Pith. sign in

Paper Citation Record · LEDGER

Linear Spatial World Models Emerge in Large Language Models

As of 17 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 3 inbound Pith citation observations for arXiv:2506.02996.

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

pith.paper-citation-record.v1
2506.02996 v1

Coverage vector

measured 56 of 56 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:17:28.279479Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T06:23:00.372251Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T09:35:41.083419Z

Reference resolution

56 of 56 outbound references displayed

  • verified exact0
  • verified fuzzy19
  • unresolved33
  • parse uncertain0
  • malformed identifier3
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe8040e9-f56f-4748-a723-f56fa8ae692f · outbound

This paper cites Emergent Abilities of Large Language Models.

Linear Spatial World Models Emerge in Large Language Models Emergent Abilities of Large Language Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:23.887289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:23.887289Z digest=sha256:3f7b76965cb77018321247c5cec591f1abebbad135cbc770e8f1644d21b6d787

Observation 900ceff0-922f-49f6-a4af-7b601291a296 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

Linear Spatial World Models Emerge in Large Language Models Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:23.983815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:23.983815Z digest=sha256:78fe1cf170046b038e8cc24628e05f99497f662de5ac129837427b1a9382e631

Observation c2e138ef-df58-44dd-bccf-73f485c23e2e · outbound

This paper cites World Models.

Linear Spatial World Models Emerge in Large Language Models World Models

Reference 3

Resolution
malformed identifier
no resolver link, observed 2026-08-07T11:17:24.014010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.014010Z digest=sha256:97f5af90d3329dafea76d6d9969bec14b233faee534e8a86f055e651c5ba418d

Observation 303b41fd-c531-4caa-8240-19ae1e43fb24 · outbound

This paper cites World-model interpretability is all we need.AI Alignment Forum, January 2023.

Linear Spatial World Models Emerge in Large Language Models World-model interpretability is all we need.AI Alignment Forum, January 2023

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:32.433703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.067297Z digest=sha256:d286533c7a07b2256a5fa050fcde0b560dba185104c5cca181c1e7e1191f647b

Observation 6cddc234-38e7-42aa-a261-6da7048d212e · outbound

This paper cites an unresolved cited work.

Linear Spatial World Models Emerge in Large Language Models Unresolved cited work

Reference 5

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:17:32.297237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.100136Z digest=sha256:1a1279c0397312c9e6cea4bc6d39c328de0e14a78871bb6ccad765d1fa7e771c

Observation 80618393-1278-41cf-b833-9267df17da5f · outbound

This paper cites Every good regulator of a system must be a model of that system.International journal of systems science, 1(2):89–97, 1970.

Linear Spatial World Models Emerge in Large Language Models Every good regulator of a system must be a model of that system.International journal of systems science, 1(2):89–97, 1970

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:32.089415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.221989Z digest=sha256:12ebd9960b0fe1819a1912e45a7af70728e4c91ed57d8d1392e9b4ab2261c0c8

Observation 05763707-f469-49d2-9404-920fd77263df · outbound

This paper cites Francis and Walter Murray Wonham.

Linear Spatial World Models Emerge in Large Language Models Francis and Walter Murray Wonham

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.259186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.259186Z digest=sha256:9a1480b1a34713ee0d9f323721277ba3bfc1a0302eeb0980b08821f220ff4ab8

Observation f47078de-afc2-4e70-b067-a0470baf38a9 · outbound

This paper cites Robust agents learn causal world models.

Linear Spatial World Models Emerge in Large Language Models Robust agents learn causal world models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.319460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.319460Z digest=sha256:496d63b057007b7181ebe90e1db714f6d628b4b3d0dca8a3bf0c933b0e21f340

Observation b23abb5f-b18f-40e4-847d-9c880f2de4b3 · outbound

This paper cites Climbing towards nlu: On meaning, form, and understanding in the age of data.

Linear Spatial World Models Emerge in Large Language Models Climbing towards nlu: On meaning, form, and understanding in the age of data

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.359201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.359201Z digest=sha256:6af1de0cfd9bce73bf44035b20cfed787997ca1074debc51bf18b9a730b61d25

Observation 18dd5334-7427-48d7-8671-e60e9e088fb1 · outbound

This paper cites Experience Grounds Language.

