{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6QYN4KXG5ACS4UHKQRGIE2RMGH","short_pith_number":"pith:6QYN4KXG","schema_version":"1.0","canonical_sha256":"f430de2ae6e8052e50ea844c826a2c31d67a9349a482aa8d9187978604211196","source":{"kind":"arxiv","id":"2407.09424","version":1},"attestation_state":"computed","paper":{"title":"TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.SP","authors_text":"Faouzi Bader, Hang Zou, Lina Bariah, Merouane Debbah, Qiyang Zhao, Thierry Lestable, Yu Tian","submitted_at":"2024-07-12T16:51:02Z","abstract_excerpt":"Large Language Models (LLMs) have the potential to revolutionize the Sixth Generation (6G) communication networks. However, current mainstream LLMs generally lack the specialized knowledge in telecom domain. In this paper, for the first time, we propose a pipeline to adapt any general purpose LLMs to a telecom-specific LLMs. We collect and build telecom-specific pre-train dataset, instruction dataset, preference dataset to perform continual pre-training, instruct tuning and alignment tuning respectively. Besides, due to the lack of widely accepted evaluation benchmarks in telecom domain, we ex"},"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":"2407.09424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.SP","submitted_at":"2024-07-12T16:51:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ee72bdc6bfd7914c95d1cd5da372da4f4a87244eb42ef69e6d948f0ce4e3e7c","abstract_canon_sha256":"61d51b02cac1a9cec984aacb40d0fb13fb75a81bcf1421d45fd670be51b5139e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:18.940575Z","signature_b64":"CHbUaeDDN2KW+gKUWiIbvHbBjRXlxPJP5HutEbRA8zBW2+L1c6Hrx830RCp/lVHqEvtYuCu2K8L7vckVqqffAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f430de2ae6e8052e50ea844c826a2c31d67a9349a482aa8d9187978604211196","last_reissued_at":"2026-07-05T08:43:18.940142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:18.940142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.SP","authors_text":"Faouzi Bader, Hang Zou, Lina Bariah, Merouane Debbah, Qiyang Zhao, Thierry Lestable, Yu Tian","submitted_at":"2024-07-12T16:51:02Z","abstract_excerpt":"Large Language Models (LLMs) have the potential to revolutionize the Sixth Generation (6G) communication networks. However, current mainstream LLMs generally lack the specialized knowledge in telecom domain. In this paper, for the first time, we propose a pipeline to adapt any general purpose LLMs to a telecom-specific LLMs. We collect and build telecom-specific pre-train dataset, instruction dataset, preference dataset to perform continual pre-training, instruct tuning and alignment tuning respectively. Besides, due to the lack of widely accepted evaluation benchmarks in telecom domain, we ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09424","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/2407.09424/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":"2407.09424","created_at":"2026-07-05T08:43:18.940206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09424v1","created_at":"2026-07-05T08:43:18.940206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09424","created_at":"2026-07-05T08:43:18.940206+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QYN4KXG5ACS","created_at":"2026-07-05T08:43:18.940206+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QYN4KXG5ACS4UHK","created_at":"2026-07-05T08:43:18.940206+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QYN4KXG","created_at":"2026-07-05T08:43:18.940206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13131","citing_title":"MM-Telco: Benchmarks and Multimodal Large Language Models for Telecom Applications","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03774","citing_title":"When Does Multimodal AI Help? Diagnostic Complementarity of Vision-Language Models and CNNs for Spectrum Management in Satellite-Terrestrial Networks","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH","json":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH.json","graph_json":"https://pith.science/api/pith-number/6QYN4KXG5ACS4UHKQRGIE2RMGH/graph.json","events_json":"https://pith.science/api/pith-number/6QYN4KXG5ACS4UHKQRGIE2RMGH/events.json","paper":"https://pith.science/paper/6QYN4KXG"},"agent_actions":{"view_html":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH","download_json":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH.json","view_paper":"https://pith.science/paper/6QYN4KXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09424&json=true","fetch_graph":"https://pith.science/api/pith-number/6QYN4KXG5ACS4UHKQRGIE2RMGH/graph.json","fetch_events":"https://pith.science/api/pith-number/6QYN4KXG5ACS4UHKQRGIE2RMGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH/action/storage_attestation","attest_author":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH/action/author_attestation","sign_citation":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH/action/citation_signature","submit_replication":"https://pith.science/pith/6QYN4KXG5ACS4UHKQRGIE2RMGH/action/replication_record"}},"created_at":"2026-07-05T08:43:18.940206+00:00","updated_at":"2026-07-05T08:43:18.940206+00:00"}