Pith. sign in

Paper Citation Record · LEDGER

When Do Neural Networks Learn World Models?

As of 8 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 1 inbound Pith citation observation for arXiv:2502.09297.

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

pith.paper-citation-record.v1
2502.09297 v5

Coverage vector

measured 95 of 95 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T22:12:50.278134Z

measured 96 of 96 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T01:13:11.483599Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T20:38:55.959708Z

Reference resolution

95 of 95 outbound references displayed

  • verified exact2
  • verified fuzzy51
  • unresolved42
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b3c4a923-7ae7-4449-b595-054fb0bf1cf6 · outbound

This paper cites write newline.

When Do Neural Networks Learn World Models? write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.898591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.898591Z digest=sha256:7db98583a1a44b2e6ec94474b238f68223f8bfa2a90a0f20d1cc5b4496ef65cf

Observation 324013d2-b817-4747-ae34-1047fb26e0ca · outbound

This paper cites Generalization on the unseen, logic reasoning and degree curriculum.

When Do Neural Networks Learn World Models? Generalization on the unseen, logic reasoning and degree curriculum

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.904503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.904503Z digest=sha256:27dd0a8fa5b05ea6ed12962a8d6252325264dbbaf4c5c0073b1f95d85867ff38

Observation cf025ddc-bea3-4353-a8e9-7385ee01b7e9 · outbound

This paper cites Interventional causal representation learning.

When Do Neural Networks Learn World Models? Interventional causal representation learning

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.908933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.908933Z digest=sha256:ffa64973e34fdb859c4a6f8d1c02d9f34a4c8191dc314edb0bc17bf8996c7272

Observation 027e45ae-e114-4713-b6d0-c2d904f2fa6f · outbound

This paper cites and Li, Y.

When Do Neural Networks Learn World Models? and Li, Y

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.913105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.913105Z digest=sha256:b9bcf2663ed1f36654cabb04ef28f751048db9632ea72e3e46af3aea9dedeb8e

Observation c4597850-61a1-44f1-823e-9cdd86b2d903 · outbound

This paper cites V., Pillaud-Vivien, L., and Flammarion, N.

When Do Neural Networks Learn World Models? V., Pillaud-Vivien, L., and Flammarion, N

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.917187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.917187Z digest=sha256:b08718c71b2d05c0e22e765f752ddd61a6b9fd9d1a674eef3753f49200985eb2

Observation ccb3f2de-8324-4560-96bb-053d86448332 · outbound

This paper cites Exploring length generalization in large language models.

When Do Neural Networks Learn World Models? Exploring length generalization in large language models

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.921275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.921275Z digest=sha256:6a6f8cfd9a94fbf7674131a38a3af07a0115680208f9bcb2271bb82546773ecb

Observation 9555662b-8e41-4491-a3ad-a5df4b31bed8 · outbound

This paper cites Invariant Risk Minimization.

When Do Neural Networks Learn World Models? Invariant Risk Minimization

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.925365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.925365Z digest=sha256:5a0dd1e2fdaaeb596d26d23a506a63c2a28c1d4f7733b993fc95b3efad496f0c

Observation a9ba07bd-3734-410a-be3b-713cde8ed9a2 · outbound

This paper cites A theoretical analysis of contrastive unsupervised representation learning.

When Do Neural Networks Learn World Models? A theoretical analysis of contrastive unsupervised representation learning

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.930254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.930254Z digest=sha256:e6fcab78e280dcd71d7208181864d7a0899abbbe7fa03cf97e7760b94c0114cc

Observation 18ca27b8-30d6-4f23-8440-e4fec2e649b8 · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.934349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.934349Z digest=sha256:87fedc86ffcce3ce9562039214f019e2c708771b6034a40341a3d99477ed43d8

Observation f569303d-eeaa-4229-8fa4-6a6f9dc49606 · outbound

This paper cites L., Foster, D.

When Do Neural Networks Learn World Models? L., Foster, D

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.938639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.938639Z digest=sha256:5d7018d1b3572ac390f6499d90cb290780d9f52440c46ab8f52cefa1b76afd2e

Observation e1624327-b057-4ea5-a1ca-3bf78d351c9b · outbound

This paper cites L., Long, P.

When Do Neural Networks Learn World Models? L., Long, P

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.942469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.942469Z digest=sha256:abd9d37a054893d04812fb99946056c57c3f8873e712570ef062e8f0bde43d5b

Observation bd61ba73-c495-4874-978c-f51a93bb8332 · outbound

This paper cites M., Gebru, T., McMillan-Major, A., and Shmitchell, S.

