{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NGYWZDMOUJP4K2YDPSRP6ZR2LF","short_pith_number":"pith:NGYWZDMO","schema_version":"1.0","canonical_sha256":"69b16c8d8ea25fc56b037ca2ff663a597823f3c7a6651fbdcfaaf61b83a92c93","source":{"kind":"arxiv","id":"2605.21322","version":1},"attestation_state":"computed","paper":{"title":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaimaa Medjadji, Feras M. Awaysheh, Guilain Leduc, Sadi Alawadi, Sylvain Kubler, Yves Le Traon","submitted_at":"2026-05-20T15:50:49Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address statistical heterogeneity across client data (non-IID), system heterogeneity in device capabilities, and communication efficiency. Existing FL approaches mitigate these challenges through improved aggregation, personalization, or knowledge distillation, but they almost universally assume a fixed client architecture, limiting adaptability to heterogeneous data complexity and hardware constraints. This architectural constraint often leads to suboptim"},"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":"2605.21322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T15:50:49Z","cross_cats_sorted":[],"title_canon_sha256":"2d617f31f078208a39c5df47ca2ac3ab681af1e9e0e84ce0cacce345c6217b7b","abstract_canon_sha256":"0204a87a6bcdab226d1a222dd53cbd60736e4f4d77b7d9b2952ef48d6b462d55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:29.134941Z","signature_b64":"rpiFNuHFVLp7GD4qYIU3LNuEiDs5/OLlnS8RcTEIxyDghfypOntJ78KpXJMy8GcRcIvKde9zpE4tQZSto38oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b16c8d8ea25fc56b037ca2ff663a597823f3c7a6651fbdcfaaf61b83a92c93","last_reissued_at":"2026-05-21T02:05:29.134260Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:29.134260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaimaa Medjadji, Feras M. Awaysheh, Guilain Leduc, Sadi Alawadi, Sylvain Kubler, Yves Le Traon","submitted_at":"2026-05-20T15:50:49Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address statistical heterogeneity across client data (non-IID), system heterogeneity in device capabilities, and communication efficiency. Existing FL approaches mitigate these challenges through improved aggregation, personalization, or knowledge distillation, but they almost universally assume a fixed client architecture, limiting adaptability to heterogeneous data complexity and hardware constraints. This architectural constraint often leads to suboptim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21322","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/2605.21322/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":"2605.21322","created_at":"2026-05-21T02:05:29.134363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21322v1","created_at":"2026-05-21T02:05:29.134363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21322","created_at":"2026-05-21T02:05:29.134363+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGYWZDMOUJP4","created_at":"2026-05-21T02:05:29.134363+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGYWZDMOUJP4K2YD","created_at":"2026-05-21T02:05:29.134363+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGYWZDMO","created_at":"2026-05-21T02:05:29.134363+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/NGYWZDMOUJP4K2YDPSRP6ZR2LF","json":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF.json","graph_json":"https://pith.science/api/pith-number/NGYWZDMOUJP4K2YDPSRP6ZR2LF/graph.json","events_json":"https://pith.science/api/pith-number/NGYWZDMOUJP4K2YDPSRP6ZR2LF/events.json","paper":"https://pith.science/paper/NGYWZDMO"},"agent_actions":{"view_html":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF","download_json":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF.json","view_paper":"https://pith.science/paper/NGYWZDMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21322&json=true","fetch_graph":"https://pith.science/api/pith-number/NGYWZDMOUJP4K2YDPSRP6ZR2LF/graph.json","fetch_events":"https://pith.science/api/pith-number/NGYWZDMOUJP4K2YDPSRP6ZR2LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF/action/storage_attestation","attest_author":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF/action/author_attestation","sign_citation":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF/action/citation_signature","submit_replication":"https://pith.science/pith/NGYWZDMOUJP4K2YDPSRP6ZR2LF/action/replication_record"}},"created_at":"2026-05-21T02:05:29.134363+00:00","updated_at":"2026-05-21T02:05:29.134363+00:00"}