{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WKTD6DFK5DKKCZTVCSJDDSSHIF","short_pith_number":"pith:WKTD6DFK","schema_version":"1.0","canonical_sha256":"b2a63f0caae8d4a16675149231ca474150ee0f52cc072891f46abc61f7eec3a6","source":{"kind":"arxiv","id":"2502.18763","version":1},"attestation_state":"computed","paper":{"title":"CommGPT: A Graph and Retrieval-Augmented Multimodal Communication Foundation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Cunhua Pan, Feibo Jiang, Kezhi Wang, Kun Yang, Li Dong, Octavia A. Dobre, Wanyun Zhu","submitted_at":"2025-02-26T02:44:21Z","abstract_excerpt":"Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain faces three major challenges: 1) Inadequate communication data; 2) Restricted input modalities; and 3) Difficulty in knowledge retrieval. To overcome these issues, we propose CommGPT, a multimodal foundation model designed specifically for communications. First, we create high-quality pretraining and fine-tuning datasets tailored in communication, enabling the LLM to engage in further pretraining and fine-tuning wit"},"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":"2502.18763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2025-02-26T02:44:21Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"cfa19283688a7f637d9755a47fa3bf6df829b5b8a0b446659740a730c8420124","abstract_canon_sha256":"ed56e4afb3cb3488d16de8be55ae1af2242713fdc9fb9795f6d54dc29bcc0d43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:03.266668Z","signature_b64":"nWTZ5OKVAPdYWYB3YUuHLf5OnQAd3jTh1zPdXvLuHy7LnnMulyvKu4XBeq5Hd9KZgqAL04TEXKooPK1lrnCiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a63f0caae8d4a16675149231ca474150ee0f52cc072891f46abc61f7eec3a6","last_reissued_at":"2026-07-05T10:20:03.266175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:03.266175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CommGPT: A Graph and Retrieval-Augmented Multimodal Communication Foundation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Cunhua Pan, Feibo Jiang, Kezhi Wang, Kun Yang, Li Dong, Octavia A. Dobre, Wanyun Zhu","submitted_at":"2025-02-26T02:44:21Z","abstract_excerpt":"Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain faces three major challenges: 1) Inadequate communication data; 2) Restricted input modalities; and 3) Difficulty in knowledge retrieval. To overcome these issues, we propose CommGPT, a multimodal foundation model designed specifically for communications. First, we create high-quality pretraining and fine-tuning datasets tailored in communication, enabling the LLM to engage in further pretraining and fine-tuning wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18763","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/2502.18763/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":"2502.18763","created_at":"2026-07-05T10:20:03.266233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18763v1","created_at":"2026-07-05T10:20:03.266233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18763","created_at":"2026-07-05T10:20:03.266233+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKTD6DFK5DKK","created_at":"2026-07-05T10:20:03.266233+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKTD6DFK5DKKCZTV","created_at":"2026-07-05T10:20:03.266233+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKTD6DFK","created_at":"2026-07-05T10:20:03.266233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22311","citing_title":"From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications","ref_index":94,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF","json":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF.json","graph_json":"https://pith.science/api/pith-number/WKTD6DFK5DKKCZTVCSJDDSSHIF/graph.json","events_json":"https://pith.science/api/pith-number/WKTD6DFK5DKKCZTVCSJDDSSHIF/events.json","paper":"https://pith.science/paper/WKTD6DFK"},"agent_actions":{"view_html":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF","download_json":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF.json","view_paper":"https://pith.science/paper/WKTD6DFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18763&json=true","fetch_graph":"https://pith.science/api/pith-number/WKTD6DFK5DKKCZTVCSJDDSSHIF/graph.json","fetch_events":"https://pith.science/api/pith-number/WKTD6DFK5DKKCZTVCSJDDSSHIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF/action/storage_attestation","attest_author":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF/action/author_attestation","sign_citation":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF/action/citation_signature","submit_replication":"https://pith.science/pith/WKTD6DFK5DKKCZTVCSJDDSSHIF/action/replication_record"}},"created_at":"2026-07-05T10:20:03.266233+00:00","updated_at":"2026-07-05T10:20:03.266233+00:00"}