{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DIF4O6JCMARIRWKKK4ZPVSRKAX","short_pith_number":"pith:DIF4O6JC","schema_version":"1.0","canonical_sha256":"1a0bc77922602288d94a5732faca2a05e58d88ec1b2e2824ecb0174d0ae97e53","source":{"kind":"arxiv","id":"1906.06629","version":2},"attestation_state":"computed","paper":{"title":"Robust Federated Learning in a Heterogeneous Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Avishek Ghosh, Dong Yin, Justin Hong, Kannan Ramchandran","submitted_at":"2019-06-16T00:14:53Z","abstract_excerpt":"We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computational challenges arise in Federated Learning particularly in the presence of heterogeneous data distribution (i.e., data points on different devices belong to different distributions signifying different clusters) and Byzantine machines (i.e., machines that may behave abnormally, or even exhibit arbitrary and potentially adversarial behavior). To address the aforementioned challenges, first we propose a general statisti"},"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":"1906.06629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-16T00:14:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2d53b9d982c4f6b4f6c007d016922ae25a35ef095fdc1af82fa6ad1eea0af59b","abstract_canon_sha256":"639ddb5f643371eaf262fe94d8ed5396eb67e141ffd0ee4e50799fce9b24a2e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:04.472815Z","signature_b64":"W2DCY5N5nEFAOvVwyL3A4gcnqdxL128IKhPGSsgcvqos5MIYXhKnjg7Z5AwZKvVdiG5Y8nWXxdSSwFIeuHUmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a0bc77922602288d94a5732faca2a05e58d88ec1b2e2824ecb0174d0ae97e53","last_reissued_at":"2026-07-05T00:11:04.472356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:04.472356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Federated Learning in a Heterogeneous Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Avishek Ghosh, Dong Yin, Justin Hong, Kannan Ramchandran","submitted_at":"2019-06-16T00:14:53Z","abstract_excerpt":"We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computational challenges arise in Federated Learning particularly in the presence of heterogeneous data distribution (i.e., data points on different devices belong to different distributions signifying different clusters) and Byzantine machines (i.e., machines that may behave abnormally, or even exhibit arbitrary and potentially adversarial behavior). To address the aforementioned challenges, first we propose a general statisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06629","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/1906.06629/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":"1906.06629","created_at":"2026-07-05T00:11:04.472413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06629v2","created_at":"2026-07-05T00:11:04.472413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06629","created_at":"2026-07-05T00:11:04.472413+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIF4O6JCMARI","created_at":"2026-07-05T00:11:04.472413+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIF4O6JCMARIRWKK","created_at":"2026-07-05T00:11:04.472413+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIF4O6JC","created_at":"2026-07-05T00:11:04.472413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30615","citing_title":"Tuning-Free Efficient Estimation for Multi-Source Data via Covariance-Aware Shrinkage","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2407.09658","citing_title":"BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01901","citing_title":"FedBiCross: Personalized One-Shot Federated Learning on Medical Images","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09337","citing_title":"Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06282","citing_title":"Tight Convergence Rates for Online Distributed Linear Estimation with Adversarial Measurements","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX","json":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX.json","graph_json":"https://pith.science/api/pith-number/DIF4O6JCMARIRWKKK4ZPVSRKAX/graph.json","events_json":"https://pith.science/api/pith-number/DIF4O6JCMARIRWKKK4ZPVSRKAX/events.json","paper":"https://pith.science/paper/DIF4O6JC"},"agent_actions":{"view_html":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX","download_json":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX.json","view_paper":"https://pith.science/paper/DIF4O6JC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06629&json=true","fetch_graph":"https://pith.science/api/pith-number/DIF4O6JCMARIRWKKK4ZPVSRKAX/graph.json","fetch_events":"https://pith.science/api/pith-number/DIF4O6JCMARIRWKKK4ZPVSRKAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX/action/storage_attestation","attest_author":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX/action/author_attestation","sign_citation":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX/action/citation_signature","submit_replication":"https://pith.science/pith/DIF4O6JCMARIRWKKK4ZPVSRKAX/action/replication_record"}},"created_at":"2026-07-05T00:11:04.472413+00:00","updated_at":"2026-07-05T00:11:04.472413+00:00"}