{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KZU4IC323RHDB3QZADCY2YQZKX","short_pith_number":"pith:KZU4IC32","schema_version":"1.0","canonical_sha256":"5669c40b7adc4e30ee1900c58d621955e82750b471d68069c8d8635c71d8344d","source":{"kind":"arxiv","id":"2607.07103","version":1},"attestation_state":"computed","paper":{"title":"A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Heye Huang, Jianqiang Wang, Jingguang Li, Kitae Jang, Mingyu Wu, Paul Liang, Zhiyuan Zhou","submitted_at":"2026-07-08T07:39:21Z","abstract_excerpt":"Safe autonomous driving requires both rapid responses to common high-risk events and deeper reasoning over rare, extreme long-tail scenarios in traffic safety. These scenarios are severely under-represented in naturalistic driving data, and existing trajectory and language-augmented datasets seldom provide high-risk event labels, semantic annotations, and verifiable safety signals. Here we present K-Risk, a knowledge-augmented dataset that combines structured driving trajectories with large language model generated semantic annotations for safety-critical driving scenarios. K-Risk integrates 2"},"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":"2607.07103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T07:39:21Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"1fffb84e4310d905d1b85bcfde32c20488d6581037e8bb056959add11dc98099","abstract_canon_sha256":"71a40bf7f2b3f7a1813571414b047bfabfc739d07fb9ed6d5d21db03924d0eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:14.554652Z","signature_b64":"PHXSjKY0JAf3KbQnZ4Xd+dFJRzinj1H20DxczML2L+8Cn70OMEHMndgvWHxUvYZiZTMSWhghoihHQCozcM34Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5669c40b7adc4e30ee1900c58d621955e82750b471d68069c8d8635c71d8344d","last_reissued_at":"2026-07-09T01:20:14.554147Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:14.554147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for autonomous driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Heye Huang, Jianqiang Wang, Jingguang Li, Kitae Jang, Mingyu Wu, Paul Liang, Zhiyuan Zhou","submitted_at":"2026-07-08T07:39:21Z","abstract_excerpt":"Safe autonomous driving requires both rapid responses to common high-risk events and deeper reasoning over rare, extreme long-tail scenarios in traffic safety. These scenarios are severely under-represented in naturalistic driving data, and existing trajectory and language-augmented datasets seldom provide high-risk event labels, semantic annotations, and verifiable safety signals. Here we present K-Risk, a knowledge-augmented dataset that combines structured driving trajectories with large language model generated semantic annotations for safety-critical driving scenarios. K-Risk integrates 2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07103","kind":"arxiv","version":1},"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/2607.07103/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":"2607.07103","created_at":"2026-07-09T01:20:14.554204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07103v1","created_at":"2026-07-09T01:20:14.554204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07103","created_at":"2026-07-09T01:20:14.554204+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZU4IC323RHD","created_at":"2026-07-09T01:20:14.554204+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZU4IC323RHDB3QZ","created_at":"2026-07-09T01:20:14.554204+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZU4IC32","created_at":"2026-07-09T01:20:14.554204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX","json":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX.json","graph_json":"https://pith.science/api/pith-number/KZU4IC323RHDB3QZADCY2YQZKX/graph.json","events_json":"https://pith.science/api/pith-number/KZU4IC323RHDB3QZADCY2YQZKX/events.json","paper":"https://pith.science/paper/KZU4IC32"},"agent_actions":{"view_html":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX","download_json":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX.json","view_paper":"https://pith.science/paper/KZU4IC32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07103&json=true","fetch_graph":"https://pith.science/api/pith-number/KZU4IC323RHDB3QZADCY2YQZKX/graph.json","fetch_events":"https://pith.science/api/pith-number/KZU4IC323RHDB3QZADCY2YQZKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX/action/storage_attestation","attest_author":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX/action/author_attestation","sign_citation":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX/action/citation_signature","submit_replication":"https://pith.science/pith/KZU4IC323RHDB3QZADCY2YQZKX/action/replication_record"}},"created_at":"2026-07-09T01:20:14.554204+00:00","updated_at":"2026-07-09T01:20:14.554204+00:00"}