Paper Citation Record · LEDGER

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

As of 9 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 7 inbound Pith citation observations for arXiv:2502.02145.

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

pith.paper-citation-record.v1
2502.02145 v4

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T13:12:23.930548Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:35:41.554877Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T12:46:24.176668Z

Reference resolution

36 of 36 outbound references displayed

verified exact1
verified fuzzy18
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5cd89cb4-d795-41ce-a34e-0dd5befbd6ce · outbound

This paper cites A new taxonomy for automated driving: Structuring applications based on their operational design domain, level of automation and automation readiness,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios A new taxonomy for automated driving: Structuring applications based on their operational design domain, level of automation and automation readiness,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.480835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8aba6331-6abe-43d7-946b-646099bc7dca · outbound

This paper cites Safety testing of automated driving systems: A literature review,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Safety testing of automated driving systems: A literature review,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.469307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ded3f922-987a-44e5-88ea-6c7a3ba82a7d · outbound

This paper cites Survey on scenario-based safety assessment of automated vehicles,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Survey on scenario-based safety assessment of automated vehicles,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.457787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1d376071-118e-49cf-95ee-12c02c4db960 · outbound

This paper cites Simulation-based identification of critical scenarios for cooperative and automated vehicles,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Simulation-based identification of critical scenarios for cooperative and automated vehicles,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.445834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5ab967e9-9625-4680-84d3-e54879265c6e · outbound

This paper cites Language models are few-shot learners,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Language models are few-shot learners,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.814694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6245643c-8113-4961-9a08-c5499bd55439 · outbound

This paper cites Attention is all you need,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Attention is all you need,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.818208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fc5fa52-dd36-4a1a-948a-a8045ba6ca23 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.822676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01b5c9a9-2f84-4eb9-af89-507e08583603 · outbound

This paper cites Language Prompt for Autonomous Driving.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Language Prompt for Autonomous Driving

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.826515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86daac16-4764-4310-be15-ac6a35f84a53 · outbound

This paper cites DualAD: Dual-Layer Planning for Reasoning in Autonomous Driving.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios DualAD: Dual-Layer Planning for Reasoning in Autonomous Driving

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.830391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b6b984-1c52-46af-92d0-fb809378504a · outbound

This paper cites Drivegpt4: Interpretable end-to-end autonomous driving via large language model,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Drivegpt4: Interpretable end-to-end autonomous driving via large language model,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.834758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3edd2f2-18ee-4df4-ad80-10ba0ce1a740 · outbound

This paper cites Critical scenario identification for realistic testing of autonomous driving systems,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Critical scenario identification for realistic testing of autonomous driving systems,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.417649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bac7a671-bf37-45ce-8721-08f640353c66 · outbound

This paper cites Reality bites: Assessing the realism of driving scenarios with large language models,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Reality bites: Assessing the realism of driving scenarios with large language models,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.405531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 83680c38-a5f6-47d0-bd22-124bfaeb5cbd · outbound

This paper cites Deepscenario: An open driving scenario dataset for autonomous driving system testing,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Deepscenario: An open driving scenario dataset for autonomous driving system testing,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.394365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7043fb65-38bc-4221-a7e8-fc3d46bb4488 · outbound

This paper cites A Comprehensive LLM-powered Framework for Driving Intelligence Evaluation.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios A Comprehensive LLM-powered Framework for Driving Intelligence Evaluation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.848893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 525e91e1-843d-4587-bf6b-60a9bd658781 · outbound

This paper cites CARLA: An open urban driving simulator,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios CARLA: An open urban driving simulator,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.852958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16cbcf5d-d614-42b4-ab3b-8a60d4936db4 · outbound

This paper cites Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehicles.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Multimodal Large Language Model Driven Scenario Testing for Autonomous Vehicles

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.856099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a79917a-42b0-4ca6-8655-db7e00956eba · outbound

This paper cites Foundation models in autonomous driving: A survey on scenario generation and scenario analysis,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Foundation models in autonomous driving: A survey on scenario generation and scenario analysis,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.376923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 089e1f0d-c328-4454-9833-64bcc1b01b5f · outbound

This paper cites A survey on safety-critical driving scenario generation—a methodological perspective,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios A survey on safety-critical driving scenario generation—a methodological perspective,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.366052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bdb4b2a5-99df-4a10-9c5f-a9fcb6b77fa9 · outbound

This paper cites Factor graph scene distributions for automotive safety analysis,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Factor graph scene distributions for automotive safety analysis,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.355548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f071e738-656f-42e0-99cd-326bf89d3595 · outbound

This paper cites A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-09T13:12:24.186957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1ad5cbad-ba99-49fe-ba3c-31b09de72b65 · outbound

This paper cites Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.874820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4196ce24-5bd2-4042-9de4-97609a6eb877 · outbound

