{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T2Y4DKBKSPRY3OGKF2RTX6A7RU","short_pith_number":"pith:T2Y4DKBK","schema_version":"1.0","canonical_sha256":"9eb1c1a82a93e38db8ca2ea33bf81f8d18a6bc6b32adb0f084ada6d927cd4802","source":{"kind":"arxiv","id":"2304.10628","version":1},"attestation_state":"computed","paper":{"title":"HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Xiang, Jiaqi Ma, Runsheng Xu","submitted_at":"2023-04-20T20:09:59Z","abstract_excerpt":"Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are equipped with the same type of sensors, which significantly hampers the scale of collaboration and benefit of cross-modality interactions. In this paper, we investigate the multi-agent hetero-modal cooperative perception problem where agents may have distinct sensor modalities. We present HM-ViT, the first unified multi-agent hetero-modal cooperative perceptio"},"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":"2304.10628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-20T20:09:59Z","cross_cats_sorted":[],"title_canon_sha256":"635bc9b4a0a9368e3ea41ff1cda3506ddbba943078feb0726f1f99356faed7bf","abstract_canon_sha256":"85fb3371c17ec05f0392cd7171a0d78807e24d2357ac0eaf5122c77f3baf0257"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:13.406582Z","signature_b64":"YAlAb2HAI7lvfgO2/GYtncenzvy9RNXgKuL4AKQ7O3hHFj2fekuZ20ju+QAQPv0Ns0B9bp7ykw5Hqo639+uQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb1c1a82a93e38db8ca2ea33bf81f8d18a6bc6b32adb0f084ada6d927cd4802","last_reissued_at":"2026-07-05T06:03:13.406209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:13.406209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Xiang, Jiaqi Ma, Runsheng Xu","submitted_at":"2023-04-20T20:09:59Z","abstract_excerpt":"Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are equipped with the same type of sensors, which significantly hampers the scale of collaboration and benefit of cross-modality interactions. In this paper, we investigate the multi-agent hetero-modal cooperative perception problem where agents may have distinct sensor modalities. We present HM-ViT, the first unified multi-agent hetero-modal cooperative perceptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10628","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/2304.10628/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":"2304.10628","created_at":"2026-07-05T06:03:13.406275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10628v1","created_at":"2026-07-05T06:03:13.406275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10628","created_at":"2026-07-05T06:03:13.406275+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2Y4DKBKSPRY","created_at":"2026-07-05T06:03:13.406275+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2Y4DKBKSPRY3OGK","created_at":"2026-07-05T06:03:13.406275+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2Y4DKBK","created_at":"2026-07-05T06:03:13.406275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01812","citing_title":"V2XPnP: Vehicle-to-Everything Spatio-Temporal Fusion for Multi-Agent Perception and Prediction","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU","json":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU.json","graph_json":"https://pith.science/api/pith-number/T2Y4DKBKSPRY3OGKF2RTX6A7RU/graph.json","events_json":"https://pith.science/api/pith-number/T2Y4DKBKSPRY3OGKF2RTX6A7RU/events.json","paper":"https://pith.science/paper/T2Y4DKBK"},"agent_actions":{"view_html":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU","download_json":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU.json","view_paper":"https://pith.science/paper/T2Y4DKBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10628&json=true","fetch_graph":"https://pith.science/api/pith-number/T2Y4DKBKSPRY3OGKF2RTX6A7RU/graph.json","fetch_events":"https://pith.science/api/pith-number/T2Y4DKBKSPRY3OGKF2RTX6A7RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU/action/storage_attestation","attest_author":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU/action/author_attestation","sign_citation":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU/action/citation_signature","submit_replication":"https://pith.science/pith/T2Y4DKBKSPRY3OGKF2RTX6A7RU/action/replication_record"}},"created_at":"2026-07-05T06:03:13.406275+00:00","updated_at":"2026-07-05T06:03:13.406275+00:00"}