023e48fcde8bab045738eeb14e6e5698193eaec6222cda77bcbbf8bd0cd1f85e

Observation f353655c-e3c7-4930-833a-33793bfa0ea6 · inbound

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models cites this paper.

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 2015

Resolution
unresolved
no resolver link, observed 2026-08-11T11:29:14.938467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T11:29:14.938467Z digest=sha256:7a0c7eba9680022d3ab14fa4f92f0469379faf12810d6751f0ea49f1eb3dcf1c

Observation 694b52da-2449-4a49-85d1-611c2155d860 · inbound

ICLR: In-Context Learning of Representations cites this paper.

ICLR: In-Context Learning of Representations Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-10T23:24:01.580066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T23:24:01.580066Z digest=sha256:40367b0422d6f9650ce22da2b411f12eb676524312980e0d7d31b4caef550c67

Observation 7387344f-2b53-4931-b2cc-64a8922bc2cf · inbound

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models cites this paper.

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-10T22:28:32.520502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T22:28:32.520502Z digest=sha256:7d3f285f7dbb11d202aa5fe18501f8768cf88a550bc1901fa44bb0b75d4813f7

Observation b5304e6f-bca5-474f-9cc3-630ae9067eef · inbound

How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons cites this paper.

How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neurons Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-11T00:50:28.425457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T00:50:28.425457Z digest=sha256:3df9944225b65fd4f5a7b237161312aaa3f6eccd088e6994a243653a7b0f87f1

Observation 6086e946-671f-4eda-b162-269ac43f1836 · inbound

Low-Rank Adapting Models for Sparse Autoencoders cites this paper.

Low-Rank Adapting Models for Sparse Autoencoders Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T20:18:31.013489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T20:18:31.013489Z digest=sha256:f6e464fbe48d45f08e91d314813ebdeda7a64117bc9b74e64d23fb38be0fa4be

Observation c2d7b254-970a-4ac9-94af-cb0d55c4bae7 · inbound

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions cites this paper.

Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-09T18:24:40.211172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-09T18:24:40.211172Z digest=sha256:2e431a441431e5a493b30f315e8856c970a51eeb131893e66a100b5b1ed78039

Observation 7b55d802-9926-4402-8e5f-7d467a5a5e89 · inbound

When Do Neural Networks Learn World Models? cites this paper.

When Do Neural Networks Learn World Models? Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.147169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.147169Z digest=sha256:a39cfc1eea8ee8966807e59388bdf1743f63547f021e8a4114eee40566d63c80

Observation 9c413880-f22d-4d1e-a1d0-cc77a3fedf1a · inbound

The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition cites this paper.

The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognition Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 91

Resolution
unresolved
no resolver link, observed 2026-08-10T17:37:45.915875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-10T17:37:45.915875Z digest=sha256:28d207c91da86e2746878f516a3cf896b9cabf21c9d06b8d372ffef324fdf6f9

Observation d40b9a34-3608-482d-b5ea-b4fee4a0d62e · inbound

The Origins of Representation Manifolds in Large Language Models cites this paper.

The Origins of Representation Manifolds in Large Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T14:43:18.021974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T14:43:18.021974Z digest=sha256:a137e5326885b473aeb19e4f0777b2c0d71649900ccd82e3d2ae7a88ced75a2f

Observation cc192d4b-c79b-4d19-b930-07014592f85c · inbound

Understanding the learned look-ahead behavior of chess neural networks cites this paper.

Understanding the learned look-ahead behavior of chess neural networks Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T14:17:47.799785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:17:47.799785Z digest=sha256:f5dc295571552c659cf76b261c4581e379c609bf6ee97346b714d219c9c9af5f

Observation 2e442602-811d-4164-be37-aae9d9a4c077 · inbound

Linear Spatial World Models Emerge in Large Language Models cites this paper.

Linear Spatial World Models Emerge in Large Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:26.052638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:26.052638Z digest=sha256:ffefd6464f257ba32a54f70659dab8585787d489ba5710b860cd95ca04399bb1

Observation 740cb4f6-0837-459f-8fa0-a3c2cf3d6896 · inbound

A Statistical Physics of Language Model Reasoning cites this paper.

A Statistical Physics of Language Model Reasoning Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T10:50:54.169589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T10:50:54.169589Z digest=sha256:67bf36e354facdd802c7091efd4e5f732c672989b3b815a01fba9289eeb441be

Observation a388cbc4-65e3-4248-a348-4ebebf3db623 · inbound

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey cites this paper.

Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-07T10:46:20.154656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T10:46:20.154656Z digest=sha256:84cebaf709c9b838fbc3f506942c23b9aee50e7126839f5a624cb3604f28172e

Observation 5c47d229-72dc-4e54-b230-71e1415343d1 · inbound

Large Language Models and Emergence: A Complex Systems Perspective cites this paper.

