{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WY6QYWCECNIA5TANJCG6Z32VZG","short_pith_number":"pith:WY6QYWCE","schema_version":"1.0","canonical_sha256":"b63d0c584413500ecc0d488decef55c990d32389d84384c5432790d5cca4d697","source":{"kind":"arxiv","id":"2205.11506","version":2},"attestation_state":"computed","paper":{"title":"Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Akhil Mathur, Chi Ian Tang, Ekdeep Singh Lubana, Fahim Kawsar, Robert P. Dick","submitted_at":"2022-05-23T17:59:03Z","abstract_excerpt":"Federated learning is generally used in tasks where labels are readily available (e.g., next word prediction). Relaxing this constraint requires design of unsupervised learning techniques that can support desirable properties for federated training: robustness to statistical/systems heterogeneity, scalability with number of participants, and communication efficiency. Prior work on this topic has focused on directly extending centralized self-supervised learning techniques, which are not designed to have the properties listed above. To address this situation, we propose Orchestra, a novel unsup"},"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":"2205.11506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T17:59:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"97f73c946f204eeca2939f03bf1915ab4edb905a144a5ae53548ef3b861a46ea","abstract_canon_sha256":"c1b529f59ec207fc6724ccf7cf4ae55b9863c201ace91b6305a285981f19294d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:56.701935Z","signature_b64":"5zmTogk6w1G9aMgxPPZNVIbKTw8jbKF6uvhFAnq7sV+Cs9gEgUS+0oL5sebw9zMZEhWLbFrdmaAIvzXooqAwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b63d0c584413500ecc0d488decef55c990d32389d84384c5432790d5cca4d697","last_reissued_at":"2026-07-05T04:30:56.701171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:56.701171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Akhil Mathur, Chi Ian Tang, Ekdeep Singh Lubana, Fahim Kawsar, Robert P. Dick","submitted_at":"2022-05-23T17:59:03Z","abstract_excerpt":"Federated learning is generally used in tasks where labels are readily available (e.g., next word prediction). Relaxing this constraint requires design of unsupervised learning techniques that can support desirable properties for federated training: robustness to statistical/systems heterogeneity, scalability with number of participants, and communication efficiency. Prior work on this topic has focused on directly extending centralized self-supervised learning techniques, which are not designed to have the properties listed above. To address this situation, we propose Orchestra, a novel unsup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11506","kind":"arxiv","version":2},"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/2205.11506/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":"2205.11506","created_at":"2026-07-05T04:30:56.701227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11506v2","created_at":"2026-07-05T04:30:56.701227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11506","created_at":"2026-07-05T04:30:56.701227+00:00"},{"alias_kind":"pith_short_12","alias_value":"WY6QYWCECNIA","created_at":"2026-07-05T04:30:56.701227+00:00"},{"alias_kind":"pith_short_16","alias_value":"WY6QYWCECNIA5TAN","created_at":"2026-07-05T04:30:56.701227+00:00"},{"alias_kind":"pith_short_8","alias_value":"WY6QYWCE","created_at":"2026-07-05T04:30:56.701227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.05824","citing_title":"Navigating Distribution Shifts in Medical Image Analysis: A Survey","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07888","citing_title":"Enhancing Federated Quadruplet Learning: Stochastic Client Selection and Embedding Stability Analysis","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18237","citing_title":"Semantic-based Distributed Learning for Diverse and Discriminative Representations","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG","json":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG.json","graph_json":"https://pith.science/api/pith-number/WY6QYWCECNIA5TANJCG6Z32VZG/graph.json","events_json":"https://pith.science/api/pith-number/WY6QYWCECNIA5TANJCG6Z32VZG/events.json","paper":"https://pith.science/paper/WY6QYWCE"},"agent_actions":{"view_html":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG","download_json":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG.json","view_paper":"https://pith.science/paper/WY6QYWCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11506&json=true","fetch_graph":"https://pith.science/api/pith-number/WY6QYWCECNIA5TANJCG6Z32VZG/graph.json","fetch_events":"https://pith.science/api/pith-number/WY6QYWCECNIA5TANJCG6Z32VZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG/action/storage_attestation","attest_author":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG/action/author_attestation","sign_citation":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG/action/citation_signature","submit_replication":"https://pith.science/pith/WY6QYWCECNIA5TANJCG6Z32VZG/action/replication_record"}},"created_at":"2026-07-05T04:30:56.701227+00:00","updated_at":"2026-07-05T04:30:56.701227+00:00"}