{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4W5GJPK6FUBVA72ZNATEPW4LZ6","short_pith_number":"pith:4W5GJPK6","schema_version":"1.0","canonical_sha256":"e5ba64bd5e2d03507f59682647db8bcfba595a89a2082eba7558cfb55a74fcba","source":{"kind":"arxiv","id":"2507.00082","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dusit Niyato, Faranaksadat Solat, H. Vincent Poor, Joohyung Lee, Mohamed Seif","submitted_at":"2025-06-30T02:56:11Z","abstract_excerpt":"Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers. Unlike traditional end-to-end LLM inference, HLMs reduce latency and communication by invoking LLMs only when local SLM predictions are uncertain, i.e., when token-level confidence is low or entropy is high. However, ambiguous or low-confidence predictions still require frequent offloading to the LLM, leading to significant communication overhead in bandwidth-constrained settings. To address this, we prop"},"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":"2507.00082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T02:56:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2ac2b20b1e04c55fa6503529aba6c31d2aacf0213ffb7ee525e7d85c517b8598","abstract_canon_sha256":"2f83eb729671fd148d9581e006ae8e4e0b3ea3e854775537ea16af61a4a0e029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:36.547805Z","signature_b64":"eTbIZxcV10Dha5vIqmJMYzaNz74us1qAXMtblk05eXClO45mJfeAiBe6w3kIQELsc9UdiAex+CYzgfuGVpQ4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5ba64bd5e2d03507f59682647db8bcfba595a89a2082eba7558cfb55a74fcba","last_reissued_at":"2026-07-05T11:29:36.547266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:36.547266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Dusit Niyato, Faranaksadat Solat, H. Vincent Poor, Joohyung Lee, Mohamed Seif","submitted_at":"2025-06-30T02:56:11Z","abstract_excerpt":"Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers. Unlike traditional end-to-end LLM inference, HLMs reduce latency and communication by invoking LLMs only when local SLM predictions are uncertain, i.e., when token-level confidence is low or entropy is high. However, ambiguous or low-confidence predictions still require frequent offloading to the LLM, leading to significant communication overhead in bandwidth-constrained settings. To address this, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00082","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/2507.00082/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":"2507.00082","created_at":"2026-07-05T11:29:36.547336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00082v1","created_at":"2026-07-05T11:29:36.547336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00082","created_at":"2026-07-05T11:29:36.547336+00:00"},{"alias_kind":"pith_short_12","alias_value":"4W5GJPK6FUBV","created_at":"2026-07-05T11:29:36.547336+00:00"},{"alias_kind":"pith_short_16","alias_value":"4W5GJPK6FUBVA72Z","created_at":"2026-07-05T11:29:36.547336+00:00"},{"alias_kind":"pith_short_8","alias_value":"4W5GJPK6","created_at":"2026-07-05T11:29:36.547336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6","json":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6.json","graph_json":"https://pith.science/api/pith-number/4W5GJPK6FUBVA72ZNATEPW4LZ6/graph.json","events_json":"https://pith.science/api/pith-number/4W5GJPK6FUBVA72ZNATEPW4LZ6/events.json","paper":"https://pith.science/paper/4W5GJPK6"},"agent_actions":{"view_html":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6","download_json":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6.json","view_paper":"https://pith.science/paper/4W5GJPK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00082&json=true","fetch_graph":"https://pith.science/api/pith-number/4W5GJPK6FUBVA72ZNATEPW4LZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/4W5GJPK6FUBVA72ZNATEPW4LZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6/action/storage_attestation","attest_author":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6/action/author_attestation","sign_citation":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6/action/citation_signature","submit_replication":"https://pith.science/pith/4W5GJPK6FUBVA72ZNATEPW4LZ6/action/replication_record"}},"created_at":"2026-07-05T11:29:36.547336+00:00","updated_at":"2026-07-05T11:29:36.547336+00:00"}