Large Language Models and Emergence: A Complex Systems Perspective Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-07T04:57:41.040058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T04:57:41.040058Z digest=sha256:1700829ca151bbf5690dfdd77327a6f41c2a50ea7037ce97cbcab35b4b815c02

Observation d8e17bff-78d6-4c8d-abc4-234872b33d56 · inbound

Model Organisms for Emergent Misalignment cites this paper.

Model Organisms for Emergent Misalignment Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-07T04:07:28.194679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:07:28.194679Z digest=sha256:99a8e28fec54da5854560c3eb7c8b08b40ffaa270ca1024865794661c65f9e02

Observation fee3b4a4-6da7-44de-8224-344f435dc658 · inbound

Convergent Linear Representations of Emergent Misalignment cites this paper.

Convergent Linear Representations of Emergent Misalignment Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T04:09:26.855541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T04:09:26.855541Z digest=sha256:de6ae428ed29dcc7daa00617acb230b5f21132693da48f69cd29185e1595f85e

Observation a4c48831-74c0-4ab2-9716-4f8cd3ae78a1 · inbound

Distinct Computations Emerge From Compositional Curricula in In-Context Learning cites this paper.

Distinct Computations Emerge From Compositional Curricula in In-Context Learning Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T00:41:54.894904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T00:41:54.894904Z digest=sha256:05adee4ec43bf95d58b3f65cce46fe51e0c63969f48f184c8d8773d218141a3c

Observation 509a0729-c1e0-46ab-a923-9a4e81bc055d · inbound

The Geometry of Harmfulness in LLMs through Subconcept Probing cites this paper.

The Geometry of Harmfulness in LLMs through Subconcept Probing Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-06T15:01:47.819681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T15:01:47.819681Z digest=sha256:408cd582987cd35e3434918ffbaaf3edaf1c05bf41ffeceee29326cc67f195f0

Observation 575fcf43-1924-448c-a64e-02a093430aec · inbound

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations cites this paper.

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-06T11:01:15.009218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-06T11:01:15.009218Z digest=sha256:8c16d26585dc6c312bf4cab6549b7848661efd4a838b889a1369c6949c236ea9

Observation fa8db5d3-17e2-430c-a5c2-6ca8a5913e43 · inbound

Towards Atoms of Large Language Models cites this paper.

Towards Atoms of Large Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T15:20:32.180384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T15:20:32.180384Z digest=sha256:04cfa7a4f3d8a83812e226f0395e94dab39072b5bb71b3a538695642920aa458

Observation 55666767-d57f-4334-8c97-2d11836bae3a · inbound

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task cites this paper.

Higher Embedding Dimension Creates a Stronger World Model for a Simple Sorting Task Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T08:56:14.257028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T08:56:14.257028Z digest=sha256:fc8aaf87839df4205549ba9a3c0b8f9eec50f4b529c500f508f55ab8fa7a7fdc

Observation c8e86fc7-8a12-47aa-aae1-5a78966ba4d8 · inbound

Predicting Where Steering Vectors Succeed cites this paper.

Predicting Where Steering Vectors Succeed Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 8

Resolution
verified exact
arxiv_id, observed 2026-05-10T11:00:03.826975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-10T10:59:30.755424Z digest=sha256:583a75db3f24060fce1af78835b81328b6b98e627f14cd244219ba824691719f

Observation 05340939-5c79-4805-a1c8-b24010b6a93e · inbound

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes cites this paper.

Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-11T19:31:10.553775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-05-08T11:42:16.090162Z digest=sha256:00eeb44ec278cda3f227911d8cd463ba61821e1ae95e0eaa1083d2e2bbace231

Observation fcced561-ab36-4422-ab5f-2a862aeebb69 · inbound

Tool Calling is Linearly Readable and Steerable in Language Models cites this paper.

Tool Calling is Linearly Readable and Steerable in Language Models Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 62

Resolution
verified exact
arxiv_id, observed 2026-05-11T03:10:52.673298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-05-11T03:09:11.013914Z digest=sha256:ab10ffb5aa65fb2013a2f21c31a8d63bd4fcc7ae85e2126d4a6fa743df7d3854

Observation 60a25d7d-07af-4ecc-86d3-6ce70228e3c1 · inbound

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions cites this paper.

Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 18

Resolution
metadata mismatch
arxiv_id, observed 2026-05-12T07:16:30.249384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-12T03:31:40.195348Z digest=sha256:441bdf70b9bbbe1d7df622aabea278cd4b337de4b2b199c99f3599a9d9621583

Observation 46399647-6412-41c2-9375-464b7a27c16a · inbound

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 21

Resolution
verified exact
arxiv_id, observed 2026-05-13T05:22:18.847386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-05-13T05:17:34.283917Z digest=sha256:992b40b2f85f49c33cb70818021df1a5907d6fff85bbd0de31be7b80767d65e4

Observation 93d65bcf-d254-4999-8e07-1370d471365f · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 246

Resolution
metadata mismatch
arxiv_id, observed 2026-05-14T20:17:55.562942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-05-14T20:17:01.224864Z digest=sha256:d73ebc92de6ab2be2082f518c61294041e575e2b0b9038d624172f89528f347a

Observation 887951cc-fc69-40d6-bad8-eb2f4fc74d7b · inbound

Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift cites this paper.

Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 31

Resolution
verified exact
arxiv_id, observed 2026-05-19T14:42:37.684579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-05-19T14:37:45.304949Z digest=sha256:f6bd104ea0bdce1bb5a74f0111d96fa0d1ef7453712c4c58edf4fafe36790371

Observation 7525c5af-6a0e-4bc3-9d34-bea755b8333f · inbound

GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving cites this paper.

GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-06-29T22:54:01.534874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-06-29T22:44:39.024780Z digest=sha256:de406b31dde3e4b4b43a7954c10a03284a876e2d36a64f7baece250fa6edfc3d

Observation 4ccf0d14-90fa-4316-b1d9-7486f15f7dc6 · inbound

A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners cites this paper.

A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-07-02T01:46:26.459346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-06-28T11:36:14.896698Z digest=sha256:604cfae2f9ad8da410608116d59f8745a4bb70ba9d1235794ec589a769f214f9

Observation 24c95a46-b8c4-488e-b2ab-619d73d9267f · inbound

The New Associationism: Lessons from Deep Learning cites this paper.

The New Associationism: Lessons from Deep Learning Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 89

Resolution
metadata mismatch
arxiv_id, observed 2026-06-30T18:35:00.211465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=arxiv_source observed=2026-06-30T18:33:24.819008Z digest=sha256:6445da2dac6ec9da3e7b67f904a448307e575db84964e83e3e7b422fce7cd213

Observation 3eeb4439-99ef-4f66-86f2-60f638a08696 · inbound

Investigating The Security of Modern AI and Cloud Infrastructure cites this paper.

Investigating The Security of Modern AI and Cloud Infrastructure Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 102

Resolution
verified exact
arxiv_id, observed 2026-07-04T08:29:42.330969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

source=pdf_text observed=2026-06-26T11:31:39.910784Z digest=sha256:47294c4ef020410daccd3284f38d374fe66d20d7766dd7f89fa99b752ed4f714

Observation fd4f8eb0-375e-4397-aab1-6c786969f6ab · inbound

How are linear representations learned? Exact solutions to the dynamics of abstraction cites this paper.

How are linear representations learned? Exact solutions to the dynamics of abstraction Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-13T06:19:30.027337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-13T06:19:30.027337Z digest=sha256:47c853f8f27929d3c253bcfdedc1d7256df11dfbab3086a1741c59c15cbc2555

Observation 5eea63f0-ffb2-4e6d-9c24-8bcfaddf1b5e · inbound

Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins cites this paper.

Exposure is not manifestation: measurement target and output resolution jointly determine which behavioural-faithfulness evaluator wins Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-02T07:44:07.480279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T07:44:07.480279Z digest=sha256:3f8a2d803c70c7d5f19fba449404a2bfc8a0be2bceda503ce71a21503b3d950d

Observation a6f867a3-47ed-48fb-b57b-18bc59e0d013 · inbound

Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias cites this paper.

Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 55

Resolution
unresolved
no resolver link, observed 2026-07-14T02:33:34.084111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-14T02:33:34.084111Z digest=sha256:5a15282620efea5419bf88f6319a6e1585f47d4c103ecc75cebe3a0869b3cfac

Observation df5dc5b4-399b-4d3d-9142-6db19f2e0a8b · inbound

When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal cites this paper.

When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T07:20:40.064986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T07:20:40.064986Z digest=sha256:8864553ccfeecd600bbf084e3e67318127912a0a2ae1edf6fbc83ccc79d9ed53

Observation f3671bb1-a417-463a-ad44-4b3f8319f5e1 · inbound

Geometry-Guided Constraint Learning for LLM Safety Classification cites this paper.

Geometry-Guided Constraint Learning for LLM Safety Classification Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T11:57:52.868313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T11:57:52.868313Z digest=sha256:8631d0b291f7adc7378f9f2b0ae65833f504331ac20d37610b75e71a58d20fd8

Observation a66ec76f-6e1e-4d73-b0b1-5f9605e8ca97 · inbound

Context Is King: How In-Context Specification Shapes the Geometry of Concepts cites this paper.

Context Is King: How In-Context Specification Shapes the Geometry of Concepts Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-31T15:17:59.808955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T15:17:59.808955Z digest=sha256:5f3fa60343a5a8c1cb41a7bf2e13e596e811db3c8e73cbbdea05389b8c718122