{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZHFMYAHD7ES2HUAONLFWMWLZF7","short_pith_number":"pith:ZHFMYAHD","schema_version":"1.0","canonical_sha256":"c9cacc00e3f925a3d00e6acb6659792fc6237352f856e068a4a47217963dcd8e","source":{"kind":"arxiv","id":"2605.16438","version":1},"attestation_state":"computed","paper":{"title":"Byzantine-Resilient Federated Learning via QUBO-Based Client Selection on Quantum Annealers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"(2) Columbia University), Andras Ferenczi (1), Dagen Wang (1), Jason Qizhe Qin (2) ((1) American Express Co., Sutapa Samanta (1)","submitted_at":"2026-05-14T22:42:14Z","abstract_excerpt":"Federated Learning (FL) trains a global model across decentralized clients while preserving data privacy, but at scale it is vulnerable to malicious updates. Byzantine-resilient aggregation methods such as MultiKrum score gradients against their nearest neighbors and can miss malicious updates that preserve the statistical properties of honest ones. We propose a quantum annealing approach that reformulates client selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem, encoding pairwise distances into a cost function solved by quantum annealers (QA). Unlike MultiKrum's greedy"},"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":"2605.16438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T22:42:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0239174bbb6bb9bdc7efc4be0956a43d2be2d81114e55ff2d64f78218c370bbe","abstract_canon_sha256":"a17a8fbb7a94350f175d8cf6f6ee36cff9446c931825d12f66deb7dde7d45b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:22.075745Z","signature_b64":"GKlR7zs66qKfXKhSIDzAUMpXcdgOfWrE43/pQhcOJrQhPJ9PkgdZ1OkluKSfcOOxg1ozscBee8fzhPDuJMeABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9cacc00e3f925a3d00e6acb6659792fc6237352f856e068a4a47217963dcd8e","last_reissued_at":"2026-05-20T00:02:22.075124Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:22.075124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Byzantine-Resilient Federated Learning via QUBO-Based Client Selection on Quantum Annealers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"(2) Columbia University), Andras Ferenczi (1), Dagen Wang (1), Jason Qizhe Qin (2) ((1) American Express Co., Sutapa Samanta (1)","submitted_at":"2026-05-14T22:42:14Z","abstract_excerpt":"Federated Learning (FL) trains a global model across decentralized clients while preserving data privacy, but at scale it is vulnerable to malicious updates. Byzantine-resilient aggregation methods such as MultiKrum score gradients against their nearest neighbors and can miss malicious updates that preserve the statistical properties of honest ones. We propose a quantum annealing approach that reformulates client selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem, encoding pairwise distances into a cost function solved by quantum annealers (QA). Unlike MultiKrum's greedy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16438","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/2605.16438/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.577522Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:21:57.101587Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"82c997b314203c0608aed9080d77660051cb46c14fbd2b0990c6d5d961617fd8"},"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":"2605.16438","created_at":"2026-05-20T00:02:22.075214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16438v1","created_at":"2026-05-20T00:02:22.075214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16438","created_at":"2026-05-20T00:02:22.075214+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHFMYAHD7ES2","created_at":"2026-05-20T00:02:22.075214+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHFMYAHD7ES2HUAO","created_at":"2026-05-20T00:02:22.075214+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHFMYAHD","created_at":"2026-05-20T00:02:22.075214+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/ZHFMYAHD7ES2HUAONLFWMWLZF7","json":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7.json","graph_json":"https://pith.science/api/pith-number/ZHFMYAHD7ES2HUAONLFWMWLZF7/graph.json","events_json":"https://pith.science/api/pith-number/ZHFMYAHD7ES2HUAONLFWMWLZF7/events.json","paper":"https://pith.science/paper/ZHFMYAHD"},"agent_actions":{"view_html":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7","download_json":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7.json","view_paper":"https://pith.science/paper/ZHFMYAHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16438&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHFMYAHD7ES2HUAONLFWMWLZF7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHFMYAHD7ES2HUAONLFWMWLZF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7/action/storage_attestation","attest_author":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7/action/author_attestation","sign_citation":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7/action/citation_signature","submit_replication":"https://pith.science/pith/ZHFMYAHD7ES2HUAONLFWMWLZF7/action/replication_record"}},"created_at":"2026-05-20T00:02:22.075214+00:00","updated_at":"2026-05-20T00:02:22.075214+00:00"}