{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U2EZMMSURYUBSUWYVKCXBMQYBT","short_pith_number":"pith:U2EZMMSU","schema_version":"1.0","canonical_sha256":"a6899632548e281952d8aa8570b2180cea8d63806e97e1b118732a3858f8632e","source":{"kind":"arxiv","id":"2509.03837","version":1},"attestation_state":"computed","paper":{"title":"Vehicle-to-Infrastructure Collaborative Spatial Perception via Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Kimia Ehsani, Walid Saad","submitted_at":"2025-09-04T02:57:47Z","abstract_excerpt":"Accurate prediction of communication link quality metrics is essential for vehicle-to-infrastructure (V2I) systems, enabling smooth handovers, efficient beam management, and reliable low-latency communication. The increasing availability of sensor data from modern vehicles motivates the use of multimodal large language models (MLLMs) because of their adaptability across tasks and reasoning capabilities. However, MLLMs inherently lack three-dimensional spatial understanding. To overcome this limitation, a lightweight, plug-and-play bird's-eye view (BEV) injection connector is proposed. In this "},"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":"2509.03837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T02:57:47Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"a808049501669957216d666c04fd606f0d40d41b7fc3fb390660a7ee826767bd","abstract_canon_sha256":"c61f96b9abb17b0022f313dd71bf4b399ff68733764555f0d239559ecd20ab78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:47.679595Z","signature_b64":"wlkQqtokQcdYZxYBtySWpKvcnnZgw2WxYErmH/5swiE/heNqNk8+hysfTXItNsTV31giyxOqmZuGnrABEHFDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6899632548e281952d8aa8570b2180cea8d63806e97e1b118732a3858f8632e","last_reissued_at":"2026-07-05T12:04:47.679036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:47.679036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vehicle-to-Infrastructure Collaborative Spatial Perception via Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Kimia Ehsani, Walid Saad","submitted_at":"2025-09-04T02:57:47Z","abstract_excerpt":"Accurate prediction of communication link quality metrics is essential for vehicle-to-infrastructure (V2I) systems, enabling smooth handovers, efficient beam management, and reliable low-latency communication. The increasing availability of sensor data from modern vehicles motivates the use of multimodal large language models (MLLMs) because of their adaptability across tasks and reasoning capabilities. However, MLLMs inherently lack three-dimensional spatial understanding. To overcome this limitation, a lightweight, plug-and-play bird's-eye view (BEV) injection connector is proposed. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03837","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/2509.03837/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":"2509.03837","created_at":"2026-07-05T12:04:47.679095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03837v1","created_at":"2026-07-05T12:04:47.679095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03837","created_at":"2026-07-05T12:04:47.679095+00:00"},{"alias_kind":"pith_short_12","alias_value":"U2EZMMSURYUB","created_at":"2026-07-05T12:04:47.679095+00:00"},{"alias_kind":"pith_short_16","alias_value":"U2EZMMSURYUBSUWY","created_at":"2026-07-05T12:04:47.679095+00:00"},{"alias_kind":"pith_short_8","alias_value":"U2EZMMSU","created_at":"2026-07-05T12:04:47.679095+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/U2EZMMSURYUBSUWYVKCXBMQYBT","json":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT.json","graph_json":"https://pith.science/api/pith-number/U2EZMMSURYUBSUWYVKCXBMQYBT/graph.json","events_json":"https://pith.science/api/pith-number/U2EZMMSURYUBSUWYVKCXBMQYBT/events.json","paper":"https://pith.science/paper/U2EZMMSU"},"agent_actions":{"view_html":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT","download_json":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT.json","view_paper":"https://pith.science/paper/U2EZMMSU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03837&json=true","fetch_graph":"https://pith.science/api/pith-number/U2EZMMSURYUBSUWYVKCXBMQYBT/graph.json","fetch_events":"https://pith.science/api/pith-number/U2EZMMSURYUBSUWYVKCXBMQYBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT/action/storage_attestation","attest_author":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT/action/author_attestation","sign_citation":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT/action/citation_signature","submit_replication":"https://pith.science/pith/U2EZMMSURYUBSUWYVKCXBMQYBT/action/replication_record"}},"created_at":"2026-07-05T12:04:47.679095+00:00","updated_at":"2026-07-05T12:04:47.679095+00:00"}