{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YQIX53HZKHNG3MJHKQSZYCGW3D","short_pith_number":"pith:YQIX53HZ","schema_version":"1.0","canonical_sha256":"c4117eecf951da6db12754259c08d6d8e97927bd7f00eaa4d54052e63d438ad4","source":{"kind":"arxiv","id":"2404.10595","version":5},"attestation_state":"computed","paper":{"title":"Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dit-Yan Yeung, Huchuan Lu, Kai Chen, Lanqing Hong, Meng Tian, Pengxiang Li, Ruiyuan Gao, Wenhua Zhang, Xinhai Zhao, Xu Jia, Yanxin Liu, Yanze Li, Zhenguo Li","submitted_at":"2024-04-16T14:20:55Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have received widespread attention for advancing the interpretable self-driving. Existing evaluations of LVLMs primarily focus on multi-faceted capabilities in natural circumstances, lacking automated and quantifiable assessment for self-driving, let alone the severe road corner cases. In this work, we propose CODA-LM, the very first benchmark for the automatic evaluation of LVLMs for self-driving corner cases. We adopt a hierarchical data structure and prompt powerful LVLMs to analyze complex driving scenes and generate high-quality pre-annotations for the"},"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":"2404.10595","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T14:20:55Z","cross_cats_sorted":[],"title_canon_sha256":"5389ccd86764e5619ecb3c1d0c4c44501669af2fa795c12a8ebb209bc28dc885","abstract_canon_sha256":"4802bdc3460792450a24d013be102ee1f3394bd582e43556195880b5724777af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:09.568777Z","signature_b64":"FO10LtkH+Lzr6/NVCm4fyW1n8jfhgR57Z4d9L+33b3uNKQylL0jh/1xZgXDjOxX3tf0LRx0GQ1Ix+VfgzKl7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4117eecf951da6db12754259c08d6d8e97927bd7f00eaa4d54052e63d438ad4","last_reissued_at":"2026-07-05T09:45:09.568276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:09.568276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dit-Yan Yeung, Huchuan Lu, Kai Chen, Lanqing Hong, Meng Tian, Pengxiang Li, Ruiyuan Gao, Wenhua Zhang, Xinhai Zhao, Xu Jia, Yanxin Liu, Yanze Li, Zhenguo Li","submitted_at":"2024-04-16T14:20:55Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have received widespread attention for advancing the interpretable self-driving. Existing evaluations of LVLMs primarily focus on multi-faceted capabilities in natural circumstances, lacking automated and quantifiable assessment for self-driving, let alone the severe road corner cases. In this work, we propose CODA-LM, the very first benchmark for the automatic evaluation of LVLMs for self-driving corner cases. We adopt a hierarchical data structure and prompt powerful LVLMs to analyze complex driving scenes and generate high-quality pre-annotations for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10595","kind":"arxiv","version":5},"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/2404.10595/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":"2404.10595","created_at":"2026-07-05T09:45:09.568344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10595v5","created_at":"2026-07-05T09:45:09.568344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10595","created_at":"2026-07-05T09:45:09.568344+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQIX53HZKHNG","created_at":"2026-07-05T09:45:09.568344+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQIX53HZKHNG3MJH","created_at":"2026-07-05T09:45:09.568344+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQIX53HZ","created_at":"2026-07-05T09:45:09.568344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22913","citing_title":"Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08052","citing_title":"ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D","json":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D.json","graph_json":"https://pith.science/api/pith-number/YQIX53HZKHNG3MJHKQSZYCGW3D/graph.json","events_json":"https://pith.science/api/pith-number/YQIX53HZKHNG3MJHKQSZYCGW3D/events.json","paper":"https://pith.science/paper/YQIX53HZ"},"agent_actions":{"view_html":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D","download_json":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D.json","view_paper":"https://pith.science/paper/YQIX53HZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10595&json=true","fetch_graph":"https://pith.science/api/pith-number/YQIX53HZKHNG3MJHKQSZYCGW3D/graph.json","fetch_events":"https://pith.science/api/pith-number/YQIX53HZKHNG3MJHKQSZYCGW3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D/action/storage_attestation","attest_author":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D/action/author_attestation","sign_citation":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D/action/citation_signature","submit_replication":"https://pith.science/pith/YQIX53HZKHNG3MJHKQSZYCGW3D/action/replication_record"}},"created_at":"2026-07-05T09:45:09.568344+00:00","updated_at":"2026-07-05T09:45:09.568344+00:00"}