{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6K37AZOVMWNKFMQWSFUFXA2TRM","short_pith_number":"pith:6K37AZOV","schema_version":"1.0","canonical_sha256":"f2b7f065d5659aa2b21691685b83538b362026d5b4e46c4e6268e89c8c9aabb3","source":{"kind":"arxiv","id":"2502.18200","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Semantic Communication with Multimodal Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Deniz G\\\"und\\\"uz, Fengyu Wang, Haotian Wu, Hui Gao, Jiangjing Hu, Wenjing Zhang, Wenjun Xu","submitted_at":"2025-02-25T13:41:06Z","abstract_excerpt":"Most existing semantic communication (SemCom) systems use deep joint source-channel coding (DeepJSCC) to encode task-specific semantics in a goal-oriented manner. However, their reliance on predefined tasks and datasets significantly limits their flexibility and generalizability in practical deployments. Multi-modal foundation models provide a promising solution by generating universal semantic tokens. Inspired by this, we introduce SemCLIP, a zero-shot SemCom framework leveraging the contrastive language-image pre-training (CLIP) model. By transmitting CLIP-generated image tokens instead of r"},"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":"2502.18200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2025-02-25T13:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"36f916f3ba2eb1c3abc368377259f1734e7563b018e951255958ae9e271b30bc","abstract_canon_sha256":"683f814c5f84364c1e0e1f8eb0966a04657ee03e772df79095a34af4ed1bd978"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:42.568820Z","signature_b64":"3EMWdG3Vnrv5AtV+DO2juf1F84GRTttoifkJPAZrgAV/gaZ5S+MlUGPxXyzdqPRr3afuWawXR2g/fwLsaZf/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2b7f065d5659aa2b21691685b83538b362026d5b4e46c4e6268e89c8c9aabb3","last_reissued_at":"2026-07-05T11:11:42.568279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:42.568279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Semantic Communication with Multimodal Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Deniz G\\\"und\\\"uz, Fengyu Wang, Haotian Wu, Hui Gao, Jiangjing Hu, Wenjing Zhang, Wenjun Xu","submitted_at":"2025-02-25T13:41:06Z","abstract_excerpt":"Most existing semantic communication (SemCom) systems use deep joint source-channel coding (DeepJSCC) to encode task-specific semantics in a goal-oriented manner. However, their reliance on predefined tasks and datasets significantly limits their flexibility and generalizability in practical deployments. Multi-modal foundation models provide a promising solution by generating universal semantic tokens. Inspired by this, we introduce SemCLIP, a zero-shot SemCom framework leveraging the contrastive language-image pre-training (CLIP) model. By transmitting CLIP-generated image tokens instead of r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18200","kind":"arxiv","version":2},"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/2502.18200/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":"2502.18200","created_at":"2026-07-05T11:11:42.568336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18200v2","created_at":"2026-07-05T11:11:42.568336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18200","created_at":"2026-07-05T11:11:42.568336+00:00"},{"alias_kind":"pith_short_12","alias_value":"6K37AZOVMWNK","created_at":"2026-07-05T11:11:42.568336+00:00"},{"alias_kind":"pith_short_16","alias_value":"6K37AZOVMWNKFMQW","created_at":"2026-07-05T11:11:42.568336+00:00"},{"alias_kind":"pith_short_8","alias_value":"6K37AZOV","created_at":"2026-07-05T11:11:42.568336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05925","citing_title":"Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM","json":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM.json","graph_json":"https://pith.science/api/pith-number/6K37AZOVMWNKFMQWSFUFXA2TRM/graph.json","events_json":"https://pith.science/api/pith-number/6K37AZOVMWNKFMQWSFUFXA2TRM/events.json","paper":"https://pith.science/paper/6K37AZOV"},"agent_actions":{"view_html":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM","download_json":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM.json","view_paper":"https://pith.science/paper/6K37AZOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18200&json=true","fetch_graph":"https://pith.science/api/pith-number/6K37AZOVMWNKFMQWSFUFXA2TRM/graph.json","fetch_events":"https://pith.science/api/pith-number/6K37AZOVMWNKFMQWSFUFXA2TRM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM/action/storage_attestation","attest_author":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM/action/author_attestation","sign_citation":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM/action/citation_signature","submit_replication":"https://pith.science/pith/6K37AZOVMWNKFMQWSFUFXA2TRM/action/replication_record"}},"created_at":"2026-07-05T11:11:42.568336+00:00","updated_at":"2026-07-05T11:11:42.568336+00:00"}