When Do Neural Networks Learn World Models? M., Gebru, T., McMillan-Major, A., and Shmitchell, S

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.946350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.946350Z digest=sha256:d8f61d598da6a1a05e0ea699ec7556b9dba4ab4680ccee575897436938c91ded

Observation 2b20971b-59a5-4820-90d3-9e8d3406bf53 · outbound

This paper cites Representation learning: A review and new perspectives.

When Do Neural Networks Learn World Models? Representation learning: A review and new perspectives

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.950312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.950312Z digest=sha256:edb12ec8d4106e83a3d10194e4e9c85418572a4b5f9ec70f552593feaa4fcb35

Observation 027e513c-07d8-4e5d-8a5e-4c3a248950c4 · outbound

This paper cites fail to learn ``b is a.

When Do Neural Networks Learn World Models? fail to learn ``b is a

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.954065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.954065Z digest=sha256:d3d0059eec78c840d2b60174457d96b3ad65d4fcab8accf54bd1e45bb4a6b45a

Observation 651f7b2d-6cce-49cd-a35d-cc05da07108b · outbound

This paper cites Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions.

When Do Neural Networks Learn World Models? Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.957609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.957609Z digest=sha256:08e77e39f8f74a44b1389262a847625f63902b6b7e99f64ff8a112167940c177

Observation 6e0fc7f8-41b2-4f4f-9cd3-a48ff9e18fdc · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

When Do Neural Networks Learn World Models? Towards monosemanticity: Decomposing language models with dictionary learning

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.962139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.962139Z digest=sha256:0c6e0cb4ee6490826821731c9aa96c1ba739a1a5e883c6ac9fe98b953361218b

Observation 6205c7eb-3770-4a57-beb8-eb9a7dc38ce1 · outbound

This paper cites Video generation models as world simulators, 2024.

When Do Neural Networks Learn World Models? Video generation models as world simulators, 2024

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:49.965870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:49.965870Z digest=sha256:ec0d068c5cd77eb1322ff92f3d95ba2db492341b0bec47333bf7535c1955aba6

Observation 81f8f6ff-baec-490d-9c74-07595a22c44d · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 18

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:12:51.484143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.969809Z digest=sha256:2c6837da7788c35760e904c10f2f7ff4b521d6d9e524776d0f08f686e1f38df5

Observation 23111ca0-3328-4835-b79e-4975c07cb657 · outbound

This paper cites and Sudijono, T.

When Do Neural Networks Learn World Models? and Sudijono, T

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-08-07T22:12:50.742168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.973561Z digest=sha256:0e75fd94fbc0568adb00785bd7d499d76eac17742e913fbaab3a4d442334bcfb

Observation 0fdeaba2-0fd7-4e6e-99b8-c3232bfd77d1 · outbound

This paper cites Implicit bias of gradient descent for wide two-layer neural networks trained with the logistic loss.

When Do Neural Networks Learn World Models? Implicit bias of gradient descent for wide two-layer neural networks trained with the logistic loss

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.471050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.977266Z digest=sha256:1f849114baffed3f616b84d73bce2c8bf3b6181212895b0cda860c1e54ee844a

Observation f9d1dcfe-4a50-49e9-88cd-6cfcb761fd56 · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 21

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:12:51.458513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.980848Z digest=sha256:56964d284da78df06e10f6d79ccd7d2223205412949c39cef9777335c2d296ba

Observation b2975aa4-1285-45e4-9310-9b3fb8afa323 · outbound

This paper cites Q., and Louis, A.

When Do Neural Networks Learn World Models? Q., and Louis, A

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.447850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.985044Z digest=sha256:5e23130d6666cac182dfdd755b940d37640bed707fc09c6e7d63c529430b75aa

Observation 5d026e3e-52bc-4b6f-8453-598850233a20 · outbound

This paper cites An introduction to latent variable models.

When Do Neural Networks Learn World Models? An introduction to latent variable models

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.437078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.988801Z digest=sha256:cf48110e966006a4dcb59339d748e2c628f1fbd1da43cd6b766d4c4f6abbcfa7

Observation 4f9669c4-fd26-4da4-826e-8a103282b660 · outbound

This paper cites J., Nagai, Y., Taniguchi, T., Gomi, H., and Tenenbaum, J.

