{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WB4TQREIP5TBXVZILZ75TF4UOX","short_pith_number":"pith:WB4TQREI","schema_version":"1.0","canonical_sha256":"b0793844887f661bd7285e7fd9979475e0df71325fd720eb98820fd606240627","source":{"kind":"arxiv","id":"2202.01267","version":1},"attestation_state":"computed","paper":{"title":"FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnaz Arzani, Jinhyun So, Kevin Hsieh, Ranveer Chandra, Salman Avestimehr, Shadi Noghabi","submitted_at":"2022-02-02T20:09:27Z","abstract_excerpt":"Large-scale deployments of low Earth orbit (LEO) satellites collect massive amount of Earth imageries and sensor data, which can empower machine learning (ML) to address global challenges such as real-time disaster navigation and mitigation. However, it is often infeasible to download all the high-resolution images and train these ML models on the ground because of limited downlink bandwidth, sparse connectivity, and regularization constraints on the imagery resolution. To address these challenges, we leverage Federated Learning (FL), where ground stations and satellites collaboratively train "},"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":"2202.01267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-02T20:09:27Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"cc87b4eb731e03544b75047cc809f1b641f012e0c66d0f3f3fe1e86bdaefab65","abstract_canon_sha256":"19222298013378b1087ec7cb47eab43d1b9220c219efb3c1234f0e98159e9650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:52.306685Z","signature_b64":"At+hIcRmaQP/sSh256EPa73yEER0zXneMncTxSBI2DyfUZRdRMt5RmQpgS8UK/2i6Qp4d8kd8kj8m3BbDYh5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0793844887f661bd7285e7fd9979475e0df71325fd720eb98820fd606240627","last_reissued_at":"2026-07-05T03:53:52.306267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:52.306267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnaz Arzani, Jinhyun So, Kevin Hsieh, Ranveer Chandra, Salman Avestimehr, Shadi Noghabi","submitted_at":"2022-02-02T20:09:27Z","abstract_excerpt":"Large-scale deployments of low Earth orbit (LEO) satellites collect massive amount of Earth imageries and sensor data, which can empower machine learning (ML) to address global challenges such as real-time disaster navigation and mitigation. However, it is often infeasible to download all the high-resolution images and train these ML models on the ground because of limited downlink bandwidth, sparse connectivity, and regularization constraints on the imagery resolution. To address these challenges, we leverage Federated Learning (FL), where ground stations and satellites collaboratively train "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01267","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/2202.01267/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":"2202.01267","created_at":"2026-07-05T03:53:52.306324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01267v1","created_at":"2026-07-05T03:53:52.306324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01267","created_at":"2026-07-05T03:53:52.306324+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB4TQREIP5TB","created_at":"2026-07-05T03:53:52.306324+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB4TQREIP5TBXVZI","created_at":"2026-07-05T03:53:52.306324+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB4TQREI","created_at":"2026-07-05T03:53:52.306324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.10834","citing_title":"EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04052","citing_title":"Constraint-Aware Execution Planning for Hybrid Space-Ground Compute Workloads","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04512","citing_title":"Topology-Aware Two-Stage Federated Learning via Proxy Models for Sub-THz Heterogeneous LEO Communications","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19958","citing_title":"Equinox: Decentralized Scheduling for Hardware-Aware Orbital Intelligence","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX","json":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX.json","graph_json":"https://pith.science/api/pith-number/WB4TQREIP5TBXVZILZ75TF4UOX/graph.json","events_json":"https://pith.science/api/pith-number/WB4TQREIP5TBXVZILZ75TF4UOX/events.json","paper":"https://pith.science/paper/WB4TQREI"},"agent_actions":{"view_html":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX","download_json":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX.json","view_paper":"https://pith.science/paper/WB4TQREI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01267&json=true","fetch_graph":"https://pith.science/api/pith-number/WB4TQREIP5TBXVZILZ75TF4UOX/graph.json","fetch_events":"https://pith.science/api/pith-number/WB4TQREIP5TBXVZILZ75TF4UOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX/action/storage_attestation","attest_author":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX/action/author_attestation","sign_citation":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX/action/citation_signature","submit_replication":"https://pith.science/pith/WB4TQREIP5TBXVZILZ75TF4UOX/action/replication_record"}},"created_at":"2026-07-05T03:53:52.306324+00:00","updated_at":"2026-07-05T03:53:52.306324+00:00"}