{"as_of":"2026-08-10T07:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5a97daef07024b851cc567ed0026c7e95e79f01736eef6236d3ed788a5b014ca","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:23:41.783008Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-30T19:18:40.244556Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-30T19:45:01.648924Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"cited_work":{"arxiv_id":"2507.13729","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.13729","snapshot_observed_at":"2026-06-30T19:45:01.648924Z","title":"Agents-llm: augmentative generation of challenging traffic scenarios with an agentic llm framework","venue":null,"work_id":"659fab21-c0ed-4810-ba8b-19f8d0c4c7ec","year":2025},"citing_paper":{"arxiv_id":"2605.23989","last_updated":"2026-05-17T10:26:37Z","snapshot_observed_at":"2026-07-06T23:34:08.786038Z","submitted_at":"2026-05-17T10:26:37Z","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","version":1},"reference_index":157,"source":"pdf_text","source_observed_at":"2026-06-30T19:18:40.244556Z"},"links":{"cited_paper":"/paper/2507.13729","citing_paper":"/paper/2605.23989"},"observation_digest":"sha256:1e870b4ec029c807fb383e766df43d27cf7bb35cf4a0f6da8a2bd67fa6314f0a","observation_id":"a9a6dc00-c976-459f-b9fb-058bb4dbf1a3","resolution":{"observed_at":"2026-06-30T19:45:01.650404Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.13729/citation-record","integrity":"/paper/2507.13729/integrity","json":"/paper/2507.13729/citation-record.json","paper":"/paper/2507.13729"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:48.554170Z","title":"Anomaly detection in multi-agent trajectories for automated driving,","venue":null,"work_id":"c09d3bc9-7c82-4eec-9a13-026a3e4f5d7a","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:38.685546Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:63827d6428fcd00a1e8d474f1814351dcace8e9695505734b3250e62e8a9c3a7","observation_id":"abfd15ea-b439-4971-8796-24e579e60356","resolution":{"observed_at":"2026-08-06T16:23:48.612376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:48.428559Z","title":"NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles,","venue":null,"work_id":"101367c9-6ba6-4a21-8edc-797a06af219b","year":2021},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:38.751793Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:b17962ef8c0af8c41ebe98b1e2d2f9a6edd7ac7774fc2f7c4225db6672418196","observation_id":"b2d8d0b7-a859-462e-8cc1-24e04f54d67e","resolution":{"observed_at":"2026-08-06T16:23:48.491021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:48.325730Z","title":"Scalability in perception for autonomous driving: Waymo open dataset,","venue":null,"work_id":"126365ab-e112-4724-b222-634ef4ad98c4","year":2020},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:38.824352Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:39f1f2844f158d1f9eb673f6ce8c22c864550137db88e96d7f873eb66a02803d","observation_id":"a82f4ff5-93a5-4b0c-b1a2-dbc2fbbf49fb","resolution":{"observed_at":"2026-08-06T16:23:48.377655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:48.208549Z","title":"Chat2Scenario: Scenario Extraction From Dataset Through Utilization of Large Language Model,","venue":null,"work_id":"f62fabc9-d3c3-47ff-8b7b-f5defca59f40","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:38.906059Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:6ccdae084068327dd2f4e84495e7b905dd21dd25c20d1ba13d3db9f12f29cb3b","observation_id":"43a2d1da-95bd-4600-acdf-0b528937d444","resolution":{"observed_at":"2026-08-06T16:23:48.262463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:48.077608Z","title":"SLEDGE: Synthe- sizing Driving Environments with Generative Models and Rule-Based Traffic,","venue":null,"work_id":"4f5ad244-91d3-4a7a-b8f2-bba47d68c935","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:38.971037Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:d3a53a2fa0e3b2a5469afdbbac338696403f5840fef19113a92c9c6b7d7266ba","observation_id":"80c75645-347e-4812-ad3b-bb44e7690b16","resolution":{"observed_at":"2026-08-06T16:23:48.141307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08570","last_updated":"2024-04-12T16:13:10Z","snapshot_observed_at":"2026-08-04T08:10:31.496057Z","submitted_at":"2024-04-12T16:13:10Z","title":"Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.08570","snapshot_observed_at":"2026-08-06T16:23:39.054292Z","title":"Enhancing autonomous vehicle training with language model integration and critical scenario generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.054292Z"},"links":{"cited_paper":"/paper/2404.08570","citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:f10b69430559f92e119f6b6678779812b39acdeb1c437608e0708eecdbf7ca94","observation_id":"78b1b082-0f85-4659-9a82-6665ea24ad0b","resolution":{"observed_at":"2026-08-06T16:23:39.054292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.952144Z","title":"Simnet: Learn- ing reactive self-driving simulations from real-world obser- vations,","venue":null,"work_id":"189dd658-c247-43ae-abf7-d62260b6f857","year":2021},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.127646Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:0b4d258ee0271f95dcbc2c3f39e2cc0149ef02ca7ffdfa7f7e9646339e8ed916","observation_id":"e3e0b44d-fb60-460a-9fed-2832cb442233","resolution":{"observed_at":"2026-08-06T16:23:48.020999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.828802Z","title":"Scenegen: Learning to generate realistic traffic scenes,","venue":null,"work_id":"68d7be73-6e8a-4f34-9e5c-fb905d6be88b","year":2021},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.223648Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:12953d8d45db16802d59101dacce5adf25315ded407e0e63519099dd03ce8b0a","observation_id":"4a5793d5-62d9-47b7-aacf-0ef530a32e28","resolution":{"observed_at":"2026-08-06T16:23:47.893217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.716769Z","title":"Can Vehicle Motion Planning Generalize to Realistic Long- tail Scenarios?","venue":null,"work_id":"8c058d9a-de1d-41ca-8c2d-2544efcbbfd6","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.326852Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:42ba9137e625e01024a4b987c7dd420f285b3eda61608349c97a4697fca518e3","observation_id":"1c64e8a4-73e0-4092-a08d-6f9fb7e44a1d","resolution":{"observed_at":"2026-08-06T16:23:47.763512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.581287Z","title":"React: Synergizing reasoning and acting in language models,","venue":null,"work_id":"ac33a220-43ed-4750-b90c-80062002261f","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.402097Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:085da7a6bf2b9eb383d2bc24b7bdcb83fcc484b7fbb667f0d3d85b5cff340414","observation_id":"6ae217ff-228e-4edd-9729-a59e9dd372e5","resolution":{"observed_at":"2026-08-06T16:23:47.639683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.433977Z","title":"Chatbot arena: An open platform for evaluating llms by human preference,","venue":null,"work_id":"14497fa6-99a1-4ba2-8949-60508c2066f7","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.449432Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:a4a3bd218238d5f46ded6e765da9c349762f643ee09941d5cb420035fae5c2bb","observation_id":"be0272fb-853a-4b2d-8cc9-9ceef056b7d0","resolution":{"observed_at":"2026-08-06T16:23:47.490268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.313077Z","title":"A Survey on Data-Driven Scenario Generation for Automated Vehicle Testing,","venue":null,"work_id":"31b12017-1f94-46b2-b62f-d4347a143801","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.550968Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:c9697e6bc440aa5260810ad7f1c235ca2f995b17e5cddbbb861cdbcb45dccc14","observation_id":"73950805-e5c1-4517-94c4-554e475d7b88","resolution":{"observed_at":"2026-08-06T16:23:47.379712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.177458Z","title":"A survey on safety-critical driving scenario generation—a methodological perspective,","venue":null,"work_id":"4af2ac60-8408-4c5c-99f3-7e4c67aafebe","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.641411Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:5febbeecf8d510318a0f40d7c14facac5e91169feefa20c10aaa200e5c71cafc","observation_id":"30c000ec-a436-45fb-b11a-b5b8c6415c33","resolution":{"observed_at":"2026-08-06T16:23:47.255311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:47.053437Z","title":"SceneControl: Diffusion for Controllable Traffic Scene Generation,","venue":null,"work_id":"8e0c3405-6108-4e54-86f3-5f8110215400","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.722171Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:313681377d977548d043e010de61ff61c1ca5ae9244f8a52390343ea5ae5c6e4","observation_id":"6c29a4f4-cfd0-42e8-8704-38fac5c2c47d","resolution":{"observed_at":"2026-08-06T16:23:47.106085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.946636Z","title":"GeoScenario: An open DSL for autonomous driving scenario