{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TXS7T252IN47LYDEDTFUPLXEMC","short_pith_number":"pith:TXS7T252","schema_version":"1.0","canonical_sha256":"9de5f9ebba4379f5e0641ccb47aee460a4fd7ed03e4ca53bec9931e3b5c0e161","source":{"kind":"arxiv","id":"2403.04593","version":1},"attestation_state":"computed","paper":{"title":"Embodied Understanding of Driving Scenarios","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Qiu, Hongyang Li, Hongzi Zhu, Jia Zeng, Linyan Huang, Minyi Guo, Qingwen Bu, Tianyu Li, Yunsong Zhou, Yu Qiao","submitted_at":"2024-03-07T15:39:18Z","abstract_excerpt":"Embodied scene understanding serves as the cornerstone for autonomous agents to perceive, interpret, and respond to open driving scenarios. Such understanding is typically founded upon Vision-Language Models (VLMs). Nevertheless, existing VLMs are restricted to the 2D domain, devoid of spatial awareness and long-horizon extrapolation proficiencies. We revisit the key aspects of autonomous driving and formulate appropriate rubrics. Hereby, we introduce the Embodied Language Model (ELM), a comprehensive framework tailored for agents' understanding of driving scenes with large spatial and tempora"},"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":"2403.04593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-07T15:39:18Z","cross_cats_sorted":[],"title_canon_sha256":"ed3f2a915f1fcceb794995b475641c6356c697252129ddf2e1118cab0e0900f6","abstract_canon_sha256":"22be6bda41c670d9dc54f16a5da3620cb5d6240d04fefe28585fd585ae4c36e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:25.644480Z","signature_b64":"qF+GAirza9HuZYMPKSy7zmDhgl3mHEntEAzRp+zf8fY+vwW1Pq0Zza8700N9hsPrOK6K2ENY9Afp7Z7G0jHUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9de5f9ebba4379f5e0641ccb47aee460a4fd7ed03e4ca53bec9931e3b5c0e161","last_reissued_at":"2026-07-05T07:53:25.643982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:25.643982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Embodied Understanding of Driving Scenarios","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Qiu, Hongyang Li, Hongzi Zhu, Jia Zeng, Linyan Huang, Minyi Guo, Qingwen Bu, Tianyu Li, Yunsong Zhou, Yu Qiao","submitted_at":"2024-03-07T15:39:18Z","abstract_excerpt":"Embodied scene understanding serves as the cornerstone for autonomous agents to perceive, interpret, and respond to open driving scenarios. Such understanding is typically founded upon Vision-Language Models (VLMs). Nevertheless, existing VLMs are restricted to the 2D domain, devoid of spatial awareness and long-horizon extrapolation proficiencies. We revisit the key aspects of autonomous driving and formulate appropriate rubrics. Hereby, we introduce the Embodied Language Model (ELM), a comprehensive framework tailored for agents' understanding of driving scenes with large spatial and tempora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04593","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/2403.04593/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":"2403.04593","created_at":"2026-07-05T07:53:25.644040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04593v1","created_at":"2026-07-05T07:53:25.644040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04593","created_at":"2026-07-05T07:53:25.644040+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXS7T252IN47","created_at":"2026-07-05T07:53:25.644040+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXS7T252IN47LYDE","created_at":"2026-07-05T07:53:25.644040+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXS7T252","created_at":"2026-07-05T07:53:25.644040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00283","citing_title":"What's Hidden Matters: Identifying Planning-Critical Occluded Agents using Vision-Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07608","citing_title":"AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2408.13257","citing_title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2410.22313","citing_title":"Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC","json":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC.json","graph_json":"https://pith.science/api/pith-number/TXS7T252IN47LYDEDTFUPLXEMC/graph.json","events_json":"https://pith.science/api/pith-number/TXS7T252IN47LYDEDTFUPLXEMC/events.json","paper":"https://pith.science/paper/TXS7T252"},"agent_actions":{"view_html":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC","download_json":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC.json","view_paper":"https://pith.science/paper/TXS7T252","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04593&json=true","fetch_graph":"https://pith.science/api/pith-number/TXS7T252IN47LYDEDTFUPLXEMC/graph.json","fetch_events":"https://pith.science/api/pith-number/TXS7T252IN47LYDEDTFUPLXEMC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC/action/storage_attestation","attest_author":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC/action/author_attestation","sign_citation":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC/action/citation_signature","submit_replication":"https://pith.science/pith/TXS7T252IN47LYDEDTFUPLXEMC/action/replication_record"}},"created_at":"2026-07-05T07:53:25.644040+00:00","updated_at":"2026-07-05T07:53:25.644040+00:00"}