Linear Spatial World Models Emerge in Large Language Models Experience Grounds Language

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.396251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.396251Z digest=sha256:49e124cda2f2bf46fde850f807b9b77cebb34db0d5f2d11a74a6c74b8395eb89

Observation 1d952693-570e-463b-8a0f-d24c88da0cb8 · outbound

This paper cites Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell.

Linear Spatial World Models Emerge in Large Language Models Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.428797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.428797Z digest=sha256:dc3205e3c7ac65fac254dbe89f1f37bdc3300908f4766a376ac303177da3e697

Observation 0311a1cf-da0e-49d4-9442-e1c45318ff1b · outbound

This paper cites Actually, othello-gpt has a linear emergent world representation.Neel Nanda’s Blog, March 2023.

Linear Spatial World Models Emerge in Large Language Models Actually, othello-gpt has a linear emergent world representation.Neel Nanda’s Blog, March 2023

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.921685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.462040Z digest=sha256:2f570dd4b454ec6d9e3cb1bfb76f292032ac7bb903ba5532441710f399a5c4b6

Observation 6ce25a7c-d292-43d6-ade2-ce597e277226 · outbound

This paper cites On the dangers of stochastic parrots: Can language models be too big? InProceedings of the 2021 ACM conference on fairness, accountability, and transparency, pages 610–623, 2021.

Linear Spatial World Models Emerge in Large Language Models On the dangers of stochastic parrots: Can language models be too big? InProceedings of the 2021 ACM conference on fairness, accountability, and transparency, pages 610–623, 2021

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.495280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.495280Z digest=sha256:bb7467a7fb1e539687c40329088e92324eef0626e29dea6384bbca62daafdbec

Observation 162ca001-d60d-4d69-b8fb-fddcf3abca04 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Linear Spatial World Models Emerge in Large Language Models On the Opportunities and Risks of Foundation Models

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.575321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.575321Z digest=sha256:09707049a12731e1813b1e315b579043415972956d7f30efa276a1b323f51cb5

Observation afa0dbda-d86d-4160-bb8b-5580cba74dbd · outbound

This paper cites The alignment problem from a deep learning perspective, 2023.

Linear Spatial World Models Emerge in Large Language Models The alignment problem from a deep learning perspective, 2023

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.729457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.615721Z digest=sha256:e854989d84863b618b3be0d897cbfb2a4fc8b52898b8923df524038ab66bb527

Observation d546b1c4-b4ff-4f0a-bae2-43062f573083 · outbound

This paper cites World models: The safety perspective.

Linear Spatial World Models Emerge in Large Language Models World models: The safety perspective

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.596464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.655233Z digest=sha256:5a4a43e71693147fab42ec00dee0d1c58c4cc03f53af3c26cf3a7ceca7a6c702

Observation 5e24bd4b-b5fd-4772-9a2e-71c4d34e8e8d · outbound

This paper cites Evaluating the world model implicit in a generative model.Advances in Neural Information Processing Systems, 37:26941–26975, 2024.

Linear Spatial World Models Emerge in Large Language Models Evaluating the world model implicit in a generative model.Advances in Neural Information Processing Systems, 37:26941–26975, 2024

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.439056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.695702Z digest=sha256:9ccdfc1b49872fce98113ac3d133eda83130f1d636e868c96c9b15a83c74d1b5

Observation 10f8caa2-bc31-4205-9390-d07ba9879ea5 · outbound

This paper cites Getting aligned on representational alignment.

Linear Spatial World Models Emerge in Large Language Models Getting aligned on representational alignment

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.754887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.754887Z digest=sha256:859a7268c6cfefa0278137cd478b1e566293302064509c35127d7b6d6d8aaa6c

Observation f18e1bb7-bc8a-402c-9564-89ab99c4ed93 · outbound

This paper cites Toy models of superposition.Transformer Circuits Thread, 2022.

Linear Spatial World Models Emerge in Large Language Models Toy models of superposition.Transformer Circuits Thread, 2022

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.291218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.822385Z digest=sha256:74c5b1abb3112664a89edac3ae34b584e5b5ad7c500f6e019a1a0f305c0f7f70

Observation 193268f3-32e0-410d-a5d8-5cc291844ab6 · outbound

This paper cites Distributed representations: Composition & superposition.Trans- former Circuits Thread, 2023.

