{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HW7KZDDB4DFXSZMQTGNJ3D4XR3","short_pith_number":"pith:HW7KZDDB","schema_version":"1.0","canonical_sha256":"3dbeac8c61e0cb796590999a9d8f978eede57aea6ed2a535eaf55b28beb6ddc7","source":{"kind":"arxiv","id":"2206.01366","version":5},"attestation_state":"computed","paper":{"title":"Supernet Training for Federated Image Classification under System Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Se-Young Yun, Taehyeon Kim","submitted_at":"2022-06-03T02:21:01Z","abstract_excerpt":"Efficient deployment of deep neural networks across many devices and resource constraints, particularly on edge devices, is one of the most challenging problems in the presence of data-privacy preservation issues. Conventional approaches have evolved to either improve a single global model while keeping each local heterogeneous training data decentralized (i.e. data heterogeneity; Federated Learning (FL)) or to train an overarching network that supports diverse architectural settings to address heterogeneous systems equipped with different computational capabilities (i.e. system heterogeneity;"},"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":"2206.01366","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-03T02:21:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1350533e5547d6b30980d3871349392a2410827094485ccd24b649cbc1657222","abstract_canon_sha256":"4616444255499a03b4b7f09547e32b4778c69ff6999c32a91d351e0627ee1bea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:51.243820Z","signature_b64":"bStaWDDTQj+pTnDPnNF5fql/V5Kydre77TJRFJzuBOh58gaEWlxWgKVhNnqFu6HQu5uNtJhJLAg31t+PKAyADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dbeac8c61e0cb796590999a9d8f978eede57aea6ed2a535eaf55b28beb6ddc7","last_reissued_at":"2026-07-05T05:03:51.243410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:51.243410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supernet Training for Federated Image Classification under System Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Se-Young Yun, Taehyeon Kim","submitted_at":"2022-06-03T02:21:01Z","abstract_excerpt":"Efficient deployment of deep neural networks across many devices and resource constraints, particularly on edge devices, is one of the most challenging problems in the presence of data-privacy preservation issues. Conventional approaches have evolved to either improve a single global model while keeping each local heterogeneous training data decentralized (i.e. data heterogeneity; Federated Learning (FL)) or to train an overarching network that supports diverse architectural settings to address heterogeneous systems equipped with different computational capabilities (i.e. system heterogeneity;"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01366","kind":"arxiv","version":5},"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/2206.01366/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":"2206.01366","created_at":"2026-07-05T05:03:51.243467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01366v5","created_at":"2026-07-05T05:03:51.243467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01366","created_at":"2026-07-05T05:03:51.243467+00:00"},{"alias_kind":"pith_short_12","alias_value":"HW7KZDDB4DFX","created_at":"2026-07-05T05:03:51.243467+00:00"},{"alias_kind":"pith_short_16","alias_value":"HW7KZDDB4DFXSZMQ","created_at":"2026-07-05T05:03:51.243467+00:00"},{"alias_kind":"pith_short_8","alias_value":"HW7KZDDB","created_at":"2026-07-05T05:03:51.243467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00687","citing_title":"Towards Privacy-Preserving Medical Imaging: Federated Learning with Differential Privacy and Secure Aggregation Using a Modified ResNet Architecture","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3","json":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3.json","graph_json":"https://pith.science/api/pith-number/HW7KZDDB4DFXSZMQTGNJ3D4XR3/graph.json","events_json":"https://pith.science/api/pith-number/HW7KZDDB4DFXSZMQTGNJ3D4XR3/events.json","paper":"https://pith.science/paper/HW7KZDDB"},"agent_actions":{"view_html":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3","download_json":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3.json","view_paper":"https://pith.science/paper/HW7KZDDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01366&json=true","fetch_graph":"https://pith.science/api/pith-number/HW7KZDDB4DFXSZMQTGNJ3D4XR3/graph.json","fetch_events":"https://pith.science/api/pith-number/HW7KZDDB4DFXSZMQTGNJ3D4XR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3/action/storage_attestation","attest_author":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3/action/author_attestation","sign_citation":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3/action/citation_signature","submit_replication":"https://pith.science/pith/HW7KZDDB4DFXSZMQTGNJ3D4XR3/action/replication_record"}},"created_at":"2026-07-05T05:03:51.243467+00:00","updated_at":"2026-07-05T05:03:51.243467+00:00"}