When Do Neural Networks Learn World Models? J., Nagai, Y., Taniguchi, T., Gomi, H., and Tenenbaum, J

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.425459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.992380Z digest=sha256:1847c1ebeffbeadf63a7e1cb12c2ae995ffecc13d378fca64f5e4d2e9bf76d88

Observation e00d8db7-8ccf-423a-bf02-57ed19b69658 · outbound

This paper cites On the approximate realization of continuous mappings by neural networks.

When Do Neural Networks Learn World Models? On the approximate realization of continuous mappings by neural networks

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.414924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:49.996138Z digest=sha256:1d4ae1bc07945b7bde8010f2e5e657bd47155786721c3bf909f353b1e95c6630

Observation 0434e89f-ff80-485e-b5ab-40c1380b4ce3 · outbound

This paper cites A., and Brendel, W.

When Do Neural Networks Learn World Models? A., and Brendel, W

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.404072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.000167Z digest=sha256:b73d9be1aa57674241ee5b12062d2ebfea9a4b77d04a021dcaf3ef062e727618

Observation 6de8f12d-cb44-47f3-9775-b6c5d410df9c · outbound

This paper cites A Survey of Quantization Methods for Efficient Neural Network Inference.

When Do Neural Networks Learn World Models? A Survey of Quantization Methods for Efficient Neural Network Inference

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.004131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.004131Z digest=sha256:412cc163370362f3348cba2618255d63ed5083727b8f55e2184c86025b9dad38

Observation 565f5320-396a-476c-b25b-801ddf0a0a10 · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:12:51.391614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.008325Z digest=sha256:2c911690d93972f61f6d407c026277f2139c17818a0dca63c98d1426a9cd71ad

Observation 2daaa960-61e1-4fd6-8eb9-80278208fb19 · outbound

This paper cites Inductive Biases for Deep Learning of Higher-Level Cognition.

When Do Neural Networks Learn World Models? Inductive Biases for Deep Learning of Higher-Level Cognition

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.012673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.012673Z digest=sha256:38d0c325259409ff26ea8d1a37d597d62b51e186a89a06c722fde496a64ac9b3

Observation 253af9c5-fe3b-4c00-b6b5-2a186ed3dfad · outbound

This paper cites Characterizing implicit bias in terms of optimization geometry.

When Do Neural Networks Learn World Models? Characterizing implicit bias in terms of optimization geometry

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.379350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.017385Z digest=sha256:3a7d8052d15e75a220c464212005ff040634022567a88d25682e7eeffb6e8fd2

Observation 5a00f6a6-e471-4af4-8dd1-0946aa292b97 · outbound

This paper cites D., Soudry, D., and Srebro, N.

When Do Neural Networks Learn World Models? D., Soudry, D., and Srebro, N

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.366609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.021248Z digest=sha256:e2a30e8617b8a5079bef7c91332e18cf426c4a3bf8fb96379b56e35da3d41344

Observation af77a08a-f0ed-447d-b72f-71283a79f1b6 · outbound

This paper cites and Tegmark, M.

When Do Neural Networks Learn World Models? and Tegmark, M

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.355575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.025070Z digest=sha256:bedbe214a2992806f0b1b53bca65c2d49e0d391dbef0ffe5b611c604d6f3052c

Observation 56212e73-2742-45ad-a217-78db692550fe · outbound

This paper cites World Models.

When Do Neural Networks Learn World Models? World Models

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.028734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.028734Z digest=sha256:1e6fb2e7753b81f44e2e11e431cab3f31146065f7d418f519bfa87eddcbe3eda

Observation 07313a32-312c-42d1-909f-2945eb1d8d69 · outbound

This paper cites Masked autoencoders are scalable vision learners.

When Do Neural Networks Learn World Models? Masked autoencoders are scalable vision learners

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.343765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.033145Z digest=sha256:7a9ebf6ce32c5a84b019ecbb950e7107882dde0daaf17c5b4119593a00a79b7a

Observation d727f540-3a4d-4be9-a03a-22920e70273e · outbound

This paper cites An Overview of Catastrophic AI Risks.

When Do Neural Networks Learn World Models? An Overview of Catastrophic AI Risks

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.037040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.037040Z digest=sha256:8d7bed24fb07c33b3ae18b8d77830c4097373618fd6ae186b43dc86083b3667b

Observation 8d07a6a0-8b8c-4416-a619-b7d42f506ae1 · outbound

This paper cites Multilayer feedforward networks are universal approximators.

When Do Neural Networks Learn World Models? Multilayer feedforward networks are universal approximators

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.331038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.041310Z digest=sha256:98aaea3327f0a33c6796ab7bff57098f5eb86b480318a7e7c7e5c025c18fac8c

Observation b214df8c-250d-4ff7-be1e-f5db1959fe37 · outbound

This paper cites The low-rank simplicity bias in deep networks.