representation,","venue":null,"work_id":"fedadf25-c905-40ba-8d27-90d3d3013e96","year":2019},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.793656Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:263b3501ad694f1ddad9810cab3a3fd5ab9a51704073d3e2891250d678087b66","observation_id":"ddad598a-5389-4fe8-a57d-9f1f60f76658","resolution":{"observed_at":"2026-08-06T16:23:47.004732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.810733Z","title":"SceGene: Bio-Inspired Traffic Scenario Genera- tion for Autonomous Driving Testing,","venue":null,"work_id":"9375710a-ace5-41cd-a6eb-43611513595b","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.850932Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:6b5d100ec7847060a0660337cd96e5e6925de14e5a84fb7eccc1fc2a058fbed1","observation_id":"c8210e08-17ed-4da0-91b5-44ea8ae1b8f9","resolution":{"observed_at":"2026-08-06T16:23:46.881425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.665552Z","title":"A comprehensive review on ontologies for scenario-based testing in the context of autonomous driving,","venue":null,"work_id":"48cbf1c0-40d4-4da5-af3f-04958d45d591","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.899559Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:cd147418b9f3d9b541f2ffc31f674b2b2eb3d7347097adf11ff0241c431fbfe6","observation_id":"54257cfc-bdfe-4394-836a-22308fcd1f7a","resolution":{"observed_at":"2026-08-06T16:23:46.745755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.547162Z","title":"Traffic Scenarios for Automated Vehicle Testing: A Review of Description Languages and Systems,","venue":null,"work_id":"2dee8b91-54cc-4edd-a150-f1e18192d0db","year":2021},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.928319Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:811070f72749e83ab7394e332e11027a046627d6f71e05a234be15270e702bd6","observation_id":"9378043d-93bb-4003-8a9a-a53cfe04b67d","resolution":{"observed_at":"2026-08-06T16:23:46.594041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.425850Z","title":"Text-to-drive: Diverse driving behavior synthesis via large language models,","venue":null,"work_id":"8236797b-44c0-4e7a-82c1-439271f2b331","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:39.992945Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:50a4fc0c1e7829e65778ef48dcbaf15eb37e81a04b77ec8d4ed9495e043db690","observation_id":"e93eca1e-f9c2-4e0e-b747-c4225d22509a","resolution":{"observed_at":"2026-08-06T16:23:46.484182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.284048Z","title":"Scenic: a lan- guage for scenario specification and scene generation,","venue":null,"work_id":"12e264fc-be72-4d6e-a7fa-ea7c309216c6","year":2019},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.066992Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:1bc68e74216e65ab331442b5a0b5f648d3bce898efc2f9540306fd08c0cdebdd","observation_id":"b0092be5-819b-424e-8a0e-c5c7192601bf","resolution":{"observed_at":"2026-08-06T16:23:46.352536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:46.005948Z","title":"ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehi- cles,","venue":null,"work_id":"58c2f879-5299-4f87-aca8-ccf9ab633a02","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.143070Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:d15cbbbc0fbc00e097977b0cf5b78d49c2e45c369fd3cdfa6d917dfa919be104","observation_id":"bf036d69-9f21-4c24-bc22-57f00d441a42","resolution":{"observed_at":"2026-08-06T16:23:46.109490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17372","last_updated":"2023-10-26T13:07:01Z","snapshot_observed_at":"2026-07-06T16:38:56.540232Z","submitted_at":"2023-10-26T13:07:01Z","title":"Dialogue-based generation of self-driving simulation scenarios using Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.17372","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.17372","snapshot_observed_at":"2026-08-06T16:23:41.972868Z","title":"Dialogue-based generation of self-driving simulation scenarios using Large Language Models","venue":"cs.AI","work_id":"0eb38b57-4d57-490d-8e8e-37ea176502ed","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.205917Z"},"links":{"cited_paper":"/paper/2310.17372","citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:ba95d34292a67cdca6cf9de9d2311ed4f567d37a3f68ac38b576355149523a0c","observation_id":"8062d74f-e287-4d08-8aa4-9c59415c112f","resolution":{"observed_at":"2026-08-06T16:23:42.073641Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:45.785230Z","title":"Language Conditioned Traffic