{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JGVKJLEEHCWDUKGRDITRZ6MA7S","short_pith_number":"pith:JGVKJLEE","schema_version":"1.0","canonical_sha256":"49aaa4ac8438ac3a28d11a271cf980fc936ed19da37853a9a4a42a4800ad44ce","source":{"kind":"arxiv","id":"2412.13238","version":2},"attestation_state":"computed","paper":{"title":"SafeDrive: Knowledge- and Data-Driven Risk-Sensitive Decision-Making for Autonomous Vehicles with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.RO"],"primary_cat":"cs.AI","authors_text":"Boqi Li, Heye Huang, Jianqiang Wang, Shiyue Zhao, Yao Mu, Zhiyuan Zhou","submitted_at":"2024-12-17T16:45:27Z","abstract_excerpt":"Recent advancements in autonomous vehicles (AVs) use Large Language Models (LLMs) to perform well in normal driving scenarios. However, ensuring safety in dynamic, high-risk environments and managing safety-critical long-tail events remain significant challenges. To address these issues, we propose SafeDrive, a knowledge- and data-driven risk-sensitive decision-making framework to enhance AV safety and adaptability. The proposed framework introduces a modular system comprising: (1) a Risk Module for quantifying multi-factor coupled risks involving driver, vehicle, and road interactions; (2) a "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.13238","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-17T16:45:27Z","cross_cats_sorted":["cs.ET","cs.RO"],"title_canon_sha256":"faa8ba2d5508666fdcdbdc098dbf4d03c6c4d181fd6576d7e7231dfd691a35b8","abstract_canon_sha256":"53d7aee46203d585a4f2ab4266a360fa4a45a97fb75dc3f5e33a5b8f7a82b913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:40.491432Z","signature_b64":"kE1CeDKd2V76kY+YG2nZG6qcdZ1tEzfAV/Of3lLAWbBNWn/1hvDfhcweb3F8UGvcAyKqeXfiFKGtVfOa9xxoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49aaa4ac8438ac3a28d11a271cf980fc936ed19da37853a9a4a42a4800ad44ce","last_reissued_at":"2026-07-05T09:51:40.490948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:40.490948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeDrive: Knowledge- and Data-Driven Risk-Sensitive Decision-Making for Autonomous Vehicles with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.RO"],"primary_cat":"cs.AI","authors_text":"Boqi Li, Heye Huang, Jianqiang Wang, Shiyue Zhao, Yao Mu, Zhiyuan Zhou","submitted_at":"2024-12-17T16:45:27Z","abstract_excerpt":"Recent advancements in autonomous vehicles (AVs) use Large Language Models (LLMs) to perform well in normal driving scenarios. However, ensuring safety in dynamic, high-risk environments and managing safety-critical long-tail events remain significant challenges. To address these issues, we propose SafeDrive, a knowledge- and data-driven risk-sensitive decision-making framework to enhance AV safety and adaptability. The proposed framework introduces a modular system comprising: (1) a Risk Module for quantifying multi-factor coupled risks involving driver, vehicle, and road interactions; (2) a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13238","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.13238/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.13238","created_at":"2026-07-05T09:51:40.491008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13238v2","created_at":"2026-07-05T09:51:40.491008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13238","created_at":"2026-07-05T09:51:40.491008+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGVKJLEEHCWD","created_at":"2026-07-05T09:51:40.491008+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGVKJLEEHCWDUKGR","created_at":"2026-07-05T09:51:40.491008+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGVKJLEE","created_at":"2026-07-05T09:51:40.491008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07103","citing_title":"A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21406","citing_title":"MC-Risk: Multi-Component Risk Fields for Risk Identification and Motion Planning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S","json":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S.json","graph_json":"https://pith.science/api/pith-number/JGVKJLEEHCWDUKGRDITRZ6MA7S/graph.json","events_json":"https://pith.science/api/pith-number/JGVKJLEEHCWDUKGRDITRZ6MA7S/events.json","paper":"https://pith.science/paper/JGVKJLEE"},"agent_actions":{"view_html":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S","download_json":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S.json","view_paper":"https://pith.science/paper/JGVKJLEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13238&json=true","fetch_graph":"https://pith.science/api/pith-number/JGVKJLEEHCWDUKGRDITRZ6MA7S/graph.json","fetch_events":"https://pith.science/api/pith-number/JGVKJLEEHCWDUKGRDITRZ6MA7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S/action/storage_attestation","attest_author":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S/action/author_attestation","sign_citation":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S/action/citation_signature","submit_replication":"https://pith.science/pith/JGVKJLEEHCWDUKGRDITRZ6MA7S/action/replication_record"}},"created_at":"2026-07-05T09:51:40.491008+00:00","updated_at":"2026-07-05T09:51:40.491008+00:00"}