{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BAODT3NZE3W3IODTLDYQGDT7NT","short_pith_number":"pith:BAODT3NZ","schema_version":"1.0","canonical_sha256":"081c39edb926edb4387358f1030e7f6ce4be96ef4838eb34180be8158804db1a","source":{"kind":"arxiv","id":"2607.03099","version":1},"attestation_state":"computed","paper":{"title":"AirTF: Over-the-Air Token Fusion for Task-Oriented Multi-Modal Token Communications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"eess.IV","authors_text":"Bole Liu, Li Qiao, Minghui Wu, Yulin Shao, Zhen Gao","submitted_at":"2026-07-03T08:36:07Z","abstract_excerpt":"In the Internet of Vehicles (IoV), transmitting high-dimensional multi-modal sensory data to edge servers for time-sensitive tasks faces severe spectrum bottlenecks. To address this, we propose a foundation model-driven over-the-air token fusion (AirTF) framework for task-oriented multi-modal token communications. Unlike existing schemes for segmentation that rely on convolutional neural networks (CNNs) with limited local receptive fields, AirTF leverages vision transformer (ViT) encoders to extract globally contextualized semantic tokens from distributed heterogeneous sensors. By concurrently"},"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":"2607.03099","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2026-07-03T08:36:07Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"94314960ed479179a79791139a5dcea73ccdd9da4b0a7f432ea8620f5a442925","abstract_canon_sha256":"08f174982401067021251c8cab9e9ca9ef4588a3fd42789debf2022bbf3a2e32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:42.908225Z","signature_b64":"N6ud+ZK5BVpbjW/cDa/EpqMZQKxyDV2z1m51bYiEUEFT3fwaCi1vwVFmu3AaJt7PrOe1ttwi8Im5+rH4S/HaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"081c39edb926edb4387358f1030e7f6ce4be96ef4838eb34180be8158804db1a","last_reissued_at":"2026-07-07T01:16:42.907696Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:42.907696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AirTF: Over-the-Air Token Fusion for Task-Oriented Multi-Modal Token Communications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"eess.IV","authors_text":"Bole Liu, Li Qiao, Minghui Wu, Yulin Shao, Zhen Gao","submitted_at":"2026-07-03T08:36:07Z","abstract_excerpt":"In the Internet of Vehicles (IoV), transmitting high-dimensional multi-modal sensory data to edge servers for time-sensitive tasks faces severe spectrum bottlenecks. To address this, we propose a foundation model-driven over-the-air token fusion (AirTF) framework for task-oriented multi-modal token communications. Unlike existing schemes for segmentation that rely on convolutional neural networks (CNNs) with limited local receptive fields, AirTF leverages vision transformer (ViT) encoders to extract globally contextualized semantic tokens from distributed heterogeneous sensors. By concurrently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03099","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/2607.03099/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":"2607.03099","created_at":"2026-07-07T01:16:42.907769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03099v1","created_at":"2026-07-07T01:16:42.907769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03099","created_at":"2026-07-07T01:16:42.907769+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAODT3NZE3W3","created_at":"2026-07-07T01:16:42.907769+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAODT3NZE3W3IODT","created_at":"2026-07-07T01:16:42.907769+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAODT3NZ","created_at":"2026-07-07T01:16:42.907769+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/BAODT3NZE3W3IODTLDYQGDT7NT","json":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT.json","graph_json":"https://pith.science/api/pith-number/BAODT3NZE3W3IODTLDYQGDT7NT/graph.json","events_json":"https://pith.science/api/pith-number/BAODT3NZE3W3IODTLDYQGDT7NT/events.json","paper":"https://pith.science/paper/BAODT3NZ"},"agent_actions":{"view_html":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT","download_json":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT.json","view_paper":"https://pith.science/paper/BAODT3NZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03099&json=true","fetch_graph":"https://pith.science/api/pith-number/BAODT3NZE3W3IODTLDYQGDT7NT/graph.json","fetch_events":"https://pith.science/api/pith-number/BAODT3NZE3W3IODTLDYQGDT7NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT/action/storage_attestation","attest_author":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT/action/author_attestation","sign_citation":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT/action/citation_signature","submit_replication":"https://pith.science/pith/BAODT3NZE3W3IODTLDYQGDT7NT/action/replication_record"}},"created_at":"2026-07-07T01:16:42.907769+00:00","updated_at":"2026-07-07T01:16:42.907769+00:00"}