{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YNQGYBBTGFY5HIFTQN7BH4CDQ4","short_pith_number":"pith:YNQGYBBT","schema_version":"1.0","canonical_sha256":"c3606c04333171d3a0b3837e13f043870e96fe991ff6e6002fea7809fa3ab303","source":{"kind":"arxiv","id":"2503.22064","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Semantic Communications via Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Haofeng Sun, Wanli Ni, Xiaoming Tao, Zhijin Qin, Zhu Han","submitted_at":"2025-03-28T00:57:34Z","abstract_excerpt":"Artificial intelligence (AI) promises to revolutionize the design, optimization and management of next-generation communication systems. In this article, we explore the integration of large AI models (LAMs) into semantic communications (SemCom) by leveraging their multi-modal data processing and generation capabilities. Although LAMs bring unprecedented abilities to extract semantics from raw data, this integration entails multifaceted challenges including high resource demands, model complexity, and the need for adaptability across diverse modalities and tasks. To overcome these challenges, w"},"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":"2503.22064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-28T00:57:34Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"21e9c87fea0da3c8fa78e8b14946ffdb4c614e7908d7df4f5c18fa92a53f634d","abstract_canon_sha256":"a59045e0383a6611858831241676ad4ee7d2be37fc439b8df5a509ed0b818bc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:46.673978Z","signature_b64":"1VuMP49ZY7dpn3f904mg3CFHPU9xmefHnGzNfmld8EXXtdWVjPeVRPOBpT1en0lv3BUjsdA6t6MVfz3gQ7hVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3606c04333171d3a0b3837e13f043870e96fe991ff6e6002fea7809fa3ab303","last_reissued_at":"2026-07-05T10:40:46.673507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:46.673507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Semantic Communications via Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Haofeng Sun, Wanli Ni, Xiaoming Tao, Zhijin Qin, Zhu Han","submitted_at":"2025-03-28T00:57:34Z","abstract_excerpt":"Artificial intelligence (AI) promises to revolutionize the design, optimization and management of next-generation communication systems. In this article, we explore the integration of large AI models (LAMs) into semantic communications (SemCom) by leveraging their multi-modal data processing and generation capabilities. Although LAMs bring unprecedented abilities to extract semantics from raw data, this integration entails multifaceted challenges including high resource demands, model complexity, and the need for adaptability across diverse modalities and tasks. To overcome these challenges, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22064","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/2503.22064/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":"2503.22064","created_at":"2026-07-05T10:40:46.673572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22064v1","created_at":"2026-07-05T10:40:46.673572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22064","created_at":"2026-07-05T10:40:46.673572+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNQGYBBTGFY5","created_at":"2026-07-05T10:40:46.673572+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNQGYBBTGFY5HIFT","created_at":"2026-07-05T10:40:46.673572+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNQGYBBT","created_at":"2026-07-05T10:40:46.673572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01728","citing_title":"Token Communication in the Era of Large Models: An Information Bottleneck-Based Approach","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4","json":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4.json","graph_json":"https://pith.science/api/pith-number/YNQGYBBTGFY5HIFTQN7BH4CDQ4/graph.json","events_json":"https://pith.science/api/pith-number/YNQGYBBTGFY5HIFTQN7BH4CDQ4/events.json","paper":"https://pith.science/paper/YNQGYBBT"},"agent_actions":{"view_html":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4","download_json":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4.json","view_paper":"https://pith.science/paper/YNQGYBBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22064&json=true","fetch_graph":"https://pith.science/api/pith-number/YNQGYBBTGFY5HIFTQN7BH4CDQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/YNQGYBBTGFY5HIFTQN7BH4CDQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4/action/storage_attestation","attest_author":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4/action/author_attestation","sign_citation":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4/action/citation_signature","submit_replication":"https://pith.science/pith/YNQGYBBTGFY5HIFTQN7BH4CDQ4/action/replication_record"}},"created_at":"2026-07-05T10:40:46.673572+00:00","updated_at":"2026-07-05T10:40:46.673572+00:00"}