When Do Neural Networks Learn World Models? The low-rank simplicity bias in deep networks

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.045189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.045189Z digest=sha256:38fa07af4e2bfda49b4f0eeef833a3ca0d48896317d8e242e6b6d94d3bc41280

Observation 524469f1-7e19-47e9-829d-851e5b847ef7 · outbound

This paper cites The Platonic representation hypothesis.

When Do Neural Networks Learn World Models? The Platonic representation hypothesis

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.311716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.048900Z digest=sha256:ff282cf4cbef19024b600f36b91df031876a8ef0f3dcc657d216b9013e7d1a8e

Observation 98fee8e2-6723-4cf6-a032-301ff4bfd111 · outbound

This paper cites and Pajunen, P.

When Do Neural Networks Learn World Models? and Pajunen, P

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.300868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.052538Z digest=sha256:e98ccb4df37f8ae75c2a8d844f71443e723c956f907d08f38bf394e090034fae

Observation e5238713-1f81-46a9-bf45-42f5aa6cb62a · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:12:51.289481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.056584Z digest=sha256:1f89366ed7bd9cd10668176cf1e393e45e4ae402e4dcd6783a138c2b0d873a5b

Observation a66ec036-12f5-4770-9bfb-02158e6379fe · outbound

This paper cites Neural tangent kernel: Convergence and generalization in neural networks.

When Do Neural Networks Learn World Models? Neural tangent kernel: Convergence and generalization in neural networks

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.277345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.060426Z digest=sha256:31b8bec193dae9e8159f62f63e732d4217bb3578b1e9d0e5034870bbb20b83aa

Observation 53f8925b-d809-4f7f-a6eb-9195f599ebd0 · outbound

This paper cites Low -resource.

When Do Neural Networks Learn World Models? Low -resource

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.264673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.065175Z digest=sha256:fc0a4dd17294e119ff99b8bbe2464bceb615582f92f0ada8dc6f3deb1ec95806

Observation 383d5e46-a0ab-47fa-96fc-e8d47b749c2e · outbound

This paper cites and Rinard, M.

When Do Neural Networks Learn World Models? and Rinard, M

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.253389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.069104Z digest=sha256:1df9150912b195d6cf126e8904e4c05cff9bff1e833220e414ff0261127934c5

Observation 71e72b80-285b-48d8-9f25-fe45fcf00e3a · outbound

This paper cites SGD on neural networks learns functions of increasing complexity.

When Do Neural Networks Learn World Models? SGD on neural networks learns functions of increasing complexity

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.241544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.072865Z digest=sha256:b8d03275139e4b62c2c5a81aac3fa70e1d914780dd5f51116aad8a038285ef1d

Observation 4079ad2c-8bb3-4f4d-83e3-9582b82710e3 · outbound

This paper cites How far is video generation from world model: A physical law perspective.

When Do Neural Networks Learn World Models? How far is video generation from world model: A physical law perspective

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.229784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.076745Z digest=sha256:0bed716297ba6ae04cda34252001776d7bf7098024f09977f1637559e3a9458c

Observation 7b6679a6-812b-4474-be8a-698245e27158 · outbound

This paper cites P., Monti, R.

When Do Neural Networks Learn World Models? P., Monti, R

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.217693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.080610Z digest=sha256:4b73d9be7e72793fd52eb40abb0198eaf618a2dc20f35c68df3c8e74a02ef09a

Observation 350e01bf-faa8-4276-8a9e-6df604a566e5 · outbound

This paper cites A path towards autonomous machine intelligence version 0.9.

When Do Neural Networks Learn World Models? A path towards autonomous machine intelligence version 0.9

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.085095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.085095Z digest=sha256:a1c90767dfea541b31285a2ee3922309586103876de82a904d09d7b4c3f97d9a

Observation a33d1aeb-66ea-49c1-bf63-3685a815c831 · outbound

This paper cites D., Lei, Q., Saunshi, N., and Zhuo, J.

When Do Neural Networks Learn World Models? D., Lei, Q., Saunshi, N., and Zhuo, J

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.198434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.089203Z digest=sha256:4f344982128a845098025ea8ba5f674e51b6f9c6e800e01d3dc2260de7f8056d

Observation e1eb8231-2132-4d55-a3f9-59afddfae5aa · outbound

This paper cites Implicit Representations of Meaning in Neural Language Models.

