Paper Citation Record · LEDGER

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches

As of 21 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 2 inbound Pith citation observations for arXiv:2506.13171.

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

pith.paper-citation-record.v1
2506.13171 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:40:18.124911Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:48:44.102637Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

35 of 35 outbound references displayed

verified exact4
verified fuzzy25
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation cde15dc7-afad-4ce9-bd68-da90421b794e · outbound

This paper cites Engineering automotive software,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Engineering automotive software,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:23.565015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c261f7ed-e03b-4019-8886-03c14e4da4c8 · outbound

This paper cites Automotive software engineering: A systematic mapping study,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Automotive software engineering: A systematic mapping study,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:23.412710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c763f503-2d4c-4b1d-adaf-39ea5b543ac2 · outbound

This paper cites Large language models for software engineering: Survey and open problems,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Large language models for software engineering: Survey and open problems,

Reference 3

Resolution: verified exact; raw_fallback, observed 2026-08-07T00:40:18.963286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 95f4196b-6761-4f9d-a826-9baff32b5554 · outbound

This paper cites PlantUML.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches PlantUML

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:23.281519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4fff9cc1-6864-4462-b587-a623f88c8cd1 · outbound

This paper cites Limitations of ChatGPT in conceptual modeling: insights from experiments in metamodeling,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Limitations of ChatGPT in conceptual modeling: insights from experiments in metamodeling,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:23.152125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8b0e9c48-e397-442c-9b60-f64546ca5d5f · outbound

This paper cites On the use of large language models in model-driven engineering,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches On the use of large language models in model-driven engineering,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:15.263092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bec014e6-4b46-4444-a3de-0ec78d14a112 · outbound

This paper cites Unified Modeling Language (UML) Specification Version 2.5.1.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Unified Modeling Language (UML) Specification Version 2.5.1

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:23.026635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9ca15034-d846-4eac-9f00-54461677ed60 · outbound

This paper cites Eclipse Modeling Framework (EMF).

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Eclipse Modeling Framework (EMF)

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.896248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 21eaaa12-193d-4da7-bcd5-1debde96bc05 · outbound

This paper cites AUTOSAR (Automotive Open System Architecture).

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches AUTOSAR (Automotive Open System Architecture)

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.749363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 30ce6583-b8c2-4484-95fd-09afa02f4228 · outbound

This paper cites Model-based automotive software development,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Model-based automotive software development,

Reference 10

Resolution: verified exact; doi, observed 2026-08-07T00:40:18.272763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5b0945cb-0df7-4c63-a9cc-dadd25c913b6 · outbound

This paper cites Understanding the landscape of software modelling assistants for MDSE tools: A systematic mapping,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Understanding the landscape of software modelling assistants for MDSE tools: A systematic mapping,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.584562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ffe4bc7b-5f3f-48d7-bdb9-acb5ae9bd8c3 · outbound

This paper cites Table meets LLM: Can large language models understand structured table data? A benchmark and empirical study,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Table meets LLM: Can large language models understand structured table data? A benchmark and empirical study,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:15.840986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08c9a42c-ad50-4ccf-973b-580acef23638 · outbound

This paper cites Retrieval-Augmented Generation for Large Language Models: A Survey.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Retrieval-Augmented Generation for Large Language Models: A Survey

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:15.968249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2694eddc-5745-493b-9ca3-27444b05636a · outbound

This paper cites Cognitive architectures for language agents,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Cognitive architectures for language agents,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.417240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c817a890-d9ca-4c47-bd18-629f1741ae41 · outbound

This paper cites ART: Automatic multi-step reasoning and tool-use for large language models.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches ART: Automatic multi-step reasoning and tool-use for large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:16.334501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb653ed-54d3-4286-aa21-b419e5d738f3 · outbound

This paper cites Model Context Protocol.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Model Context Protocol

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.261089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6cc7447e-1985-4267-91a7-9db5562c7e86 · outbound

This paper cites Agent2Agent Protocol (A2A).

