Paper Citation Record · LEDGER

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning

As of 16 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2507.15521.

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

pith.paper-citation-record.v1
2507.15521 v1

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:32:48.679885Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

14 of 14 outbound references displayed

verified exact3
verified fuzzy0
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 05b1a852-5f25-4f71-b3b1-f6e2d07ba926 · outbound

This paper cites GPT-4 Technical Report.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning GPT-4 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.267318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 521becfd-98be-47a8-906e-74d573b541b4 · outbound

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

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.430793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a1dd634-25d1-4989-9f20-f960d7689124 · outbound

This paper cites Adversarial Policies Beat Superhuman Go AIs.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Adversarial Policies Beat Superhuman Go AIs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.569329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f86d6c-bd51-4705-8105-25b03c61cab9 · outbound

This paper cites Language Models Meet World Models: Embodied Experiences Enhance Language Models.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Language Models Meet World Models: Embodied Experiences Enhance Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.679885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2125ecfc-490c-4cc2-aeea-c479e77d91fe · outbound

This paper cites Till Tantau.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Till Tantau

Reference 1971

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.496061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ca5b0d9-a3ee-42be-876e-6a99ff8e2043 · outbound

This paper cites doi: 10.2307/2529310.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning doi: 10.2307/2529310

Reference 1977

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.032411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7de69ad-7594-4e37-aa57-3a4f11a4953f · outbound

This paper cites Zhiting Hu and Tianmin Shu.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Zhiting Hu and Tianmin Shu

Reference 1988

Resolution: verified exact; doi, observed 2026-08-06T15:32:48.947506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fa0c13b2-d59e-48b6-9aea-4fb54660e6a1 · outbound

This paper cites doi: 10.3758/BF03200867.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning doi: 10.3758/BF03200867

Reference 1994

Resolution: verified exact; doi, observed 2026-08-06T15:32:49.107985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8e2ba0e5-cca1-4e04-9b3a-e13efd5818ce · outbound

This paper cites Sébastien Bubeck et al.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Sébastien Bubeck et al

Reference 1996

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.352779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 824aabf6-0f97-4a44-a3b7-8d9c60fc1940 · outbound

This paper cites Mary Hegarty.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Mary Hegarty

Reference 1998

Resolution: verified exact; raw_fallback, observed 2026-08-06T15:32:49.436699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation eb50ccb6-9a5c-48c0-b060-766c784b9a38 · outbound

This paper cites doi: 10.1016/j.tics.2004.04.001.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning doi: 10.1016/j.tics.2004.04.001

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:47.715864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0384f2e-e547-4c1f-b83b-be6ca2f07337 · outbound

This paper cites The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.177589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6818f7d3-cbc4-4923-97b5-a6c507ebe51b · outbound

This paper cites Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Language Models, Agent Models, and World Models: The LAW for Machine Reasoning and Planning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:47.959750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e039aa87-54b4-4974-83c4-ca302c732830 · outbound

This paper cites Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models.

LLM world models are mental: Output layer evidence of brittle world model use in LLM mechanical reasoning Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T15:32:48.102882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.