Linear Spatial World Models Emerge in Large Language Models Distributed representations: Composition & superposition.Trans- former Circuits Thread, 2023

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.175128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.872112Z digest=sha256:96a814b6e33ed6063ac4227486c95a6d8a78481883e9397b0e49f051c650bc5e

Observation 147e7dd2-086b-4066-88df-9f2aae440515 · outbound

This paper cites Taking features out of superposition with sparse autoencoders.AI Alignment Forum, 2022.

Linear Spatial World Models Emerge in Large Language Models Taking features out of superposition with sparse autoencoders.AI Alignment Forum, 2022

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:31.032398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.921271Z digest=sha256:7af3f251c8f900d7cd4ded4693c58bb34b629c2d16d3e51464a0aa73d6057be1

Observation 78e6cebd-adb5-47e5-b6f9-1e6d50a17fc6 · outbound

This paper cites Mathematical Models of Computation in Superposition.

Linear Spatial World Models Emerge in Large Language Models Mathematical Models of Computation in Superposition

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:24.992598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:24.992598Z digest=sha256:649218612490b9ec31e8481b191e1f108f5999f957065d7ea6e6c8ec7087e2eb

Observation c52cac89-9d5f-48b5-981a-215ef43d9ff2 · outbound

This paper cites an unresolved cited work.

Linear Spatial World Models Emerge in Large Language Models Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.035041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.035041Z digest=sha256:1b23e9fa7f5c431d4837b05b2c3d25ac3b51071603fd92bef65a7ad8a25989db

Observation 74ce2742-e9c2-4902-bccd-0bd7bb6f6a9e · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022.

Linear Spatial World Models Emerge in Large Language Models Probing classifiers: Promises, shortcomings, and advances.Computational Linguistics, 48(1):207–219, 2022

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.108812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.108812Z digest=sha256:502f795cec6e1dd2a257918ea678a3864363bd2b7d1ac4334b5e3c36b2438727

Observation 13bf2520-fea3-42a1-b0c6-4168620243a2 · outbound

This paper cites Probing the probing paradigm: Does probing accuracy entail task relevance?ACL, pages 3363–3377, 2021.

Linear Spatial World Models Emerge in Large Language Models Probing the probing paradigm: Does probing accuracy entail task relevance?ACL, pages 3363–3377, 2021

Reference 26

Resolution
malformed identifier
no resolver link, observed 2026-08-07T11:17:25.161107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.161107Z digest=sha256:b025607e2d1177afd0f714282be2a0c0619f375d49ca18084cb1a3741fe1863d

Observation 159e7901-3906-4bff-adc9-ef5612918072 · outbound

This paper cites Zoom in: An introduction to circuits.Distill, 5(3):e00024–001, 2020.

Linear Spatial World Models Emerge in Large Language Models Zoom in: An introduction to circuits.Distill, 5(3):e00024–001, 2020

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.224495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.224495Z digest=sha256:32eb2eceee759094fc179d9ce1bebf06ea8eb80b823a1ea706f99a5fc87d0d9e

Observation 1304c339-2372-4425-88c9-a60a5335503b · outbound

This paper cites Toward transparent ai: A survey on interpreting the inner structures of deep neural networks.

Linear Spatial World Models Emerge in Large Language Models Toward transparent ai: A survey on interpreting the inner structures of deep neural networks

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.878862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:25.284316Z digest=sha256:1c727635538fe77c1e0c224e013bfa44d624b57663c9761b1d40611741d1efad

Observation f4f3d1f0-c099-46cb-81ea-2ee9c97577c9 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Linear Spatial World Models Emerge in Large Language Models Mechanistic Interpretability for AI Safety -- A Review

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.404532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.404532Z digest=sha256:05f4cef7e2540e6a8701e9272afaea17535a1b2812dc02b4be9068674c153b86

Observation 6a7710c6-2ff1-4add-9ae7-542225f7084b · outbound

This paper cites A comprehensive mechanistic interpretability explainer & glos- sary.Neel Nanda’s Blog, December 2022.

