{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LR5TWA5ZP3VDQVBNKEVIBCPV4J","short_pith_number":"pith:LR5TWA5Z","schema_version":"1.0","canonical_sha256":"5c7b3b03b97eea38542d512a8089f5e2711f8b07b4dfab6240b2bd2e59486016","source":{"kind":"arxiv","id":"2506.05442","version":2},"attestation_state":"computed","paper":{"title":"Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuan Hu, Hao Jiang, Ke Wang, Xi Zhang, Yuan He, Yukang Shi, Zhipeng Zhang","submitted_at":"2025-06-05T12:59:35Z","abstract_excerpt":"Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications. One major limitation is that existing datasets with loosely formatted language descriptions are not machine-friendly and may introduce redundancy. Additionally, high computational cost and massive scale of VLMs hinder the inference speed and real-world deployment. To bridge the gap, this paper introduces a structured and concise benchmark dataset, NuScenes-"},"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":"2506.05442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T12:59:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c60b7dd3f3ef144d5e7e271f7b3be1f806ce5be22b57e41ccb2266b596b32505","abstract_canon_sha256":"851cf821e6f1c4aee83a22bbc79db84e77a1809de990d31fdbdf40bfac7a58d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:50.978701Z","signature_b64":"C9CFBs2o9WCAoy1G5Sqt3HiDlvuvPoSaasIX+KpzT4Gd6fUPIp5H0croC0xW9olPh/zBu7Ue546AAU1h6i8qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7b3b03b97eea38542d512a8089f5e2711f8b07b4dfab6240b2bd2e59486016","last_reissued_at":"2026-05-20T00:02:50.977860Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:50.977860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuan Hu, Hao Jiang, Ke Wang, Xi Zhang, Yuan He, Yukang Shi, Zhipeng Zhang","submitted_at":"2025-06-05T12:59:35Z","abstract_excerpt":"Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications. One major limitation is that existing datasets with loosely formatted language descriptions are not machine-friendly and may introduce redundancy. Additionally, high computational cost and massive scale of VLMs hinder the inference speed and real-world deployment. To bridge the gap, this paper introduces a structured and concise benchmark dataset, NuScenes-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05442","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/2506.05442/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":"2506.05442","created_at":"2026-05-20T00:02:50.977998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05442v2","created_at":"2026-05-20T00:02:50.977998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05442","created_at":"2026-05-20T00:02:50.977998+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR5TWA5ZP3VD","created_at":"2026-05-20T00:02:50.977998+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR5TWA5ZP3VDQVBN","created_at":"2026-05-20T00:02:50.977998+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR5TWA5Z","created_at":"2026-05-20T00:02:50.977998+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/LR5TWA5ZP3VDQVBNKEVIBCPV4J","json":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J.json","graph_json":"https://pith.science/api/pith-number/LR5TWA5ZP3VDQVBNKEVIBCPV4J/graph.json","events_json":"https://pith.science/api/pith-number/LR5TWA5ZP3VDQVBNKEVIBCPV4J/events.json","paper":"https://pith.science/paper/LR5TWA5Z"},"agent_actions":{"view_html":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J","download_json":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J.json","view_paper":"https://pith.science/paper/LR5TWA5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05442&json=true","fetch_graph":"https://pith.science/api/pith-number/LR5TWA5ZP3VDQVBNKEVIBCPV4J/graph.json","fetch_events":"https://pith.science/api/pith-number/LR5TWA5ZP3VDQVBNKEVIBCPV4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J/action/storage_attestation","attest_author":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J/action/author_attestation","sign_citation":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J/action/citation_signature","submit_replication":"https://pith.science/pith/LR5TWA5ZP3VDQVBNKEVIBCPV4J/action/replication_record"}},"created_at":"2026-05-20T00:02:50.977998+00:00","updated_at":"2026-05-20T00:02:50.977998+00:00"}