{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7HGEODOF5CWA5EFQVGYFYIU6GI","short_pith_number":"pith:7HGEODOF","schema_version":"1.0","canonical_sha256":"f9cc470dc5e8ac0e90b0a9b05c229e3208a5b1ac2bcc06dc096ff84b3198a7ce","source":{"kind":"arxiv","id":"2505.23801","version":1},"attestation_state":"computed","paper":{"title":"SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Muhammad Sohail, Nauman Ali Khan, Sajid Hussain","submitted_at":"2025-05-26T20:58:13Z","abstract_excerpt":"Background: Federated Learning (FL) has emerged as a promising paradigm for training machine learning models while preserving data privacy. However, applying FL to Natural Language Processing (NLP) tasks presents unique challenges due to semantic heterogeneity across clients, vocabulary mismatches, and varying resource constraints on edge devices. Objectives: This paper introduces SEMFED, a novel semantic-aware resource-efficient federated learning framework specifically designed for heterogeneous NLP tasks. Methods: SEMFED incorporates three key innovations: (1) a semantic-aware client select"},"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":"2505.23801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T20:58:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3a25b0af7188a8142a74f2ec21c0ef3a46306325e5f295bf1a47790d467776bc","abstract_canon_sha256":"ae823377d73d26c77179b4d9a826891bbe3220e83508a836125bd83f13c44b92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:35.685580Z","signature_b64":"FDQXSByi2XMh74DENiNHJziJTOkAH+WBVxG3GE0MOpUeqGLOle+Q+2yyic8aH2OokL0oj/dPuQ9pKQTqu0+GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9cc470dc5e8ac0e90b0a9b05c229e3208a5b1ac2bcc06dc096ff84b3198a7ce","last_reissued_at":"2026-07-05T11:12:35.685000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:35.685000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Muhammad Sohail, Nauman Ali Khan, Sajid Hussain","submitted_at":"2025-05-26T20:58:13Z","abstract_excerpt":"Background: Federated Learning (FL) has emerged as a promising paradigm for training machine learning models while preserving data privacy. However, applying FL to Natural Language Processing (NLP) tasks presents unique challenges due to semantic heterogeneity across clients, vocabulary mismatches, and varying resource constraints on edge devices. Objectives: This paper introduces SEMFED, a novel semantic-aware resource-efficient federated learning framework specifically designed for heterogeneous NLP tasks. Methods: SEMFED incorporates three key innovations: (1) a semantic-aware client select"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23801","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/2505.23801/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":"2505.23801","created_at":"2026-07-05T11:12:35.685064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23801v1","created_at":"2026-07-05T11:12:35.685064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23801","created_at":"2026-07-05T11:12:35.685064+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HGEODOF5CWA","created_at":"2026-07-05T11:12:35.685064+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HGEODOF5CWA5EFQ","created_at":"2026-07-05T11:12:35.685064+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HGEODOF","created_at":"2026-07-05T11:12:35.685064+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/7HGEODOF5CWA5EFQVGYFYIU6GI","json":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI.json","graph_json":"https://pith.science/api/pith-number/7HGEODOF5CWA5EFQVGYFYIU6GI/graph.json","events_json":"https://pith.science/api/pith-number/7HGEODOF5CWA5EFQVGYFYIU6GI/events.json","paper":"https://pith.science/paper/7HGEODOF"},"agent_actions":{"view_html":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI","download_json":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI.json","view_paper":"https://pith.science/paper/7HGEODOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23801&json=true","fetch_graph":"https://pith.science/api/pith-number/7HGEODOF5CWA5EFQVGYFYIU6GI/graph.json","fetch_events":"https://pith.science/api/pith-number/7HGEODOF5CWA5EFQVGYFYIU6GI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI/action/storage_attestation","attest_author":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI/action/author_attestation","sign_citation":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI/action/citation_signature","submit_replication":"https://pith.science/pith/7HGEODOF5CWA5EFQVGYFYIU6GI/action/replication_record"}},"created_at":"2026-07-05T11:12:35.685064+00:00","updated_at":"2026-07-05T11:12:35.685064+00:00"}