{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3IZVEE2S6KV3C3KVNEJCROIEPK","short_pith_number":"pith:3IZVEE2S","schema_version":"1.0","canonical_sha256":"da33521352f2abb16d55691228b9047aa6d02ce1c24a0eeddda5866495bc7b3f","source":{"kind":"arxiv","id":"2512.10719","version":2},"attestation_state":"computed","paper":{"title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Andreas Zell, David Holtz, Hang Yu, Peizheng Li, Rui Song, Yutong Yang, Yuzhi Lai, Zhenghao Zhang","submitted_at":"2025-12-11T14:59:07Z","abstract_excerpt":"End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual understanding and strong reasoning capabilities obtained from the large-scale pretraining. However, we find that current VLMs struggle to understand fine-grained 3D spatial relationships which is a fundamental requirement for systems interacting with the physical world. To address this issue, we propose SpaceDrive, a spatial-aware VLM-based driving framework that treats spatial information as explicit positional encodings (PEs) instead of textual digit "},"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":"2512.10719","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T14:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"f0f0accbc8008c39a774eaa9fdb1969699c6e250a9c0823109619436adf12c4f","abstract_canon_sha256":"0fc2399ed6cd79303ccdd5c110c5de3cd9bf737b803a2dacdcf9278d72fd7fde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:16.405311Z","signature_b64":"APGqWC92Q2j6nt2jKXRiWXATQB6CVtozhF0ETHXYxH3SoSLAuEkRUoWAN09pcACC7UwM6BSYKhyDIoCb1cSXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da33521352f2abb16d55691228b9047aa6d02ce1c24a0eeddda5866495bc7b3f","last_reissued_at":"2026-05-22T01:03:16.404250Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:16.404250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Andreas Zell, David Holtz, Hang Yu, Peizheng Li, Rui Song, Yutong Yang, Yuzhi Lai, Zhenghao Zhang","submitted_at":"2025-12-11T14:59:07Z","abstract_excerpt":"End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual understanding and strong reasoning capabilities obtained from the large-scale pretraining. However, we find that current VLMs struggle to understand fine-grained 3D spatial relationships which is a fundamental requirement for systems interacting with the physical world. To address this issue, we propose SpaceDrive, a spatial-aware VLM-based driving framework that treats spatial information as explicit positional encodings (PEs) instead of textual digit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10719","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/2512.10719/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":"2512.10719","created_at":"2026-05-22T01:03:16.404376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.10719v2","created_at":"2026-05-22T01:03:16.404376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10719","created_at":"2026-05-22T01:03:16.404376+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IZVEE2S6KV3","created_at":"2026-05-22T01:03:16.404376+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IZVEE2S6KV3C3KV","created_at":"2026-05-22T01:03:16.404376+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IZVEE2S","created_at":"2026-05-22T01:03:16.404376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.21139","citing_title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21139","citing_title":"Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14696","citing_title":"EponaV2: Driving World Model with Comprehensive Future Reasoning","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19145","citing_title":"ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18484","citing_title":"XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK","json":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK.json","graph_json":"https://pith.science/api/pith-number/3IZVEE2S6KV3C3KVNEJCROIEPK/graph.json","events_json":"https://pith.science/api/pith-number/3IZVEE2S6KV3C3KVNEJCROIEPK/events.json","paper":"https://pith.science/paper/3IZVEE2S"},"agent_actions":{"view_html":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK","download_json":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK.json","view_paper":"https://pith.science/paper/3IZVEE2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.10719&json=true","fetch_graph":"https://pith.science/api/pith-number/3IZVEE2S6KV3C3KVNEJCROIEPK/graph.json","fetch_events":"https://pith.science/api/pith-number/3IZVEE2S6KV3C3KVNEJCROIEPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK/action/storage_attestation","attest_author":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK/action/author_attestation","sign_citation":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK/action/citation_signature","submit_replication":"https://pith.science/pith/3IZVEE2S6KV3C3KVNEJCROIEPK/action/replication_record"}},"created_at":"2026-05-22T01:03:16.404376+00:00","updated_at":"2026-05-22T01:03:16.404376+00:00"}