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Agent2Agent Protocol (A2A)

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.132241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 50e7d20e-f3b8-40a8-84e6-7e769253f5cf · outbound

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

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Chain-of-Thought prompting elicits reasoning in large language models,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:21.907607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1d2714b1-b034-4f20-abc8-6b8e4fe72400 · outbound

This paper cites Self-consistency improves chain of thought reasoning in language models,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Self-consistency improves chain of thought reasoning in language models,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:21.609770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f8bae612-fd2c-42fd-a30f-a6947a4c3e02 · outbound

This paper cites Evaluating open-domain question answering in the era of large language models,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Evaluating open-domain question answering in the era of large language models,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:21.391733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 16ce2b65-9fc1-43b3-9ab4-ace68cdd3794 · outbound

This paper cites Evaluation of Semantic Answer Similarity Metrics.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Evaluation of Semantic Answer Similarity Metrics

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:40:18.636102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1a0d2f36-7f99-4b90-863c-425c93e235a5 · outbound

This paper cites Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:17.022076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 995812b6-cf97-4c91-b984-1a49ffa1d9af · outbound

This paper cites Reference-guided verdict: LLMs-as- Judges in automatic evaluation of free-form text,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Reference-guided verdict: LLMs-as- Judges in automatic evaluation of free-form text,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:40:17.111330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3553c49-5a9a-4a98-99a0-c80f86c2c141 · outbound

This paper cites Mermaid.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Mermaid

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:21.232888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ba4459fd-710b-44aa-8e9f-27919714f6fb · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches ReAct: Synergizing reasoning and acting in language models,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:21.099136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e96ab375-537b-4c33-bd33-72bb5b06823e · outbound

This paper cites SWE-agent: Agent-computer interfaces enable automated software engineering,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches SWE-agent: Agent-computer interfaces enable automated software engineering,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:20.933405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a2f46adf-038b-4913-b9fb-1f4df128301d · outbound

This paper cites INCHRON’s am2inc Ecore model.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches INCHRON’s am2inc Ecore model

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:20.807172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 91b5f639-edbc-4810-ab8e-a3099f1485cc · outbound

This paper cites Eclipse APP4MC.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Eclipse APP4MC

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:20.720751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 082538c8-b140-4b02-a26d-f3d13443d509 · outbound

This paper cites chronSUITE from INCHRON.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches chronSUITE from INCHRON

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:20.559946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f1c72ff5-a585-4672-a4b5-b42d1f00b4d3 · outbound

This paper cites INCHRON’s APP4MC / Amalthea Importer.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches INCHRON’s APP4MC / Amalthea Importer

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:20.249452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 97a22225-48fa-4661-be77-fb5b26e1e9cb · outbound

This paper cites Factuality of large language models: A survey,.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Factuality of large language models: A survey,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:19.959837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3717f797-c231-4050-8010-23c251e6a9ad · outbound

This paper cites LangSmith Hub Prompt: Evaluation for RAG answer accuracy vs a reference.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches LangSmith Hub Prompt: Evaluation for RAG answer accuracy vs a reference

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:19.661229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0037b909-c6bb-405d-a01b-ce901124f795 · outbound

This paper cites Available: https://docs.ragas.io/en/v0.2.15/.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Available: https://docs.ragas.io/en/v0.2.15/

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:19.462975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cba06c68-aaaa-419d-bc24-d802f6fc51d2 · outbound

This paper cites Available: https://ieeexplore.ieee.org/document/4142919.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Available: https://ieeexplore.ieee.org/document/4142919

Reference 2007

Resolution: verified exact; raw_fallback, observed 2026-08-07T00:40:19.179203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5021d1b5-6085-4f80-9997-fe1c1a105f9b · outbound

This paper cites Available: https://openreview.net/forum?id=1i6ZCvflQJ.

Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches Available: https://openreview.net/forum?id=1i6ZCvflQJ

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:40:22.349026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 980c0941-1199-4641-9980-2f5c023f9b13 · inbound

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code cites this paper.

Survey of GenAI for Automotive Software Development: From Requirements to Executable Code Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:44.102637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dafc0761-edef-4987-a7b6-0d0fa16a5e8d · inbound

Large Language Models for Fault Localization: An Empirical Study cites this paper.

Large Language Models for Fault Localization: An Empirical Study Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-04T08:28:24.869080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.