Linear Spatial World Models Emerge in Large Language Models A comprehensive mechanistic interpretability explainer & glos- sary.Neel Nanda’s Blog, December 2022

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.750779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:25.476664Z digest=sha256:f0dd783269217739ac0ebd3cef8f89f3a4b85e8653a69213d8109e11894695eb

Observation 93f48b40-4020-402a-abad-fcec54dd46ff · outbound

This paper cites Steering Language Models With Activation Engineering.

Linear Spatial World Models Emerge in Large Language Models Steering Language Models With Activation Engineering

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.566086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.566086Z digest=sha256:3cef5120746a0f0af2a3c60d112283faffbd6f95197a4aac19a684ce93d57c67

Observation 108e52b0-0780-4005-80b5-8d8ce9aa1c52 · outbound

This paper cites Attribution patching: Activation patching at industrial scale.Neel Nanda’s Blog, February 2023.

Linear Spatial World Models Emerge in Large Language Models Attribution patching: Activation patching at industrial scale.Neel Nanda’s Blog, February 2023

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.592147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:25.662468Z digest=sha256:b1326f31b896b2539898aa0207afbc2debdd365d538e175a6d792395d8d790ec

Observation 06bc19da-8c00-4fe0-9a9f-4d61ef5f904b · outbound

This paper cites Chess as a testbed for language model state tracking.

Linear Spatial World Models Emerge in Large Language Models Chess as a testbed for language model state tracking

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.462866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:25.727420Z digest=sha256:1ae9a4d006b0fabf82593b9bc25dbcc19cfddd6ec856c63033785813c2cea886

Observation 518385f5-3e20-4dca-90d7-550c1e0b9c62 · outbound

This paper cites Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task.

Linear Spatial World Models Emerge in Large Language Models Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.775461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.775461Z digest=sha256:f638b54053a00f7865ca73c995e354eb6e5b12d223fe38fa7421611af10324c1

Observation 00205dca-834e-4186-9a7b-4b2ffd78de6f · outbound

This paper cites Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models.

Linear Spatial World Models Emerge in Large Language Models Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:25.897642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:25.897642Z digest=sha256:d10e8f3b43b374ed64f8112a229eb6805521e9cae51d76cdc5eca801c4ecc231

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

This paper cites Emergent Linear Representations in World Models of Self-Supervised Sequence Models.

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=sha256:2eab2a7bd62d7092da95d3a7539d5233e9107513bdabc66792e2852a27ec6ffd

Observation 8fe309fb-0706-460b-a5bf-ece172981e13 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Linear Spatial World Models Emerge in Large Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:26.179218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:26.179218Z digest=sha256:497712cecb92ee30afe516a9ce681ea9744ac26b8a1e5d4fbc0f01ed873c56a3

Observation b336fd90-3db8-4b96-8ea8-4b41083aa7a8 · outbound

This paper cites Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT.

Linear Spatial World Models Emerge in Large Language Models Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:26.326793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:26.326793Z digest=sha256:8a2f7cbb2648ae37a83e84f6aa8ddad48454179e801582bd058e2b7a24d2052e

Observation 7f31df7a-51a5-4cbb-96fb-d20249ddb841 · outbound

This paper cites Language Models Represent Space and Time.

Linear Spatial World Models Emerge in Large Language Models Language Models Represent Space and Time

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:26.479690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:26.479690Z digest=sha256:26ff5aabd1995f6cd70194804ad3171269081f32544e8af73635cbd246a37039

Observation 794b4c22-70a0-4a8e-90bd-800697b0669b · outbound

This paper cites Language encodes geographical information.Cognitive Science, 33(1):51–73, 2009.

Linear Spatial World Models Emerge in Large Language Models Language encodes geographical information.Cognitive Science, 33(1):51–73, 2009

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.310067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:26.627151Z digest=sha256:90995eee5003f8ab5fbb69a8aa17c3d357cb49ef1f2d82107865f59508ce3391

Observation 595e3771-47b0-4854-b67c-09e062735c7a · outbound

This paper cites Representing spatial structure through maps and language: Lord of the rings encodes the spatial structure of middle earth.Cognitive science, 36(8): 1556–1569, 2012.