When Do Neural Networks Learn World Models? Implicit Representations of Meaning in Neural Language Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.093046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.093046Z digest=sha256:aeed6e64253010eb10c953c142fb4afdc2b979390af16f355233f23c9cdc96e8

Observation 2a29a239-b4a6-4f92-825a-98bf1b1045c2 · outbound

This paper cites K., and Bau, D.

When Do Neural Networks Learn World Models? K., and Bau, D

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.186932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.097291Z digest=sha256:559838bea578d9d90270afd205b498c8a66b578e177492a86919af72ea046fba

Observation 25e02eed-2f1d-4d43-82fc-1c66b6f12667 · outbound

This paper cites An introduction to Kolmogorov complexity and its applications, volume 3.

When Do Neural Networks Learn World Models? An introduction to Kolmogorov complexity and its applications, volume 3

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.175433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.101073Z digest=sha256:cafa140299593a171e62dd76d8031ff77583379c500c28ea271c445a3130d5fb

Observation 1c07cacc-babe-4582-acac-031d88a283cd · outbound

This paper cites Self-supervised learning: Generative or contrastive.

When Do Neural Networks Learn World Models? Self-supervised learning: Generative or contrastive

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.164172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.104742Z digest=sha256:ce9b990d7b77fc3280f928672027855ba5febe744469501a7461f2ec1d9c8efc

Observation 68916361-4f92-48da-a5dc-0d6d628b0698 · outbound

This paper cites Grokking as Compression: A Nonlinear Complexity Perspective.

When Do Neural Networks Learn World Models? Grokking as Compression: A Nonlinear Complexity Perspective

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.108574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.108574Z digest=sha256:5b6fafb5717e25ed144db421d83f2b8c0df89722b8b259ec1f36a3e3c458a638

Observation 9b908d7b-c5b9-4cf7-8d7e-02d8555a4616 · outbound

This paper cites and Hutter, F.

When Do Neural Networks Learn World Models? and Hutter, F

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.152233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.112683Z digest=sha256:df2554fe0edf2b02ec6daf33aed88adc466a3a2283ea60281092c28e77c9d0c3

Observation 81ca0171-85cf-40a0-93ee-46bcaa6aa881 · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 55

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:12:51.140387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.116402Z digest=sha256:61f0c36d4071ac50c438c89ac16d02c8c63b50f6d99154c19c517460f354438a

Observation 9fbee53d-5271-43b2-bfc5-d8305c9613d5 · outbound

This paper cites Gradient descent on two-layer nets: Margin maximization and simplicity bias.

When Do Neural Networks Learn World Models? Gradient descent on two-layer nets: Margin maximization and simplicity bias

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.128596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.120098Z digest=sha256:6b4be8e65dbccabc95da699cfe0ed299aced893cc29b3b326b64ecce3ffd301e

Observation c6d99339-6de8-46f0-aef0-6f5b6c9baa73 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

When Do Neural Networks Learn World Models? The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.123935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.123935Z digest=sha256:ef542d5074705de9e8e6a834dc6027cb03bbd51d173718906198892d0f3b01e2

Observation 390608a4-27da-4738-83d6-f55bc11999ac · outbound

This paper cites Linguistic regularities in continuous space word representations.

When Do Neural Networks Learn World Models? Linguistic regularities in continuous space word representations

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.117106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.128194Z digest=sha256:fd1409fce3563421764c05bdfe84c12501677d66f635305b3f7214ee1cb3adb7

Observation 35dd6bf2-88c7-4a6c-a34c-0603ec54d8e3 · outbound

This paper cites GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models.

When Do Neural Networks Learn World Models? GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.131856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.131856Z digest=sha256:620212e3d445e543fde01505aa421067d00beaacac0bf4abf622c6f666fa86b9

Observation 3522f7f9-ae42-4232-87a7-3c56b59c3d90 · outbound

This paper cites Ai’s challenge of understanding the world.

When Do Neural Networks Learn World Models? Ai’s challenge of understanding the world

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.105905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.135699Z digest=sha256:71680a28aa28f4fa0f7c74aec14e054e5cc28818460e026a31f930047a93f916

Observation 421c1ee7-b03e-48f4-8b0c-3947c10e3a52 · outbound

This paper cites Do generative video models understand physical principles?.

When Do Neural Networks Learn World Models? Do generative video models understand physical principles?

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.139386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.139386Z digest=sha256:09dc8b7faa21b440155b957a9a4f3cdd74c611afaad32adcf28a20861595d253

Observation c1861d6e-0c06-432d-97fd-4ee9eb30e478 · outbound

This paper cites A White Paper on Neural Network Quantization.

