{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IV7ECLCT3KWEQOB7EG5PJ72NLZ","short_pith_number":"pith:IV7ECLCT","schema_version":"1.0","canonical_sha256":"457e412c53daac48383f21baf4ff4d5e5ea5f52f32dc3c5aa07fa9dc2dd1de83","source":{"kind":"arxiv","id":"2412.07216","version":3},"attestation_state":"computed","paper":{"title":"Learnable Sparse Customization in Heterogeneous Edge Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Jingjing Xue, Jingyuan Wang, Min Liu, Sheng Sun, Yuwei Wang, Zhuotao Liu","submitted_at":"2024-12-10T06:14:31Z","abstract_excerpt":"To effectively manage and utilize massive distributed data at the network edge, Federated Learning (FL) has emerged as a promising edge computing paradigm across data silos. However, FL still faces two challenges: system heterogeneity (i.e., the diversity of hardware resources across edge devices) and statistical heterogeneity (i.e., non-IID data). Although sparsification can extract diverse submodels for diverse clients, most sparse FL works either simply assign submodels with artificially-given rigid rules or prune partial parameters using heuristic strategies, resulting in inflexible sparsi"},"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":"2412.07216","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-12-10T06:14:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c2a8fe3e09b1e409a5d05e3a488095fea8c78af8ac08acb4418ff4da04356074","abstract_canon_sha256":"15bdc4272a56426fd4ace6bbc1e45f07a533a32b09d6071e958cc25b5a376fe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:15.140604Z","signature_b64":"NR7ec1EPlohOdtCYAtdxqKQTis1tar50WSHzNFgvGf8FrMEogsrFufWzc0qVbp/UzowL4moq2bMfdIHkNwJ3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457e412c53daac48383f21baf4ff4d5e5ea5f52f32dc3c5aa07fa9dc2dd1de83","last_reissued_at":"2026-07-05T10:45:15.140085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:15.140085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnable Sparse Customization in Heterogeneous Edge Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Jingjing Xue, Jingyuan Wang, Min Liu, Sheng Sun, Yuwei Wang, Zhuotao Liu","submitted_at":"2024-12-10T06:14:31Z","abstract_excerpt":"To effectively manage and utilize massive distributed data at the network edge, Federated Learning (FL) has emerged as a promising edge computing paradigm across data silos. However, FL still faces two challenges: system heterogeneity (i.e., the diversity of hardware resources across edge devices) and statistical heterogeneity (i.e., non-IID data). Although sparsification can extract diverse submodels for diverse clients, most sparse FL works either simply assign submodels with artificially-given rigid rules or prune partial parameters using heuristic strategies, resulting in inflexible sparsi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07216","kind":"arxiv","version":3},"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/2412.07216/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":"2412.07216","created_at":"2026-07-05T10:45:15.140175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07216v3","created_at":"2026-07-05T10:45:15.140175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07216","created_at":"2026-07-05T10:45:15.140175+00:00"},{"alias_kind":"pith_short_12","alias_value":"IV7ECLCT3KWE","created_at":"2026-07-05T10:45:15.140175+00:00"},{"alias_kind":"pith_short_16","alias_value":"IV7ECLCT3KWEQOB7","created_at":"2026-07-05T10:45:15.140175+00:00"},{"alias_kind":"pith_short_8","alias_value":"IV7ECLCT","created_at":"2026-07-05T10:45:15.140175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07157","citing_title":"Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ","json":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ.json","graph_json":"https://pith.science/api/pith-number/IV7ECLCT3KWEQOB7EG5PJ72NLZ/graph.json","events_json":"https://pith.science/api/pith-number/IV7ECLCT3KWEQOB7EG5PJ72NLZ/events.json","paper":"https://pith.science/paper/IV7ECLCT"},"agent_actions":{"view_html":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ","download_json":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ.json","view_paper":"https://pith.science/paper/IV7ECLCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07216&json=true","fetch_graph":"https://pith.science/api/pith-number/IV7ECLCT3KWEQOB7EG5PJ72NLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IV7ECLCT3KWEQOB7EG5PJ72NLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ/action/storage_attestation","attest_author":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ/action/author_attestation","sign_citation":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ/action/citation_signature","submit_replication":"https://pith.science/pith/IV7ECLCT3KWEQOB7EG5PJ72NLZ/action/replication_record"}},"created_at":"2026-07-05T10:45:15.140175+00:00","updated_at":"2026-07-05T10:45:15.140175+00:00"}