Paper Citation Record · LEDGER

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation

As of 20 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2508.21378.

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

pith.paper-citation-record.v1
2508.21378 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:20:42.354783Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-27T19:55:20.212198Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T21:07:24.117503Z

Reference resolution

44 of 44 outbound references displayed

verified exact0
verified fuzzy19
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5bb025e1-78f9-4f6d-a858-0767dd7ab527 · outbound

This paper cites GPT-4 Technical Report.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:36.545665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f74101-04ca-483a-afdc-0dfcab74eaf2 · outbound

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

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:36.680088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13e7b8c3-8d60-4370-b906-a5da79014053 · outbound

This paper cites Llm-driven robots risk enacting discrimination, violence, and unlawful actions.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Llm-driven robots risk enacting discrimination, violence, and unlawful actions

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:36.788071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e043c4b1-05a3-4d70-a621-b09038d870f1 · outbound

This paper cites Roboagent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Roboagent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:51.659135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 63cd2728-8046-4125-a284-097c8bff83f1 · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:37.015548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bfedc21-204a-4b87-9d64-828dbbf6f089 · outbound

This paper cites Video generation models as world simulators.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Video generation models as world simulators

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:37.123014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 129859b3-2bc4-4ede-b200-ee88f9129acd · outbound

This paper cites Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:37.248332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1990d285-678b-4293-b8ea-ab30e72c7df2 · outbound

This paper cites Tongyi qianwen (qwen) - alibaba cloud, 2025.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Tongyi qianwen (qwen) - alibaba cloud, 2025

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:51.205858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3bb7488c-d7f8-443e-822e-c0d353f3650f · outbound

This paper cites Language as a cognitive tool to imagine goals in curiosity driven exploration.Advances in Neural Information Processing Systems, 33:3761–3774, 2020.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Language as a cognitive tool to imagine goals in curiosity driven exploration.Advances in Neural Information Processing Systems, 33:3761–3774, 2020

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:50.908104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 31107f97-b821-4e31-a5c8-c53fef10bb44 · outbound

This paper cites Teleoperation of humanoid robots: A survey.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Teleoperation of humanoid robots: A survey

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:50.554760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fb38652-5170-4ce1-affa-20e8778d7592 · outbound

This paper cites DeepSeek.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation DeepSeek

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:50.244754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c5ef637-9588-4185-98e4-0105a057f105 · outbound

This paper cites PaLM-E: An Embodied Multimodal Language Model.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation PaLM-E: An Embodied Multimodal Language Model

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:38.150967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea303629-0092-4732-a44c-99154a717c71 · outbound

This paper cites Anymal parkour: Learning agile navigation for quadrupedal robots.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Anymal parkour: Learning agile navigation for quadrupedal robots

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:49.894756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d8505c1b-46e4-4132-b4b0-8644a45c5137 · outbound

This paper cites Language instructed reinforcement learning for human-ai coordination.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Language instructed reinforcement learning for human-ai coordination

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:49.544757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 27606a79-a654-4aec-824c-aeb7f7dbd8b9 · outbound

This paper cites Language models as zero-shot planners: Extracting actionable knowledge for embodied agents.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Language models as zero-shot planners: Extracting actionable knowledge for embodied agents

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:38.668402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa88dab0-0449-47fd-ac8a-eb4fb444a5a8 · outbound

This paper cites Voxposer: Composable 3d value maps for robotic manipulation with language models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Voxposer: Composable 3d value maps for robotic manipulation with language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:49.114861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4a7ad2d7-7d7a-4c06-909d-0e66d5060bd9 · outbound

This paper cites Grounded decoding: Guiding text generation with grounded models for embodied agents.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Grounded decoding: Guiding text generation with grounded models for embodied agents

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:48.804926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2783c770-d220-44f4-bd37-c9a8676571ff · outbound

This paper cites Inner Monologue: Embodied Reasoning through Planning with Language Models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Inner Monologue: Embodied Reasoning through Planning with Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:39.117587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11283071-696a-4041-860f-c35b6183bdbe · outbound

This paper cites Robots enact malignant stereotypes.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Robots enact malignant stereotypes

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:48.414756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5850b996-54a1-4784-a498-eaa531d4e5c8 · outbound

This paper cites Rlbench: The robot learning benchmark & learning environment.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Rlbench: The robot learning benchmark & learning environment

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:48.089127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6b8a8d33-813f-4fb5-87c4-a8b6f74c3485 · outbound

This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation OpenVLA: An Open-Source Vision-Language-Action Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:39.593012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7905cd8-209c-4854-a2cd-513183def1c6 · outbound

This paper cites Segment anything.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Segment anything