When Do Neural Networks Learn World Models? A White Paper on Neural Network Quantization

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.143399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.143399Z digest=sha256:d9900846e87d3030e014c820917945ac48786fab8940298fc85b03dec7af65a1

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

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

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=sha256:60334db7177a1b04dc2f4cb15d44000bf215d43976786c4ec63678edfa7a7373

Observation a672be43-3bbd-4148-a1c9-0fec5e7a3367 · outbound

This paper cites Analysis of boolean functions.

When Do Neural Networks Learn World Models? Analysis of boolean functions

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.094410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.152096Z digest=sha256:f79485e9914e3b85b03f58f57db275301beb7e9f5d72c0bdfca08ef1518c01b6

Observation 5b7d7b98-8faa-4903-8c45-034d6885121e · outbound

This paper cites PyTorch : An imperative style, high-performance deep learning library.

When Do Neural Networks Learn World Models? PyTorch : An imperative style, high-performance deep learning library

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.083188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.156251Z digest=sha256:54d00e5915e0d30bf9166d30f08e4acf132721f1eab4f2d395a1740b0310acd4

Observation 38d51689-b6f8-46fe-9546-220d890d29ae · outbound

This paper cites Train short, test long: Attention with linear biases enables input length extrapolation.

When Do Neural Networks Learn World Models? Train short, test long: Attention with linear biases enables input length extrapolation

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.071357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.160268Z digest=sha256:a723ae2585911cae24df64f9cee648c434321723c2bf1fffa491572bd146d702

Observation e6ebed76-4596-4b0b-a685-5193fd053587 · outbound

This paper cites V., Louis, A.

When Do Neural Networks Learn World Models? V., Louis, A

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.057879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.163987Z digest=sha256:385409eac5d8c2abe5a95ba94d71ce4985a316caa306138deb41aba104aed88d

Observation 8d940cb7-9d52-4aea-8b28-e32391915644 · outbound

This paper cites Language models are unsupervised multitask learners.

When Do Neural Networks Learn World Models? Language models are unsupervised multitask learners

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.046693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.167942Z digest=sha256:18e066e0de40df5604eee482e62ac9f373da90186f3fdbd8d233276a9df3e926

Observation 020f9ca2-5dc2-4799-9415-57c3a86f9c50 · outbound

This paper cites Do vision transformers see like convolutional neural networks? Advances in Neural Information Processing Systems , 34: 0 12116--12128, 2021.

When Do Neural Networks Learn World Models? Do vision transformers see like convolutional neural networks? Advances in Neural Information Processing Systems , 34: 0 12116--12128, 2021

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.035317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.172371Z digest=sha256:cdb33eb3766c65b952544aa90d6e052286e1d3f93bdd20671f4087d271e20991

Observation 2bb49730-e3a3-495f-b19b-f878c5c06800 · outbound

This paper cites Position: Understanding LLMs requires more than statistical generalization.

When Do Neural Networks Learn World Models? Position: Understanding LLMs requires more than statistical generalization

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.022043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.177662Z digest=sha256:9e90db2552a3641447c6dbf19fd321a9a8f48d9248335e181286052f75823d82

Observation bee7d0ec-dfe8-40aa-aa6e-c00095a9ffca · outbound

This paper cites and Everitt, T.

When Do Neural Networks Learn World Models? and Everitt, T

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.181766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.181766Z digest=sha256:3a9b7c0cee6048a1284c85b013405489b12cdad66c013eef899c1ef04c1b1ad3

Observation 5c7895b0-8219-4ba1-b032-6ca424be538a · outbound

This paper cites R., Kalchbrenner, N., Goyal, A., and Bengio, Y.

When Do Neural Networks Learn World Models? R., Kalchbrenner, N., Goyal, A., and Bengio, Y

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:51.002176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.186148Z digest=sha256:00c9dcfbd2f8c7c9c25217e5d7c603fc78a20c0c9980290e7a30cb835bdf580f

Observation f9762ea6-0fd8-4e2b-98e1-cf1671905d9e · outbound

This paper cites S., Gunasekar, S., and Srebro, N.

When Do Neural Networks Learn World Models? S., Gunasekar, S., and Srebro, N

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.190104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.190104Z digest=sha256:42b52271ad4fcf38efa86fcef607c4c2a759bcaf8d1c52715990f450fa976a10

Observation 03b92ed4-d460-49c7-a385-07b87f148495 · outbound

This paper cites Neural Redshift: Random Networks are not Random Functions.

