{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2IAPZFB7CGA7GPZQM2RFXHAZD","short_pith_number":"pith:M2IAPZFB","schema_version":"1.0","canonical_sha256":"669007e4a1f88c0f99f9833512dce0c8ed7e0c603e00f9649cc7b119d5bef601","source":{"kind":"arxiv","id":"2408.09251","version":3},"attestation_state":"computed","paper":{"title":"V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bin Ran, Haotian Shi, Junwei You, Keshu Wu, Rui Gan, Xiaopeng Li, Xi Cheng, Zhuoyu Jiang, Zilin Huang","submitted_at":"2024-08-17T16:42:13Z","abstract_excerpt":"Vehicle-to-everything (V2X) cooperation has emerged as a promising paradigm to overcome the perception limitations of classical autonomous driving by leveraging information from both ego-vehicle and infrastructure sensors. However, effectively fusing heterogeneous visual and semantic information while ensuring robust trajectory planning remains a significant challenge. This paper introduces V2X-VLM, a novel end-to-end (E2E) cooperative autonomous driving framework based on vision-language models (VLMs). V2X-VLM integrates multiperspective camera views from vehicles and infrastructure with text"},"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":"2408.09251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-17T16:42:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"80b251bda1c1ab7ffd31c17dae092402a8ebfea8c81ab4a7339fe00e113f1a5e","abstract_canon_sha256":"54e32bea8ebe9c33f2fed60056154d00ec374dcc79c61cdc31da04cb9f828b4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:06.043809Z","signature_b64":"Voae8CQOnW4lJFaxDVZFrFeGqzBjRoKAs8lHphrup3eve0S56KkuN4Ufs+I8MaSLjGzc6oq6vj1wcnvWT7T/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669007e4a1f88c0f99f9833512dce0c8ed7e0c603e00f9649cc7b119d5bef601","last_reissued_at":"2026-07-05T11:24:06.043229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:06.043229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Bin Ran, Haotian Shi, Junwei You, Keshu Wu, Rui Gan, Xiaopeng Li, Xi Cheng, Zhuoyu Jiang, Zilin Huang","submitted_at":"2024-08-17T16:42:13Z","abstract_excerpt":"Vehicle-to-everything (V2X) cooperation has emerged as a promising paradigm to overcome the perception limitations of classical autonomous driving by leveraging information from both ego-vehicle and infrastructure sensors. However, effectively fusing heterogeneous visual and semantic information while ensuring robust trajectory planning remains a significant challenge. This paper introduces V2X-VLM, a novel end-to-end (E2E) cooperative autonomous driving framework based on vision-language models (VLMs). V2X-VLM integrates multiperspective camera views from vehicles and infrastructure with text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09251","kind":"arxiv","version":3},"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/2408.09251/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":"2408.09251","created_at":"2026-07-05T11:24:06.043290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09251v3","created_at":"2026-07-05T11:24:06.043290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09251","created_at":"2026-07-05T11:24:06.043290+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2IAPZFB7CGA","created_at":"2026-07-05T11:24:06.043290+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2IAPZFB7CGA7GPZ","created_at":"2026-07-05T11:24:06.043290+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2IAPZFB","created_at":"2026-07-05T11:24:06.043290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21165","citing_title":"OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00991","citing_title":"Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support","ref_index":122,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD","json":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD.json","graph_json":"https://pith.science/api/pith-number/M2IAPZFB7CGA7GPZQM2RFXHAZD/graph.json","events_json":"https://pith.science/api/pith-number/M2IAPZFB7CGA7GPZQM2RFXHAZD/events.json","paper":"https://pith.science/paper/M2IAPZFB"},"agent_actions":{"view_html":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD","download_json":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD.json","view_paper":"https://pith.science/paper/M2IAPZFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09251&json=true","fetch_graph":"https://pith.science/api/pith-number/M2IAPZFB7CGA7GPZQM2RFXHAZD/graph.json","fetch_events":"https://pith.science/api/pith-number/M2IAPZFB7CGA7GPZQM2RFXHAZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD/action/storage_attestation","attest_author":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD/action/author_attestation","sign_citation":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD/action/citation_signature","submit_replication":"https://pith.science/pith/M2IAPZFB7CGA7GPZQM2RFXHAZD/action/replication_record"}},"created_at":"2026-07-05T11:24:06.043290+00:00","updated_at":"2026-07-05T11:24:06.043290+00:00"}