{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KEY5HRNPF4F7QMAXL7N653X3NT","short_pith_number":"pith:KEY5HRNP","schema_version":"1.0","canonical_sha256":"5131d3c5af2f0bf830175fdbeeeefb6cc3a5e132df7e36de75e31e4668e3e3cd","source":{"kind":"arxiv","id":"2106.09580","version":1},"attestation_state":"computed","paper":{"title":"Optimality and Stability in Federated Learning: A Game-theoretic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.DC","cs.LG"],"primary_cat":"cs.GT","authors_text":"Jon Kleinberg, Kate Donahue","submitted_at":"2021-06-17T15:03:51Z","abstract_excerpt":"Federated learning is a distributed learning paradigm where multiple agents, each only with access to local data, jointly learn a global model. There has recently been an explosion of research aiming not only to improve the accuracy rates of federated learning, but also provide certain guarantees around social good properties such as total error. One branch of this research has taken a game-theoretic approach, and in particular, prior work has viewed federated learning as a hedonic game, where error-minimizing players arrange themselves into federating coalitions. This past work proves the exi"},"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":"2106.09580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2021-06-17T15:03:51Z","cross_cats_sorted":["cs.CY","cs.DC","cs.LG"],"title_canon_sha256":"78980c680a541356a4ca669bb4efade1cd319cc7fe35f397f5497438bfc28da2","abstract_canon_sha256":"ed48bb6f1a025aa0b5dd139923259fdd24b019b52ad56b6fc5620e9ec7f37c7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:17.578010Z","signature_b64":"MNs2z2AEfRrZiminq4f/hXCHrnbpl1jGDX6qPjMZCurBRxQ3de51RkI9bWInDY1ohlJ9/mfJeTxPdUMuWJ5ZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5131d3c5af2f0bf830175fdbeeeefb6cc3a5e132df7e36de75e31e4668e3e3cd","last_reissued_at":"2026-07-05T02:50:17.577513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:17.577513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimality and Stability in Federated Learning: A Game-theoretic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.DC","cs.LG"],"primary_cat":"cs.GT","authors_text":"Jon Kleinberg, Kate Donahue","submitted_at":"2021-06-17T15:03:51Z","abstract_excerpt":"Federated learning is a distributed learning paradigm where multiple agents, each only with access to local data, jointly learn a global model. There has recently been an explosion of research aiming not only to improve the accuracy rates of federated learning, but also provide certain guarantees around social good properties such as total error. One branch of this research has taken a game-theoretic approach, and in particular, prior work has viewed federated learning as a hedonic game, where error-minimizing players arrange themselves into federating coalitions. This past work proves the exi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09580","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/2106.09580/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":"2106.09580","created_at":"2026-07-05T02:50:17.577574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09580v1","created_at":"2026-07-05T02:50:17.577574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09580","created_at":"2026-07-05T02:50:17.577574+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEY5HRNPF4F7","created_at":"2026-07-05T02:50:17.577574+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEY5HRNPF4F7QMAX","created_at":"2026-07-05T02:50:17.577574+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEY5HRNP","created_at":"2026-07-05T02:50:17.577574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07138","citing_title":"Strategic Incentivization for Locally Differentially Private Federated Learning","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT","json":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT.json","graph_json":"https://pith.science/api/pith-number/KEY5HRNPF4F7QMAXL7N653X3NT/graph.json","events_json":"https://pith.science/api/pith-number/KEY5HRNPF4F7QMAXL7N653X3NT/events.json","paper":"https://pith.science/paper/KEY5HRNP"},"agent_actions":{"view_html":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT","download_json":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT.json","view_paper":"https://pith.science/paper/KEY5HRNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09580&json=true","fetch_graph":"https://pith.science/api/pith-number/KEY5HRNPF4F7QMAXL7N653X3NT/graph.json","fetch_events":"https://pith.science/api/pith-number/KEY5HRNPF4F7QMAXL7N653X3NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT/action/storage_attestation","attest_author":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT/action/author_attestation","sign_citation":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT/action/citation_signature","submit_replication":"https://pith.science/pith/KEY5HRNPF4F7QMAXL7N653X3NT/action/replication_record"}},"created_at":"2026-07-05T02:50:17.577574+00:00","updated_at":"2026-07-05T02:50:17.577574+00:00"}