When Do Neural Networks Learn World Models? Neural Redshift: Random Networks are not Random Functions

Reference 74

Resolution
verified exact
local_arxiv, observed 2026-08-07T22:12:50.368226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.194047Z digest=sha256:4c11a1f56309773f9d5eb996c009c7370e6cfae7764403f65a262a758a02d15a

Observation 6493b6b1-f067-4419-bbd1-fc4291583ef9 · outbound

This paper cites Contrastive learning, multi-view redundancy, and linear models.

When Do Neural Networks Learn World Models? Contrastive learning, multi-view redundancy, and linear models

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.984141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.198467Z digest=sha256:c4064e89d6b2ea58ca5e6fd71258dbe2f3cfcfc547f2819dc8bffc923987a564

Observation 3c6ad341-62ba-4c4a-9805-49a9dfcfa7e5 · outbound

This paper cites The nature of statistical learning theory.

When Do Neural Networks Learn World Models? The nature of statistical learning theory

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.973002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.202869Z digest=sha256:6ca4d8c766c1af71fa4a8ca2d63df14ab6e51c8ec1c9118206d460bdba128cec

Observation 47e3215b-5b8f-4479-bfe3-356a2c036b38 · outbound

This paper cites N., Kaiser, L., and Polosukhin, I.

When Do Neural Networks Learn World Models? N., Kaiser, L., and Polosukhin, I

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.961569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.207001Z digest=sha256:a87c16255465c283fa0b9880c4a9870b19f9076b33cb2ece5c7495fcafbaff27

Observation e37d0edc-05d1-4eca-bcb0-9bb1422a9011 · outbound

This paper cites Self-supervised learning with data augmentations provably isolates content from style.

When Do Neural Networks Learn World Models? Self-supervised learning with data augmentations provably isolates content from style

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.949418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.210865Z digest=sha256:c196bdeb72dd769a0099a4eafa428f57fc99044f83fc8795c92b5ee9945ab317

Observation 178533ce-0f40-4ae0-a51d-c638b15c0bfb · outbound

This paper cites Nonparametric identifiability of causal representations from unknown interventions.

When Do Neural Networks Learn World Models? Nonparametric identifiability of causal representations from unknown interventions

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.937893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.214570Z digest=sha256:a314b9e42a2bc1eee0d2446ac3584721ca580216c989bc5553f7f1f7be00040d

Observation 086d8c97-ea7b-4806-a50a-1fe1cf4fe9c9 · outbound

This paper cites M., and Ma, T.

When Do Neural Networks Learn World Models? M., and Ma, T

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.926578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.218788Z digest=sha256:614a722f6e898baaea9902c7184f58c2ced48f7d1b8ee59db4396a41299d95d6

Observation 58566301-f9be-45cc-93cd-bf7213443ef5 · outbound

This paper cites and Watson, J.

When Do Neural Networks Learn World Models? and Watson, J

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.914569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.223010Z digest=sha256:482249ba56b01e659b1b3094d78f4487247d986a9aeb1801b4a5f67ed4b499fd

Observation bfba607c-070b-42e1-8765-f4dda9082cb8 · outbound

This paper cites an unresolved cited work.

When Do Neural Networks Learn World Models? Unresolved cited work

Reference 82

Resolution
unresolved
raw_fallback, observed 2026-08-07T22:12:50.901554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.226871Z digest=sha256:b80298e30de91aa4bdfbaf31d90ddca50f5f4678e98a904d1a1f3e9f261b0696

Observation cbc82b42-5c0c-41b8-97f9-df9927e62127 · outbound

This paper cites From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought.

When Do Neural Networks Learn World Models? From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.230706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.230706Z digest=sha256:45d15ec176eb04824018cf554e345982d3414c0cffc732a7f3805a011b26d4bc

Observation 7c070b59-3f4c-41e0-b02b-0124c0af69c5 · outbound

This paper cites Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks.

When Do Neural Networks Learn World Models? Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.234654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.234654Z digest=sha256:bfc64a930823d5f969872ed9a0d920f14cf2cb4c3a0a00f781a53100f2c7712b

Observation be03045d-3c11-40a2-8474-d83bb899ba1f · outbound

This paper cites Making Large Language Models into World Models with Precondition and Effect Knowledge.

When Do Neural Networks Learn World Models? Making Large Language Models into World Models with Precondition and Effect Knowledge

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.238938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.238938Z digest=sha256:518917d6392b5572882ffea080d1d750c728a5db25cc906387a5fddf9ecfe45d

Observation da98412d-ceaf-4cb7-9b5b-11ca6de19073 · outbound

This paper cites S., Kawarabayashi, K.-i., and Jegelka, S.