Linear Spatial World Models Emerge in Large Language Models Representing spatial structure through maps and language: Lord of the rings encodes the spatial structure of middle earth.Cognitive science, 36(8): 1556–1569, 2012

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.182115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:26.758574Z digest=sha256:450509fc0cf0d83d181dd14b9f7b7714f6acbc0efba8ae57bb2315d0e6fcb33f

Observation b0ddde58-11c3-467e-85a8-430823281626 · outbound

This paper cites Do Language Models Know the Way to Rome?.

Linear Spatial World Models Emerge in Large Language Models Do Language Models Know the Way to Rome?

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:26.901920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:26.901920Z digest=sha256:945d93d85ca7a675024f52c683393ba1398c4aabcfcc87be96c8c5a2a03c62be

Observation e5f7c5ea-a6dc-4635-aa5f-8ca31f3b5a54 · outbound

This paper cites Structured World Representations in Maze-Solving Transformers.

Linear Spatial World Models Emerge in Large Language Models Structured World Representations in Maze-Solving Transformers

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:27.051537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:27.051537Z digest=sha256:f558d1d1ff385e5f821c213a1cecdc801f7c18d7ce20c75a31c3dc290ada302b

Observation fa803672-9cf9-43ed-aef2-f5fe1f329e72 · outbound

This paper cites Mapping language models to grounded conceptual spaces.ICLR,.

Linear Spatial World Models Emerge in Large Language Models Mapping language models to grounded conceptual spaces.ICLR,

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:30.036273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:27.221260Z digest=sha256:f214fd47dff608fe4c2d87316add075ad2d96dc4a16fb486b8c0956a5232f4d6

Observation 6b2e60e3-e9b1-436c-9bb7-ef933e389f62 · outbound

This paper cites The Llama 3 Herd of Models.

Linear Spatial World Models Emerge in Large Language Models The Llama 3 Herd of Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:27.474768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:27.474768Z digest=sha256:30de8c22e1a8427ef0a958ace5e4bb39385dd356c8b438ef486397933308cfdf

Observation 929d5550-991f-4aea-9ac7-9c3daa10b77a · outbound

This paper cites Probing classifiers: Promises, shortcomings, and advances.CoRR, September.

Linear Spatial World Models Emerge in Large Language Models Probing classifiers: Promises, shortcomings, and advances.CoRR, September

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:29.740442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:27.581949Z digest=sha256:895b724a0ce61325771ea037591dcb44bc22e6e3d0abc45f25c6b095a15b33e0

Observation b98c6ff9-776e-4ee1-a19b-a13b7eca0ece · outbound

This paper cites Sparse autoencoders match supervised features for model steering on the ioi task.ICML MI Workshop, June 2024.

Linear Spatial World Models Emerge in Large Language Models Sparse autoencoders match supervised features for model steering on the ioi task.ICML MI Workshop, June 2024

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:29.532243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:27.785734Z digest=sha256:a2eab84704fc9f673abcfdde044132454e058112ed573c8544735d557836a569

Observation 6a13d72c-382f-4309-8718-1b9c8c50ea3c · outbound

This paper cites an unresolved cited work.

Linear Spatial World Models Emerge in Large Language Models Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:17:29.336157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:27.853002Z digest=sha256:944c45cd9bb48a3720eb7ea0cce20d861089b352bbff2c643a68387995e8545f

Observation a89742db-a8b8-4ee6-b2c5-cba54d8426c5 · outbound

This paper cites Improving Activation Steering in Language Models with Mean-Centring.

Linear Spatial World Models Emerge in Large Language Models Improving Activation Steering in Language Models with Mean-Centring

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:27.899636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:27.899636Z digest=sha256:a3a5d8bb54b51fca3fbd93038e69974c1d3221b9377057a704c2d82199ba65e5

Observation 9a11e8db-0b7f-438d-83f8-f8e0ae14d908 · outbound

This paper cites The Platonic Representation Hypothesis.

Linear Spatial World Models Emerge in Large Language Models The Platonic Representation Hypothesis

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:27.980627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:27.980627Z digest=sha256:80d4f9c0573791302b069cf27a8cd69ae2435a68cb62223f71f681c278d4cffd

Observation 6ffa341c-45b3-4e5d-9adc-c2fa387f1b01 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Linear Spatial World Models Emerge in Large Language Models Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:28.039432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:28.039432Z digest=sha256:5b1f2bd0f811c453a012ef7b0d208c0c178729b27471a39e10503c8202da15a2

Observation 434c29f0-bd04-443a-ad44-09fa4bb2f039 · outbound

This paper cites Risks from ai misalignment at different scales, July 2024.

