{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F3AAMTOHHBR6I6XMSIC6DWR5CW","short_pith_number":"pith:F3AAMTOH","schema_version":"1.0","canonical_sha256":"2ec0064dc73863e47aec9205e1da3d15917b48982713c3a56ade807c822fa469","source":{"kind":"arxiv","id":"2409.09715","version":3},"attestation_state":"computed","paper":{"title":"Generative Semantic Communication via Textual Prompts: Latency Performance Tradeoffs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.IT"],"primary_cat":"cs.IT","authors_text":"Jian Chen, Li Qiao, Long Yang, Mahdi Boloursaz Mashhadi, Mehdi Bennis, Mengmeng Ren, Pei Xiao, Rahim Tafazolli, Zhen Gao","submitted_at":"2024-09-15T12:46:39Z","abstract_excerpt":"This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The proposed framework optimizes the use of M/VLMs on the wireless edge/device to generate high-fidelity textual prompts through visual captioning/question answering, which are then transmitted over a wireless channel for SemCom. Specifically, we develop a multi-user Gen SemCom framework using pre-trained M/VLMs, and formulate a joint optimization problem of pr"},"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":"2409.09715","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2024-09-15T12:46:39Z","cross_cats_sorted":["cs.GT","math.IT"],"title_canon_sha256":"4bd3bdf255eaf4067000d88f198f77fa8ead4611c40a34af4cbcca571ad25605","abstract_canon_sha256":"b205854c2e50902b8c0827a9cef367f8974aa0a2da43b33c2a2bdda081b35fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:28.392002Z","signature_b64":"qptcJbJEnOQiLgsd11Le7KaLZZphjDX47PZwbouCQyxYWPonESldHKhj4Pk5SIb7fxmk6v3kse6LOu9lS5ezDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ec0064dc73863e47aec9205e1da3d15917b48982713c3a56ade807c822fa469","last_reissued_at":"2026-07-05T10:57:28.391435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:28.391435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Semantic Communication via Textual Prompts: Latency Performance Tradeoffs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","math.IT"],"primary_cat":"cs.IT","authors_text":"Jian Chen, Li Qiao, Long Yang, Mahdi Boloursaz Mashhadi, Mehdi Bennis, Mengmeng Ren, Pei Xiao, Rahim Tafazolli, Zhen Gao","submitted_at":"2024-09-15T12:46:39Z","abstract_excerpt":"This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The proposed framework optimizes the use of M/VLMs on the wireless edge/device to generate high-fidelity textual prompts through visual captioning/question answering, which are then transmitted over a wireless channel for SemCom. Specifically, we develop a multi-user Gen SemCom framework using pre-trained M/VLMs, and formulate a joint optimization problem of pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09715","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/2409.09715/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":"2409.09715","created_at":"2026-07-05T10:57:28.391489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09715v3","created_at":"2026-07-05T10:57:28.391489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09715","created_at":"2026-07-05T10:57:28.391489+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3AAMTOHHBR6","created_at":"2026-07-05T10:57:28.391489+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3AAMTOHHBR6I6XM","created_at":"2026-07-05T10:57:28.391489+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3AAMTOH","created_at":"2026-07-05T10:57:28.391489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07573","citing_title":"Enhancing Mega-Satellite Networks with Generative Semantic Communication: A Networking Perspective","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW","json":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW.json","graph_json":"https://pith.science/api/pith-number/F3AAMTOHHBR6I6XMSIC6DWR5CW/graph.json","events_json":"https://pith.science/api/pith-number/F3AAMTOHHBR6I6XMSIC6DWR5CW/events.json","paper":"https://pith.science/paper/F3AAMTOH"},"agent_actions":{"view_html":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW","download_json":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW.json","view_paper":"https://pith.science/paper/F3AAMTOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09715&json=true","fetch_graph":"https://pith.science/api/pith-number/F3AAMTOHHBR6I6XMSIC6DWR5CW/graph.json","fetch_events":"https://pith.science/api/pith-number/F3AAMTOHHBR6I6XMSIC6DWR5CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW/action/storage_attestation","attest_author":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW/action/author_attestation","sign_citation":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW/action/citation_signature","submit_replication":"https://pith.science/pith/F3AAMTOHHBR6I6XMSIC6DWR5CW/action/replication_record"}},"created_at":"2026-07-05T10:57:28.391489+00:00","updated_at":"2026-07-05T10:57:28.391489+00:00"}