When Do Neural Networks Learn World Models? S., Kawarabayashi, K.-i., and Jegelka, S

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.888552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.242996Z digest=sha256:9d1ecbba6b2a65c82493db25ea323512b2a264f55e987de76be9999d6d1769fb

Observation c59a29d8-6a60-468d-97a2-20c58d040297 · outbound

This paper cites S., Kawarabayashi, K.-i., and Jegelka, S.

When Do Neural Networks Learn World Models? S., Kawarabayashi, K.-i., and Jegelka, S

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.876137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.246636Z digest=sha256:090698d30e42beed3393afb221740ef2f698a00e004af0ff56f850bd8c5b2290

Observation 2ab0add8-681f-4078-b1fb-a6369f5eaa73 · outbound

This paper cites Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks.

When Do Neural Networks Learn World Models? Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-07T22:12:50.250323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T22:12:50.250323Z digest=sha256:dbc700b56fff51f9d3785f0c726155f714428f56b981865fe3192af12869bb50

Observation e3fb2fc2-51a9-439c-8ba8-3e21315440e1 · outbound

This paper cites and Paul, L.

When Do Neural Networks Learn World Models? and Paul, L

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.864271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.254517Z digest=sha256:046e4ba4225fa55c72534167b2fd20b4099480efb3fbd638c1ede83ada304e42

Observation 68a47a00-642e-4916-8b3d-2828699f6722 · outbound

This paper cites Understanding deep learning requires rethinking generalization.

When Do Neural Networks Learn World Models? Understanding deep learning requires rethinking generalization

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.852125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.258678Z digest=sha256:a88bcfade0dcd553524cf6ff1246217a6245903b239662a84ebb61ca46fe7e20

Observation 218c12be-49ec-44bf-afdb-c4b9012798e8 · outbound

This paper cites Feature contamination: Neural networks learn uncorrelated features and fail to generalize.

When Do Neural Networks Learn World Models? Feature contamination: Neural networks learn uncorrelated features and fail to generalize

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.838112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.262692Z digest=sha256:20de138bfaa420176d1b0acc25f1728ef1b1ebf61f18700cf0ad2fe7697578d5

Observation b46c0945-daa1-4e5b-aa86-fc2f4e17a12a · outbound

This paper cites M ^3 PL : Identifying and exploiting view bias of prompt learning.

When Do Neural Networks Learn World Models? M ^3 PL : Identifying and exploiting view bias of prompt learning

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.825682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.267116Z digest=sha256:a629d221549a4df3b168e22e034f28a4844e87dca2e0a07b680ec21749fb1dcd

Observation 19e111a0-3695-4b22-b212-12ced909c0d6 · outbound

This paper cites P., and Orbanz, P.

When Do Neural Networks Learn World Models? P., and Orbanz, P

Reference 93

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.812099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.270904Z digest=sha256:f1be867497365bf15c13352df5579ef77ced1ecacc22ff6d6d28dead1c0f809a

Observation cf5c1cf8-9636-4845-82b3-6c64265e3d2b · outbound

This paper cites S., Sharma, Y., Schneider, S., Bethge, M., and Brendel, W.

When Do Neural Networks Learn World Models? S., Sharma, Y., Schneider, S., Bethge, M., and Brendel, W

Reference 94

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.798854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.274433Z digest=sha256:8e278d98cd2f3943428c3f5c9c268786e71d8b2f1a8a56f93834c642dfdd12d7

Observation 3a9d48a9-e311-42a9-a831-df8c758a4a16 · outbound

This paper cites Neural networks fail to learn periodic functions and how to fix it.

When Do Neural Networks Learn World Models? Neural networks fail to learn periodic functions and how to fix it

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T22:12:50.785901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-08-07T22:12:50.278134Z digest=sha256:8c670b1c139002088496c0777fe5d60c50c3565da7d4b5055f1081ad3db2af54

Pith citing papers

Observation 4da73e55-874a-4baf-8256-557b114f231d · inbound

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning cites this paper.

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning When Do Neural Networks Learn World Models?

Reference 64

Resolution
verified exact
arxiv_id, observed 2026-07-03T20:38:55.961175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

source=arxiv_source observed=2026-06-27T01:13:11.483599Z digest=sha256:7faefacc245816e479c166ba8bb4f1522666db202a9585721cc241dd56290ac5