Generation,","venue":null,"work_id":"fe48242e-7d88-4881-b382-33dcd93202cd","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.254415Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:ffd58910d20818fff62661ad87f43b3f6b924622531dc5f5812ad58c5e9a728b","observation_id":"af0d15aa-b3f9-4111-875c-b7bb0730d934","resolution":{"observed_at":"2026-08-06T16:23:45.871269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:45.545042Z","title":"Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion,","venue":null,"work_id":"84d0d4dc-9004-434c-8909-939c446b50b4","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.305413Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:d4aeee347a7305e0c952995d8af8bfbff88e5404e6a6e3ca9b4e0b0d6be28f78","observation_id":"537f5ba2-ab6c-4b45-8623-0d3428c51eba","resolution":{"observed_at":"2026-08-06T16:23:45.627447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:45.306832Z","title":"DriveSceneGen: Generating Diverse and Realistic Driving Scenarios From Scratch,","venue":null,"work_id":"4130a37a-2813-4d9f-b341-2ec4519bce2d","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.358785Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:96edea604f0b6f421232edeaffa521ce3a701b4e9a039558cbce33f5feda25ae","observation_id":"d19b54ca-f4cc-4786-9c11-96139abd8146","resolution":{"observed_at":"2026-08-06T16:23:45.419651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:45.127504Z","title":"Realgen: Retrieval augmented generation for controllable traffic scenarios,","venue":null,"work_id":"c62c196a-aa88-476e-9209-958c92912509","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.412950Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:ff3d0c24e500341286e27e761e6cd69fc9558f4e34fef02dd68cee66fb732e6f","observation_id":"6d19dd4b-565c-41d4-9915-7c72d7cc951f","resolution":{"observed_at":"2026-08-06T16:23:45.226773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:44.890983Z","title":"UniSim: A Neural Closed-Loop Sensor Simulator,","venue":null,"work_id":"3ea7fdc7-48b0-4480-bbae-55ffb2817d13","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.453287Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:8954e0333b788e623370f71413b17c019cc612f850e52eec9e82381cdcc4c70a","observation_id":"90c8c10d-d445-4e0f-909e-c81bbd4c0b0f","resolution":{"observed_at":"2026-08-06T16:23:44.979822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:44.711967Z","title":"On ad- versarial robustness of trajectory prediction for autonomous vehicles,","venue":null,"work_id":"f2cd534d-883f-4f52-b67d-86d8ba4c8d2f","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.482818Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:3f41ae2e6a6710a49f7a2581e06afd529bdc82d8a4b9c1d7cd58ffdd15022d56","observation_id":"4b413680-ba23-4077-89be-723e58668013","resolution":{"observed_at":"2026-08-06T16:23:44.793709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:44.524888Z","title":"Stay on track: A frenet wrapper to overcome off-road trajectories in vehicle motion prediction,","venue":null,"work_id":"7557d951-d0e1-4f77-aced-e743707cf584","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.601119Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:a835907711ead0e7b2b30460510bc46211cdaca53a4b98fa489e7861ce5eda5e","observation_id":"31088be1-9ab8-4379-944b-e1cf45bab983","resolution":{"observed_at":"2026-08-06T16:23:44.610266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:44.337731Z","title":"Vehicle trajectory prediction works, but not everywhere,","venue":null,"work_id":"b5872117-9db4-42e3-b5b8-f145913ede3a","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.697902Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:ae6479ea9c73bcea17d92485d03cd98f6406dcbccbd624052645e9fc88e92c1e","observation_id":"b2485a4d-cf2f-4e40-85f0-d654c4be3e01","resolution":{"observed_at":"2026-08-06T16:23:44.414407Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:44.109874Z","title":"AutoGen: Enabling Next- Gen LLM Applications via Multi-Agent Conversation,","venue":null,"work_id":"ad1b0157-6fd9-47f6-a3cb-caa32571c09a","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.808193Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:23d77a44889000ef7e770e6abb73c74c26dc2416e755934350191bc237b5cefb","observation_id":"a15012bc-6ce4-4f95-867f-1783b0bc6c71","resolution":{"observed_at":"2026-08-06T16:23:44.226472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:43.869107Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":"182abee2-d0ae-4b56-bd37-7cd98198bd99","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:40.930892Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:68873d74d677b8a43d30a669fe648e66155be2af4b120690206a1d5b7c2b0f53","observation_id":"d81e1e20-091e-426d-a198-5a2b2e5bb896","resolution":{"observed_at":"2026-08-06T16:23:44.002017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:43.669086Z","title":"Toolformer: Language models can teach themselves to use tools,","venue":null,"work_id":"0283ce0f-8e4e-4704-a7df-a621643f9b03","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.047656Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:8bd959cf24e8e5a9cf1b56f42f423827de9ef3dda7d09a7ec00306defcb7c453","observation_id":"42f9b59e-cf5e-49da-848c-47810048df0b","resolution":{"observed_at":"2026-08-06T16:23:43.794050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:43.439568Z","title":"Urban Driver: Learning to Drive from Real- world Demonstrations Using Policy Gradients,","venue":null,"work_id":"c28a3cd3-ee31-4844-9d67-1f35c14b8fe6","year":2022},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.169002Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:370a1db71d752d32f45e7cf8617a308036f178a4ba02fc021d154ff86151a3de","observation_id":"ac2c52fe-01d8-4dfa-8fb5-3ca7cd4250ac","resolution":{"observed_at":"2026-08-06T16:23:43.538027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:43.246087Z","title":"GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving,","venue":null,"work_id":"fc2daef5-176b-4602-9c9a-c4494286dff1","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.226883Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:a265a3fb84ccf17b7391a9afd5290bf1414f93a0667be3c699c382b1f64d04f9","observation_id":"66f5594a-5045-4ec1-9e1a-6fde84590dda","resolution":{"observed_at":"2026-08-06T16:23:43.336944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:43.027043Z","title":"From prediction to planning with goal conditioned lane graph traversals,","venue":null,"work_id":"58adea81-6a06-4717-b9d6-7d142f643091","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.324931Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:491dfaf2eb49df681eedff085339e253add5ceeaf9bb2e28c55a484798367d05","observation_id":"6043922e-9626-4089-a855-1a4b160a61a4","resolution":{"observed_at":"2026-08-06T16:23:43.137125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:42.770929Z","title":"DTPP: Differentiable Joint Conditional Prediction and Cost Evaluation for Tree Policy Planning in Autonomous Driving,","venue":null,"work_id":"8e3b9a07-5878-4921-9712-b1dc1dc96792","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.447801Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:e27cfcbfcf2f912029e0f23b8f7a982178150f02339a6915769d9cc8cd90d7e9","observation_id":"1e58f568-2d19-4ea7-a17e-e57c690f3184","resolution":{"observed_at":"2026-08-06T16:23:42.884079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:42.480641Z","title":"Parting with Misconceptions about Learning-based Vehicle Motion Planning,","venue":null,"work_id":"9ffc2a12-44d3-45e7-9011-c5d952a37c0b","year":2023},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.528864Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:0950e733a051a9b43cb5f490e6334f42668bb76223b5dab7216b8fd5fd5180d4","observation_id":"343056c3-6eff-45d6-9bfc-84018dbde67e","resolution":{"observed_at":"2026-08-06T16:23:42.616583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:42.269987Z","title":"MBAPPE: MCTS-built-around prediction for planning explicitly,","venue":null,"work_id":"123d6ca9-60db-4cdd-99c9-6e22b654574c","year":2024},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.634905Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:f715bf1da8013fcf4bc042cd1e5b454aeb13ad7b6b535dd83631356117e5a85e","observation_id":"f380f5ac-9a4b-4a93-b00b-ec93a1590b0d","resolution":{"observed_at":"2026-08-06T16:23:42.387733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T16:23:41.783008Z","title":"The Hungarian method for the assignment problem,","venue":null,"work_id":null,"year":1955},"citing_paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T16:23:41.783008Z"},"links":{"citing_paper":"/paper/2507.13729"},"observation_digest":"sha256:d14bac570f83a247c2147be103be0a1e3e1a21fc7e16ae5b794db7ebab96440d","observation_id":"5439393f-e6dd-49e8-ba42-307dde664582","resolution":{"observed_at":"2026-08-06T16:23:41.783008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.13729","last_updated":"2025-07-18T08:20:16Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-06T16:15:15.023763Z","submitted_at":"2025-07-18T08:20:16Z","title":"AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":40},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2507.13729."}