{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L7MIS2DIEV5RWLYTD5TVSWK7W7","short_pith_number":"pith:L7MIS2DI","schema_version":"1.0","canonical_sha256":"5fd8896868257b1b2f131f6759595fb7cfcc2f8f749f9964eab1636643e133d4","source":{"kind":"arxiv","id":"2405.17267","version":1},"attestation_state":"computed","paper":{"title":"FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lechao Cheng, Meng Wang, Xiaohua Xu, Yaxiong Wang, Yuting Ma, Zhun Zhong","submitted_at":"2024-05-27T15:25:32Z","abstract_excerpt":"Federated learning (FL) is a popular privacy-preserving paradigm that enables distributed clients to collaboratively train models with a central server while keeping raw data locally. In practice, distinct model architectures, varying data distributions, and limited resources across local clients inevitably cause model performance degradation and a slowdown in convergence speed. However, existing FL methods can only solve some of the above heterogeneous challenges and have obvious performance limitations. Notably, a unified framework has not yet been explored to overcome these challenges. Acco"},"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":"2405.17267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:25:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0200999a7cb102912301ce7ad75787e01334c0ec77b8a835815677df1d862b94","abstract_canon_sha256":"37d1c3edff898b87650ec49a5c63f3fa9f0e6c6cc4572191cd4482d54db1b9de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:42.146410Z","signature_b64":"nHC1HW/FQ+qlZvStIYjXGcF9C9fQN87liJIsCiBqWUVqWO586OObRdzhsieotkMTcvPVnLfAlMm30IF62gM7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fd8896868257b1b2f131f6759595fb7cfcc2f8f749f9964eab1636643e133d4","last_reissued_at":"2026-07-05T08:23:42.145874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:42.145874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedHPL: Efficient Heterogeneous Federated Learning with Prompt Tuning and Logit Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lechao Cheng, Meng Wang, Xiaohua Xu, Yaxiong Wang, Yuting Ma, Zhun Zhong","submitted_at":"2024-05-27T15:25:32Z","abstract_excerpt":"Federated learning (FL) is a popular privacy-preserving paradigm that enables distributed clients to collaboratively train models with a central server while keeping raw data locally. In practice, distinct model architectures, varying data distributions, and limited resources across local clients inevitably cause model performance degradation and a slowdown in convergence speed. However, existing FL methods can only solve some of the above heterogeneous challenges and have obvious performance limitations. Notably, a unified framework has not yet been explored to overcome these challenges. Acco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17267","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/2405.17267/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":"2405.17267","created_at":"2026-07-05T08:23:42.145940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17267v1","created_at":"2026-07-05T08:23:42.145940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17267","created_at":"2026-07-05T08:23:42.145940+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7MIS2DIEV5R","created_at":"2026-07-05T08:23:42.145940+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7MIS2DIEV5RWLYT","created_at":"2026-07-05T08:23:42.145940+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7MIS2DI","created_at":"2026-07-05T08:23:42.145940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16690","citing_title":"UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7","json":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7.json","graph_json":"https://pith.science/api/pith-number/L7MIS2DIEV5RWLYTD5TVSWK7W7/graph.json","events_json":"https://pith.science/api/pith-number/L7MIS2DIEV5RWLYTD5TVSWK7W7/events.json","paper":"https://pith.science/paper/L7MIS2DI"},"agent_actions":{"view_html":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7","download_json":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7.json","view_paper":"https://pith.science/paper/L7MIS2DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17267&json=true","fetch_graph":"https://pith.science/api/pith-number/L7MIS2DIEV5RWLYTD5TVSWK7W7/graph.json","fetch_events":"https://pith.science/api/pith-number/L7MIS2DIEV5RWLYTD5TVSWK7W7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7/action/storage_attestation","attest_author":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7/action/author_attestation","sign_citation":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7/action/citation_signature","submit_replication":"https://pith.science/pith/L7MIS2DIEV5RWLYTD5TVSWK7W7/action/replication_record"}},"created_at":"2026-07-05T08:23:42.145940+00:00","updated_at":"2026-07-05T08:23:42.145940+00:00"}