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:39.692880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d87d1aa-846d-47c2-8241-a9f836e426a5 · outbound

This paper cites Reward Design with Language Models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Reward Design with Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:39.757357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42188b6b-0886-4b95-9140-0a04f46a6bbc · outbound

This paper cites Code as policies: Language model programs for embodied control.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Code as policies: Language model programs for embodied control

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:47.734756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8b86dd5a-8243-4e1d-9196-afa417898e66 · outbound

This paper cites The unlocking spell on base llms: Rethinking alignment via in-context learning.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation The unlocking spell on base llms: Rethinking alignment via in-context learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:47.404755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1da663a-bcce-4014-8b83-b66cb803da3f · outbound

This paper cites Compromising Embodied Agents with Contextual Backdoor Attacks.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Compromising Embodied Agents with Contextual Backdoor Attacks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:40.094761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3cafdfe-1ef0-4aec-b1b0-eb042685a5ff · outbound

This paper cites Exploring the robustness of decision-level through adversarial attacks on llm-based embodied models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Exploring the robustness of decision-level through adversarial attacks on llm-based embodied models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:40.291723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 473e813b-0094-4568-b062-b88e24c9773f · outbound

This paper cites Eureka: Human-Level Reward Design via Coding Large Language Models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Eureka: Human-Level Reward Design via Coding Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:40.464753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935f59bb-982d-4ba1-825c-086d33363add · outbound

This paper cites Malicious path manipulations via exploitation of representation vulnerabilities of vision-language navigation systems.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Malicious path manipulations via exploitation of representation vulnerabilities of vision-language navigation systems

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:47.039804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a72c9d86-334e-4c3a-9395-2827add01c27 · outbound

This paper cites Models - openai api, 2025.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Models - openai api, 2025

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:46.724756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 69c25960-6ef3-4997-b934-53d365e63805 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation DINOv2: Learning Robust Visual Features without Supervision

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:40.784738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da3854e-f0e7-4aaf-a2b0-fd4e3d97a10a · outbound

This paper cites Exploring the robustness of decision-level through adversarial attacks on llm-based embodied models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Exploring the robustness of decision-level through adversarial attacks on llm-based embodied models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:46.425040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4eadd3b-5023-4a6f-81ba-e2f724ec0ca5 · outbound

This paper cites Progprompt: Generating situated robot task plans using large language models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Progprompt: Generating situated robot task plans using large language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:46.114752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cd67b102-7a2e-414b-8edf-369514b95615 · outbound

This paper cites Chatgpt for robotics: Design principles and model abilities.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Chatgpt for robotics: Design principles and model abilities

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:45.914760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b0c42322-7988-4407-b77c-a65261a42c97 · outbound

This paper cites Chain- of-thought prompting elicits reasoning in large language models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Chain- of-thought prompting elicits reasoning in large language models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T14:20:45.694848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3424febd-90db-4e06-aa5c-e2121ec79515 · outbound

This paper cites On the safety concerns of deploying llms/vlms in robotics: Highlighting the risks and vulnerabilities.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation On the safety concerns of deploying llms/vlms in robotics: Highlighting the risks and vulnerabilities

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:41.404837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a89dc0-7c62-4d16-9876-6b2e29cf1939 · outbound

This paper cites Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:41.544751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe4042d1-66c7-475a-b004-24d3f2b4d472 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation ReAct: Synergizing Reasoning and Acting in Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:41.664783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d501f1bb-1e69-4b08-b6d6-2d3745075ebb · outbound

This paper cites Language to Rewards for Robotic Skill Synthesis.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Language to Rewards for Robotic Skill Synthesis

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:41.754771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d02181-48ab-4780-9878-aef5cf394354 · outbound

This paper cites Robotic Control via Embodied Chain-of-Thought Reasoning.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Robotic Control via Embodied Chain-of-Thought Reasoning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:41.835732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56e139dd-37a3-4040-92e4-816f1639207f · outbound

This paper cites Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:41.945837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a08c90-5716-46a0-b2ec-36697666ed6b · outbound

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

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:42.114754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02377535-632d-4b63-b018-d78fc9aaa4cc · outbound

This paper cites SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:42.236737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d6efce0-341c-4477-8467-016f933cf6c3 · outbound

This paper cites EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents.

RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T14:20:42.354783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 696ec086-1162-4cf2-8767-b02461434d7f · inbound

Efficient Skill Grounding via Code Refactoring with Small Language Models cites this paper.

Efficient Skill Grounding via Code Refactoring with Small Language Models RoboInspector: Unveiling the Unreliability of Policy Code for LLM-enabled Robotic Manipulation

Reference 118

Resolution: verified exact; arxiv_id, observed 2026-07-22T01:23:31.573588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.