{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PT6N5UX3YYYCECOXBXJC7H4P5Q","short_pith_number":"pith:PT6N5UX3","schema_version":"1.0","canonical_sha256":"7cfcded2fbc6302209d70dd22f9f8fec0cbd849f3d3be48e77a17082d40acc7e","source":{"kind":"arxiv","id":"2606.03678","version":1},"attestation_state":"computed","paper":{"title":"EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jian Sun, Jie Deng, Junlin He, Tong Nie, Wei Ma, Yihong Tang, Yuewen Mei","submitted_at":"2026-06-02T14:01:23Z","abstract_excerpt":"Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures while preserving realism. Existing methods usually manage this trade-off with handcrafted heuristics, confining generation to known priors and overlooking underexplored patterns. While recent open-ended agentic evolution can push this limit, unconstrained general agents lack strict simulator grounding and tend to collapse the multi-objective tension into single-scalar maximization. Here we present EvoDrive, the first "},"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":"2606.03678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T14:01:23Z","cross_cats_sorted":[],"title_canon_sha256":"3495b4457b5cb8666e2c38c097781d142d810751c0990ac846806105ae559224","abstract_canon_sha256":"78b9b435ab438c68bdb878b337f269c3b23d1dbbc5f827714ca06b0779885552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:04.334400Z","signature_b64":"1WOFMNyk4A9H+2xSykclnbIu023t1FWSzCTbwQd8jyDzFX4cJQsbsgjp2fjQhjrobKFNGup4B1yssX9/364tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cfcded2fbc6302209d70dd22f9f8fec0cbd849f3d3be48e77a17082d40acc7e","last_reissued_at":"2026-06-03T01:06:04.333982Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:04.333982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jian Sun, Jie Deng, Junlin He, Tong Nie, Wei Ma, Yihong Tang, Yuewen Mei","submitted_at":"2026-06-02T14:01:23Z","abstract_excerpt":"Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expose failures while preserving realism. Existing methods usually manage this trade-off with handcrafted heuristics, confining generation to known priors and overlooking underexplored patterns. While recent open-ended agentic evolution can push this limit, unconstrained general agents lack strict simulator grounding and tend to collapse the multi-objective tension into single-scalar maximization. Here we present EvoDrive, the first "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03678","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/2606.03678/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":"2606.03678","created_at":"2026-06-03T01:06:04.334041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03678v1","created_at":"2026-06-03T01:06:04.334041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03678","created_at":"2026-06-03T01:06:04.334041+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT6N5UX3YYYC","created_at":"2026-06-03T01:06:04.334041+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT6N5UX3YYYCECOX","created_at":"2026-06-03T01:06:04.334041+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT6N5UX3","created_at":"2026-06-03T01:06:04.334041+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/PT6N5UX3YYYCECOXBXJC7H4P5Q","json":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q.json","graph_json":"https://pith.science/api/pith-number/PT6N5UX3YYYCECOXBXJC7H4P5Q/graph.json","events_json":"https://pith.science/api/pith-number/PT6N5UX3YYYCECOXBXJC7H4P5Q/events.json","paper":"https://pith.science/paper/PT6N5UX3"},"agent_actions":{"view_html":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q","download_json":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q.json","view_paper":"https://pith.science/paper/PT6N5UX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03678&json=true","fetch_graph":"https://pith.science/api/pith-number/PT6N5UX3YYYCECOXBXJC7H4P5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/PT6N5UX3YYYCECOXBXJC7H4P5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q/action/storage_attestation","attest_author":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q/action/author_attestation","sign_citation":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q/action/citation_signature","submit_replication":"https://pith.science/pith/PT6N5UX3YYYCECOXBXJC7H4P5Q/action/replication_record"}},"created_at":"2026-06-03T01:06:04.334041+00:00","updated_at":"2026-06-03T01:06:04.334041+00:00"}