This paper cites Corner case generation and analysis for safety assessment of autonomous vehicles,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Corner case generation and analysis for safety assessment of autonomous vehicles,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.878321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3776c76d-8281-448f-b8da-bd077bc6d879 · outbound

This paper cites Building safer autonomous agents by leveraging risky driving behavior knowledge,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Building safer autonomous agents by leveraging risky driving behavior knowledge,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.336228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8c15688-da1f-4b45-aee3-95f755515b01 · outbound

This paper cites Robust trajectory prediction against adversarial attacks,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Robust trajectory prediction against adversarial attacks,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.323579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2a3e3568-da16-4312-a2c4-99ad00ba7784 · outbound

This paper cites Microscopic traffic simulation using sumo,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Microscopic traffic simulation using sumo,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.313225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a59d251d-8b5f-4888-817a-361d5ca89ded · outbound

This paper cites Chatscene: Knowledge-enabled safety-critical scenario generation for autonomous vehicles,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Chatscene: Knowledge-enabled safety-critical scenario generation for autonomous vehicles,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.302433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bf69808b-e8a4-4407-a991-1a66271ec005 · outbound

This paper cites Traffic scene generation from natural language description for autonomous vehicles with large language model,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Traffic scene generation from natural language description for autonomous vehicles with large language model,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.897125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49dc45a9-00ec-495d-a949-f047178552cd · outbound

This paper cites Chatsumo: Large language model for automating traffic scenario generation in simulation of urban mobility,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Chatsumo: Large language model for automating traffic scenario generation in simulation of urban mobility,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.291134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6dd834eb-74b4-43c0-b7c8-d402366df487 · outbound

This paper cites Commonroad: Composable benchmarks for motion planning on roads,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Commonroad: Composable benchmarks for motion planning on roads,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.905099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e022a96-3036-47a5-b0e8-0ee0a943e97e · outbound

This paper cites Lanelets: Efficient map representation for autonomous driving,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Lanelets: Efficient map representation for autonomous driving,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.273773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2d95e2ce-12be-4eb9-9277-c813431cca6e · outbound

This paper cites Frenetix: A high-performance and modular motion planning framework for autonomous driving,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Frenetix: A high-performance and modular motion planning framework for autonomous driving,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.262569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8716753-e51b-43ee-97c2-cbd02f8954f3 · outbound

This paper cites GPT-4 Technical Report.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios GPT-4 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.915383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c39082f7-95aa-4d27-8c0c-b7ca7f693ea7 · outbound

This paper cites StructGPT: A General Framework for Large Language Model to Reason over Structured Data.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios StructGPT: A General Framework for Large Language Model to Reason over Structured Data

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.918602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e01c5ec8-04cf-4818-b35a-5bdad8088cc6 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Gemini: A Family of Highly Capable Multimodal Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.922895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd98f46c-9ef9-4c85-9948-94e1db7fef28 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T13:12:23.926801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25beb06a-be97-43d8-9500-94c94c051083 · outbound

This paper cites Mptree: A sampling-based vehicle motion planner for real-time obstacle avoidance,.

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios Mptree: A sampling-based vehicle motion planner for real-time obstacle avoidance,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T13:12:24.251107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation 0142195d-47f3-48c5-83c5-9be688f91712 · inbound

CrashAgent: Crash Scenario Generation via Multi-modal Reasoning cites this paper.

CrashAgent: Crash Scenario Generation via Multi-modal Reasoning From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:35:41.554877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7c0bd38-964c-4e60-a550-df245d027239 · inbound

Generative AI for Testing of Autonomous Driving Systems: A Survey cites this paper.

Generative AI for Testing of Autonomous Driving Systems: A Survey From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-05T15:24:15.552048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a72f02-2a14-41ed-bb26-1a1855897a60 · inbound

AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models cites this paper.

AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T20:19:20.411086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2f3f7d-f7fc-408a-9364-fc96891ad17c · inbound

NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving cites this paper.

NuRisk: A Visual Question Answering Dataset for Agent-Level Risk Assessment in Autonomous Driving From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:46:24.179876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4fa74fd5-bc02-4319-8401-6130ea524adf · inbound

LLM Harms: A Taxonomy and Discussion cites this paper.

LLM Harms: A Taxonomy and Discussion From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 228

Resolution: verified exact; arxiv_id, observed 2026-05-17T00:31:24.587083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8a4a2618-9914-4a29-a0da-1f250a2d6f1c · inbound

LLM Harms: A Taxonomy and Discussion cites this paper.

LLM Harms: A Taxonomy and Discussion From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 219

Resolution: unresolved; no resolver link, observed 2026-08-03T18:19:31.764169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6995223b-2920-4472-b287-406724a59464 · inbound

A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data cites this paper.

A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T08:15:18.289469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.