{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T3TUDI2XSVEYGMQMT36Q7HUBCP","short_pith_number":"pith:T3TUDI2X","schema_version":"1.0","canonical_sha256":"9ee741a357954983320c9efd0f9e8113f0f15f2d8fdf8124369ce9570d1fa06d","source":{"kind":"arxiv","id":"2508.12404","version":1},"attestation_state":"computed","paper":{"title":"LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bozhou Zhang, Jiankang Deng, Li Zhang, Nan Song, Xiatian Zhu","submitted_at":"2025-08-17T15:42:54Z","abstract_excerpt":"Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on on-board multi-view images and scene reasoning text, but this approach often lacks the holistic and nuanced scene recognition and powerful spatial awareness required for autonomous driving, especially in complex situations. To address this gap, we propose a novel vision-language framework tailored for autonomous driving, called LMAD. Our framework emulates modern end-to-end driv"},"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":"2508.12404","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-17T15:42:54Z","cross_cats_sorted":[],"title_canon_sha256":"fbdcc685ca29538d13ba1d6bb1dcae96f8a64e95d0c652de9f3f6f7138aa4063","abstract_canon_sha256":"c71c0f96e1b6afacdf5d6c538ec2b637dd390d37d17b6191b11041f71da6d5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:05.157525Z","signature_b64":"l1J2kBEyC7dpIUjZ41JSCEj1RnP8Ot8ZxSvef7r+ee7ecSRWT125wtpjoBTobkUNukNAvAzmepU36qcKlkVPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee741a357954983320c9efd0f9e8113f0f15f2d8fdf8124369ce9570d1fa06d","last_reissued_at":"2026-07-05T11:55:05.157165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:05.157165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LMAD: Integrated End-to-End Vision-Language Model for Explainable Autonomous Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bozhou Zhang, Jiankang Deng, Li Zhang, Nan Song, Xiatian Zhu","submitted_at":"2025-08-17T15:42:54Z","abstract_excerpt":"Large vision-language models (VLMs) have shown promising capabilities in scene understanding, enhancing the explainability of driving behaviors and interactivity with users. Existing methods primarily fine-tune VLMs on on-board multi-view images and scene reasoning text, but this approach often lacks the holistic and nuanced scene recognition and powerful spatial awareness required for autonomous driving, especially in complex situations. To address this gap, we propose a novel vision-language framework tailored for autonomous driving, called LMAD. Our framework emulates modern end-to-end driv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12404","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/2508.12404/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":"2508.12404","created_at":"2026-07-05T11:55:05.157220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12404v1","created_at":"2026-07-05T11:55:05.157220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12404","created_at":"2026-07-05T11:55:05.157220+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3TUDI2XSVEY","created_at":"2026-07-05T11:55:05.157220+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3TUDI2XSVEYGMQM","created_at":"2026-07-05T11:55:05.157220+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3TUDI2X","created_at":"2026-07-05T11:55:05.157220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18034","citing_title":"Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18034","citing_title":"Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP","json":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP.json","graph_json":"https://pith.science/api/pith-number/T3TUDI2XSVEYGMQMT36Q7HUBCP/graph.json","events_json":"https://pith.science/api/pith-number/T3TUDI2XSVEYGMQMT36Q7HUBCP/events.json","paper":"https://pith.science/paper/T3TUDI2X"},"agent_actions":{"view_html":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP","download_json":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP.json","view_paper":"https://pith.science/paper/T3TUDI2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12404&json=true","fetch_graph":"https://pith.science/api/pith-number/T3TUDI2XSVEYGMQMT36Q7HUBCP/graph.json","fetch_events":"https://pith.science/api/pith-number/T3TUDI2XSVEYGMQMT36Q7HUBCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP/action/storage_attestation","attest_author":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP/action/author_attestation","sign_citation":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP/action/citation_signature","submit_replication":"https://pith.science/pith/T3TUDI2XSVEYGMQMT36Q7HUBCP/action/replication_record"}},"created_at":"2026-07-05T11:55:05.157220+00:00","updated_at":"2026-07-05T11:55:05.157220+00:00"}