{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KNDZB6A5WYK5NLRD7TZTFKE6LU","short_pith_number":"pith:KNDZB6A5","schema_version":"1.0","canonical_sha256":"534790f81db615d6ae23fcf332a89e5d2522494b7f47dd289e8eeb8f8c78c605","source":{"kind":"arxiv","id":"2004.08546","version":4},"attestation_state":"computed","paper":{"title":"Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.DC","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaoyang He, Murali Annavaram, Salman Avestimehr","submitted_at":"2020-04-18T08:04:44Z","abstract_excerpt":"Federated Learning (FL) has been proved to be an effective learning framework when data cannot be centralized due to privacy, communication costs, and regulatory restrictions. When training deep learning models under an FL setting, people employ the predefined model architecture discovered in the centralized environment. However, this predefined architecture may not be the optimal choice because it may not fit data with non-identical and independent distribution (non-IID). Thus, we advocate automating federated learning (AutoFL) to improve model accuracy and reduce the manual design effort. We"},"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":"2004.08546","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-04-18T08:04:44Z","cross_cats_sorted":["cs.CV","cs.DC","cs.MA","stat.ML"],"title_canon_sha256":"c059041df65caf695c711d0617b5687bbb6b6f682670f3b4eb241ac8ab6024e8","abstract_canon_sha256":"c93b20e9f372c6de90e7fa1984b5a63c1164c2bf3e3dbcca290d064d47b0e762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:04:06.485461Z","signature_b64":"mx5/jcN7m+DTo4n4GjCMyaU9TfuFjXW8Oo44oAQz20QQ14YcVEJsP4Bvm6iP8PM8GKDMWJBOohgxMVeCRwfXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"534790f81db615d6ae23fcf332a89e5d2522494b7f47dd289e8eeb8f8c78c605","last_reissued_at":"2026-07-05T02:04:06.485101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:04:06.485101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.DC","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaoyang He, Murali Annavaram, Salman Avestimehr","submitted_at":"2020-04-18T08:04:44Z","abstract_excerpt":"Federated Learning (FL) has been proved to be an effective learning framework when data cannot be centralized due to privacy, communication costs, and regulatory restrictions. When training deep learning models under an FL setting, people employ the predefined model architecture discovered in the centralized environment. However, this predefined architecture may not be the optimal choice because it may not fit data with non-identical and independent distribution (non-IID). Thus, we advocate automating federated learning (AutoFL) to improve model accuracy and reduce the manual design effort. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.08546","kind":"arxiv","version":4},"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/2004.08546/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":"2004.08546","created_at":"2026-07-05T02:04:06.485155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.08546v4","created_at":"2026-07-05T02:04:06.485155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.08546","created_at":"2026-07-05T02:04:06.485155+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNDZB6A5WYK5","created_at":"2026-07-05T02:04:06.485155+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNDZB6A5WYK5NLRD","created_at":"2026-07-05T02:04:06.485155+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNDZB6A5","created_at":"2026-07-05T02:04:06.485155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01366","citing_title":"Auto-FL-Research: Agentic Search for Federated Learning Algorithms","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15127","citing_title":"DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU","json":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU.json","graph_json":"https://pith.science/api/pith-number/KNDZB6A5WYK5NLRD7TZTFKE6LU/graph.json","events_json":"https://pith.science/api/pith-number/KNDZB6A5WYK5NLRD7TZTFKE6LU/events.json","paper":"https://pith.science/paper/KNDZB6A5"},"agent_actions":{"view_html":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU","download_json":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU.json","view_paper":"https://pith.science/paper/KNDZB6A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.08546&json=true","fetch_graph":"https://pith.science/api/pith-number/KNDZB6A5WYK5NLRD7TZTFKE6LU/graph.json","fetch_events":"https://pith.science/api/pith-number/KNDZB6A5WYK5NLRD7TZTFKE6LU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU/action/storage_attestation","attest_author":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU/action/author_attestation","sign_citation":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU/action/citation_signature","submit_replication":"https://pith.science/pith/KNDZB6A5WYK5NLRD7TZTFKE6LU/action/replication_record"}},"created_at":"2026-07-05T02:04:06.485155+00:00","updated_at":"2026-07-05T02:04:06.485155+00:00"}