Linear Spatial World Models Emerge in Large Language Models Risks from ai misalignment at different scales, July 2024

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T11:17:29.129512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:28.128217Z digest=sha256:ef1a658e29da461440c5df5ee10d040fee62d2c79a0ae15d68e9e7ce333d7517

Observation d9e06cc5-0ae3-40c8-8558-edfc789ab2cd · outbound

This paper cites Qwen2 Technical Report.

Linear Spatial World Models Emerge in Large Language Models Qwen2 Technical Report

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:28.219897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:28.219897Z digest=sha256:b543dd25e5768f5d6414706dfce2aa6e73b79de4a32418b5136e49d281c678a8

Observation 0ca5db7e-73da-4d38-bdbd-b5ad48ef3a35 · outbound

This paper cites Qwen2.5 Technical Report.

Linear Spatial World Models Emerge in Large Language Models Qwen2.5 Technical Report

Reference 54

Resolution
malformed identifier
no resolver link, observed 2026-08-07T11:17:28.279479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:28.279479Z digest=sha256:6a428a9151abaafce6f30ce564695547d2df23773699b4e6a3fbeea1f202e7cc

Observation 55045c0e-f855-4e75-b090-403d603daa75 · outbound

This paper cites Probing Classifiers: Promises, Shortcomings, and Advances.

Linear Spatial World Models Emerge in Large Language Models Probing Classifiers: Promises, Shortcomings, and Advances

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-07T11:17:27.650715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T11:17:27.650715Z digest=sha256:825be36342915b6b1dc189eeac41669017e4ff56e4f5fee1c18c100a68939d4e

Observation df1fcd02-d569-4ac4-8075-1baf5968c3fa · outbound

This paper cites an unresolved cited work.

Linear Spatial World Models Emerge in Large Language Models Unresolved cited work

Reference 2022

Resolution
unresolved
raw_fallback, observed 2026-08-07T11:17:29.863532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:27.338443Z digest=sha256:00b367837b9c8a5535dd7795180995344fbccb1c745b0921f6e176077f34f613

Observation 115550ee-404a-4bec-ac1b-e27989979144 · outbound

This paper cites From task structures to world models: What do LLMs know?.

Linear Spatial World Models Emerge in Large Language Models From task structures to world models: What do LLMs know?

Reference 2023

Resolution
metadata mismatch
local_arxiv, observed 2026-08-07T11:17:28.563354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T11:17:24.145257Z digest=sha256:50127b12d1c8425055b7950e66f187e7422eac80272feefd1ce8699a48940e93

Pith citing papers

Observation 9519416f-eed8-4037-b369-c89841b0deba · inbound

Cell-Based Representation of Relational Binding in Language Models cites this paper.

Cell-Based Representation of Relational Binding in Language Models Linear Spatial World Models Emerge in Large Language Models

Reference 63

Resolution
verified exact
arxiv_id, observed 2026-05-11T13:06:04.654139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=arxiv_source observed=2026-05-10T02:21:04.591556Z digest=sha256:8c8cc1fa54c9f33fb2b3b85c3854209d9596a53d5d08c75706d66cbe69060383

Observation 0d0fdd4e-6d1a-4a93-9455-6b94734e17c1 · inbound

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models cites this paper.

Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models Linear Spatial World Models Emerge in Large Language Models

Reference 44

Resolution
verified exact
arxiv_id, observed 2026-05-11T05:00:54.983163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-05-11T00:56:06.243890Z digest=sha256:83241dbe249b601c797adb77290608dd3fa968f815db006db8aa667750023a00

Observation ac6cc103-0246-4fde-9cd3-0afc358c5171 · inbound

Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning cites this paper.

Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning Linear Spatial World Models Emerge in Large Language Models

Reference 37

Resolution
verified exact
arxiv_id, observed 2026-07-01T09:35:41.085970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-07-01T06:23:00.372251Z digest=sha256:7858ae295110ebdd6021383d113d44b0ce093f52b5c33ed1b9fffcc6e43a2106