Paper Citation Record · LEDGER

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making

As of 16 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2505.19933.

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

pith.paper-citation-record.v1
2505.19933 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:12:28.429014Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

31 of 31 outbound references displayed

verified exact0
verified fuzzy10
unresolved20
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 81675f90-ef15-4d97-8f95-7035cb2d71de · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:32.862255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9c66ab54-0159-4bb2-8033-21cd376d125d · outbound

This paper cites drop_vase_on_table.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making drop_vase_on_table

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:32.692068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f5b029b2-e2cd-4323-af4c-c9ece47e01e3 · outbound

This paper cites • State changes must result from explicitagent actions.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making • State changes must result from explicitagent actions

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:32.027185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2a9979f2-daf0-4255-8253-bc7ccf2eb8bc · outbound

This paper cites Code as Policies: Language Model Programs for Embodied Control.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Code as Policies: Language Model Programs for Embodied Control

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:26.533633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a508691-375e-46ca-85e8-676b5d34dda0 · outbound

This paper cites BadRobot: Jailbreaking Embodied LLM Agents in the Physical World.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:26.613618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1de8ebd2-22c4-4101-b95f-2502ff4f2a85 · outbound

This paper cites opening cabinets.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making opening cabinets

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:33.043013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d7fb505c-55ca-4557-b49e-09401aa81319 · outbound

This paper cites name": "sink_7.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making name": "sink_7

Reference 7

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:12:28.622136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2c94f8be-f34f-48de-959b-44ea57dbfbc9 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:32.503999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fedd2073-985a-49cc-8a1b-372337aae129 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:32.334554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dc681a38-a624-47cf-b4aa-d1c9382d0cda · outbound

This paper cites natural_language_instruction.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making natural_language_instruction

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:31.808388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 12f2655c-3793-4f44-972c-bc3c5073810c · outbound

This paper cites new_actions_description.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making new_actions_description

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:31.567144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2a086953-7331-4b80-8feb-573c0f44189a · outbound

This paper cites • The agent must reason about the environment to act safely.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making • The agent must reason about the environment to act safely

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:31.210673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 734179b3-af11-40df-9e18-8ada27a4c80e · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:31.010112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9a92cc0d-cbe6-4b62-9346-c62c9c6d6f51 · outbound

This paper cites • State changes must result from explicit agent actions.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making • State changes must result from explicit agent actions

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:30.780810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation fb3932a5-f19f-45c0-b87e-8a38f11c2661 · outbound

This paper cites • The final action must satisfy the goal safely, using correct preconditions.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making • The final action must satisfy the goal safely, using correct preconditions

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:30.542424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 25e7b031-6a32-4001-b409-6bc9d955caac · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:30.337084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a1d4ae7b-ccdf-436f-a1e3-545a8e1b1573 · outbound

This paper cites natural_language_instruction.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making natural_language_instruction

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:30.215525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a6020621-aef7-46ff-83a5-b4528660354b · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:30.125615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dd1468da-2c56-4735-b593-69ab3e9ca824 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:30.018079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d693e4a7-9bda-4ad6-b36e-c6adac2279b0 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:29.896006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 21873e00-eac5-492a-9005-bc9245cf208d · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:29.758128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 78103950-b8c8-4e65-96c0-37d32b0100f2 · outbound

This paper cites risky" in the first sentence is replaced with.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making risky" in the first sentence is replaced with

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:12:29.606429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 22bfe093-c3f7-4202-9874-aae0edf3480f · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:29.446742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9542294c-eeab-462d-a828-7e8460a0edb4 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:29.367183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2fd9abcf-6cfa-4465-bd12-4e6f60a80301 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:29.207919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f5305142-22a8-4544-9f58-fa776ed3a1b9 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:29.060766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a3d72fa7-a124-40fb-ad5d-2f99bcf842ac · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:28.899090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 923e0868-aaeb-4aa3-9301-bbd914c2fcd0 · outbound

This paper cites an unresolved cited work.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:12:28.780252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6a534289-e31c-4c48-b27e-b899512a1dcd · outbound

This paper cites iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:26.432904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc7c3a19-c28a-48e4-abe9-833cd3fe8f5d · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:26.284427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 241e9071-a2a1-4512-816d-10f477369f8d · outbound

This paper cites The Llama 3 Herd of Models.

Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:26.352482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.