{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X22SQRBKYI25VU3SDGMBBKSZ27","short_pith_number":"pith:X22SQRBK","schema_version":"1.0","canonical_sha256":"beb528442ac235dad372199810aa59d7c26d62929919b69c0d154fba0efb713b","source":{"kind":"arxiv","id":"2512.21831","version":2},"attestation_state":"computed","paper":{"title":"End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weidong Zhang, Yibo Ai, Zhenwei Yang","submitted_at":"2025-12-26T02:20:22Z","abstract_excerpt":"Multiview cooperative perception and multimodal fusion are essential for reliable 3-D spatiotemporal understanding in autonomous driving, especially in cases with occlusions, limited viewpoints, and communication delays in vehicle-to-everything (V2X) scenarios. In this paper, Cross-modal End-to-End Tracking for V2X (XET-V2X), a multimodal fused end-to-end tracking framework for V2X collaboration that unifies multiview multimodal sensing within a shared spatiotemporal representation, is proposed. To efficiently align heterogeneous viewpoints and modalities, XET-V2X introduces a dual-layer spati"},"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":"2512.21831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-26T02:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"9b749fdaf232de6c0be28b6fc3eafcff8627a4149a45156552399e6d2b5ee70c","abstract_canon_sha256":"1e7c950ad9ca6005357e9f1880a9d95e790a7f987231c2e76c4a180b4eb1ae76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:24:27.354740Z","signature_b64":"RyZ5BYk7FiBYL4sDakNUVFatNuc44YzsyjthU5an7763BstbRNiZEyF+f6NPqi/nwj9zTYeIzuIaeqqF1rlMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"beb528442ac235dad372199810aa59d7c26d62929919b69c0d154fba0efb713b","last_reissued_at":"2026-07-29T01:24:27.353795Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:24:27.353795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End 3-D Spatiotemporal Perception with Multimodal Fusion and V2X Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weidong Zhang, Yibo Ai, Zhenwei Yang","submitted_at":"2025-12-26T02:20:22Z","abstract_excerpt":"Multiview cooperative perception and multimodal fusion are essential for reliable 3-D spatiotemporal understanding in autonomous driving, especially in cases with occlusions, limited viewpoints, and communication delays in vehicle-to-everything (V2X) scenarios. In this paper, Cross-modal End-to-End Tracking for V2X (XET-V2X), a multimodal fused end-to-end tracking framework for V2X collaboration that unifies multiview multimodal sensing within a shared spatiotemporal representation, is proposed. To efficiently align heterogeneous viewpoints and modalities, XET-V2X introduces a dual-layer spati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.21831","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/2512.21831/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":"2512.21831","created_at":"2026-07-29T01:24:27.354235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.21831v2","created_at":"2026-07-29T01:24:27.354235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.21831","created_at":"2026-07-29T01:24:27.354235+00:00"},{"alias_kind":"pith_short_12","alias_value":"X22SQRBKYI25","created_at":"2026-07-29T01:24:27.354235+00:00"},{"alias_kind":"pith_short_16","alias_value":"X22SQRBKYI25VU3S","created_at":"2026-07-29T01:24:27.354235+00:00"},{"alias_kind":"pith_short_8","alias_value":"X22SQRBK","created_at":"2026-07-29T01:24:27.354235+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/X22SQRBKYI25VU3SDGMBBKSZ27","json":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27.json","graph_json":"https://pith.science/api/pith-number/X22SQRBKYI25VU3SDGMBBKSZ27/graph.json","events_json":"https://pith.science/api/pith-number/X22SQRBKYI25VU3SDGMBBKSZ27/events.json","paper":"https://pith.science/paper/X22SQRBK"},"agent_actions":{"view_html":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27","download_json":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27.json","view_paper":"https://pith.science/paper/X22SQRBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.21831&json=true","fetch_graph":"https://pith.science/api/pith-number/X22SQRBKYI25VU3SDGMBBKSZ27/graph.json","fetch_events":"https://pith.science/api/pith-number/X22SQRBKYI25VU3SDGMBBKSZ27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27/action/storage_attestation","attest_author":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27/action/author_attestation","sign_citation":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27/action/citation_signature","submit_replication":"https://pith.science/pith/X22SQRBKYI25VU3SDGMBBKSZ27/action/replication_record"}},"created_at":"2026-07-29T01:24:27.354235+00:00","updated_at":"2026-07-29T01:24:27.354235+00:00"}