{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IHDRFVS3LZV6UIMXY6Z5KG2TYC","short_pith_number":"pith:IHDRFVS3","schema_version":"1.0","canonical_sha256":"41c712d65b5e6bea2197c7b3d51b53c0ae59a3ac0814ce4ba04036b40035dc1f","source":{"kind":"arxiv","id":"2210.04620","version":3},"attestation_state":"computed","paper":{"title":"FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Bellet, Aymeric Dieuleveut, Boris Muzellec, Chaoyang He, Constantin Philippenko, Edwige Cyffers, Erum Mushtaq, Felix Grimberg, Giovanni Neglia, Jean Ogier Du Terrail, Marco Lorenzi, Marc Tommasi, Maria Tele\\'nczuk, Martin Jaggi, Mathieu Andreux, Othmane Marfoq, Paul Mangold, Regis Loeb, Sai Praneeth Karimireddy, Salman Avestimehr, Samy-Safwan Ayed, Santiago Silva, Shadi Albarqouni, Tanguy Marchand","submitted_at":"2022-10-10T12:17:30Z","abstract_excerpt":"Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models, without centralizing data. The cross-silo FL setting corresponds to the case of few ($2$--$50$) reliable clients, each holding medium to large datasets, and is typically found in applications such as healthcare, finance, or industry. While previous works have proposed representative datasets for cross-device FL, few realistic healthcare cross-silo FL datasets exist, thereby slowing algorithmic research in this critical application. In this work, we propo"},"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":"2210.04620","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-10T12:17:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"223141b649bba9115bf3e508fffc5b2eab0aebda822a22a5e62c38451ab3290a","abstract_canon_sha256":"ac4b9d1f49d50535de5535296ad59d15fdb63c2ab372a8ce0982a6a1a87701ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:21.009617Z","signature_b64":"+xw55o2AABOul22vOXFMZf6ESB4Uit3TQHg+lSos9vXY98+Tby4xv7RyGFo/yBPB8OYjy1nRX86oQwXdGdIQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c712d65b5e6bea2197c7b3d51b53c0ae59a3ac0814ce4ba04036b40035dc1f","last_reissued_at":"2026-07-05T06:07:21.009155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:21.009155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Bellet, Aymeric Dieuleveut, Boris Muzellec, Chaoyang He, Constantin Philippenko, Edwige Cyffers, Erum Mushtaq, Felix Grimberg, Giovanni Neglia, Jean Ogier Du Terrail, Marco Lorenzi, Marc Tommasi, Maria Tele\\'nczuk, Martin Jaggi, Mathieu Andreux, Othmane Marfoq, Paul Mangold, Regis Loeb, Sai Praneeth Karimireddy, Salman Avestimehr, Samy-Safwan Ayed, Santiago Silva, Shadi Albarqouni, Tanguy Marchand","submitted_at":"2022-10-10T12:17:30Z","abstract_excerpt":"Federated Learning (FL) is a novel approach enabling several clients holding sensitive data to collaboratively train machine learning models, without centralizing data. The cross-silo FL setting corresponds to the case of few ($2$--$50$) reliable clients, each holding medium to large datasets, and is typically found in applications such as healthcare, finance, or industry. While previous works have proposed representative datasets for cross-device FL, few realistic healthcare cross-silo FL datasets exist, thereby slowing algorithmic research in this critical application. In this work, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04620","kind":"arxiv","version":3},"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/2210.04620/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":"2210.04620","created_at":"2026-07-05T06:07:21.009217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04620v3","created_at":"2026-07-05T06:07:21.009217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04620","created_at":"2026-07-05T06:07:21.009217+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHDRFVS3LZV6","created_at":"2026-07-05T06:07:21.009217+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHDRFVS3LZV6UIMX","created_at":"2026-07-05T06:07:21.009217+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHDRFVS3","created_at":"2026-07-05T06:07:21.009217+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/IHDRFVS3LZV6UIMXY6Z5KG2TYC","json":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC.json","graph_json":"https://pith.science/api/pith-number/IHDRFVS3LZV6UIMXY6Z5KG2TYC/graph.json","events_json":"https://pith.science/api/pith-number/IHDRFVS3LZV6UIMXY6Z5KG2TYC/events.json","paper":"https://pith.science/paper/IHDRFVS3"},"agent_actions":{"view_html":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC","download_json":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC.json","view_paper":"https://pith.science/paper/IHDRFVS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04620&json=true","fetch_graph":"https://pith.science/api/pith-number/IHDRFVS3LZV6UIMXY6Z5KG2TYC/graph.json","fetch_events":"https://pith.science/api/pith-number/IHDRFVS3LZV6UIMXY6Z5KG2TYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC/action/storage_attestation","attest_author":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC/action/author_attestation","sign_citation":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC/action/citation_signature","submit_replication":"https://pith.science/pith/IHDRFVS3LZV6UIMXY6Z5KG2TYC/action/replication_record"}},"created_at":"2026-07-05T06:07:21.009217+00:00","updated_at":"2026-07-05T06:07:21.009217+00:00"}