{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7GOZOPEB4PCGANVYQO6LSNL6RM","short_pith_number":"pith:7GOZOPEB","schema_version":"1.0","canonical_sha256":"f99d973c81e3c46036b883bcb9357e8b06ec4e594c5a1484c77ef4eaa62532e0","source":{"kind":"arxiv","id":"2412.01812","version":3},"attestation_state":"computed","paper":{"title":"V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Hao Xiang, Jiaqi Ma, Johnson Liu, Maheswari Bajji, Mingyue Lei, Seth Z. Zhao, Tianhui Cai, Xin Xia, Xinyi Liu, Yun Zhang, Zewei Zhou, Zhaoliang Zheng, Zhiyu Huang","submitted_at":"2024-12-02T18:55:34Z","abstract_excerpt":"Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents' information across different spatial locations but ignores temporal cues and temporal tasks (e.g., temporal perception and prediction). In this paper, we focus on the spatio-temporal fusion in V2X scenarios and design one-step and multi-step communication strategies (when to transmit) as well as examine their integration with three fusion strategies - early"},"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":"2412.01812","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:55:34Z","cross_cats_sorted":[],"title_canon_sha256":"7605544648150b2558f3815bcdc2522f6d4cb59f93c2542f7d527f6ed96e2e28","abstract_canon_sha256":"48b10bd56532b97e1a04378b9a464d963c9500f0dfa27a3f68c82856b64a0aef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:05.765610Z","signature_b64":"jGQY/z30gbNykPesJbb7gVkC/mPyDGBqZXIxaPvBXLP5LoINQ65PFaEf7zd/LcJLrMZEWc59AV01nRlp2wvTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f99d973c81e3c46036b883bcb9357e8b06ec4e594c5a1484c77ef4eaa62532e0","last_reissued_at":"2026-07-05T11:49:05.765125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:05.765125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bolei Zhou, Hao Xiang, Jiaqi Ma, Johnson Liu, Maheswari Bajji, Mingyue Lei, Seth Z. Zhao, Tianhui Cai, Xin Xia, Xinyi Liu, Yun Zhang, Zewei Zhou, Zhaoliang Zheng, Zhiyu Huang","submitted_at":"2024-12-02T18:55:34Z","abstract_excerpt":"Vehicle-to-everything (V2X) technologies offer a promising paradigm to mitigate the limitations of constrained observability in single-vehicle systems. Prior work primarily focuses on single-frame cooperative perception, which fuses agents' information across different spatial locations but ignores temporal cues and temporal tasks (e.g., temporal perception and prediction). In this paper, we focus on the spatio-temporal fusion in V2X scenarios and design one-step and multi-step communication strategies (when to transmit) as well as examine their integration with three fusion strategies - early"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01812","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/2412.01812/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":"2412.01812","created_at":"2026-07-05T11:49:05.765179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01812v3","created_at":"2026-07-05T11:49:05.765179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01812","created_at":"2026-07-05T11:49:05.765179+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GOZOPEB4PCG","created_at":"2026-07-05T11:49:05.765179+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GOZOPEB4PCGANVY","created_at":"2026-07-05T11:49:05.765179+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GOZOPEB","created_at":"2026-07-05T11:49:05.765179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.26641","citing_title":"All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehicles","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13757","citing_title":"AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19710","citing_title":"SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM","json":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM.json","graph_json":"https://pith.science/api/pith-number/7GOZOPEB4PCGANVYQO6LSNL6RM/graph.json","events_json":"https://pith.science/api/pith-number/7GOZOPEB4PCGANVYQO6LSNL6RM/events.json","paper":"https://pith.science/paper/7GOZOPEB"},"agent_actions":{"view_html":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM","download_json":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM.json","view_paper":"https://pith.science/paper/7GOZOPEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01812&json=true","fetch_graph":"https://pith.science/api/pith-number/7GOZOPEB4PCGANVYQO6LSNL6RM/graph.json","fetch_events":"https://pith.science/api/pith-number/7GOZOPEB4PCGANVYQO6LSNL6RM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM/action/storage_attestation","attest_author":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM/action/author_attestation","sign_citation":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM/action/citation_signature","submit_replication":"https://pith.science/pith/7GOZOPEB4PCGANVYQO6LSNL6RM/action/replication_record"}},"created_at":"2026-07-05T11:49:05.765179+00:00","updated_at":"2026-07-05T11:49:05.765179+00:00"}