{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3XHZBYDMUGLBZM74HYJ4CVWXJX","short_pith_number":"pith:3XHZBYDM","schema_version":"1.0","canonical_sha256":"ddcf90e06ca1961cb3fc3e13c156d74dfe34fd45ab9a6a8a2b43bdfb82db98e2","source":{"kind":"arxiv","id":"2210.02129","version":3},"attestation_state":"computed","paper":{"title":"Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Naoyuki Terashita, Satoshi Hara","submitted_at":"2022-10-05T10:23:45Z","abstract_excerpt":"This paper addresses the communication issues when estimating hyper-gradients in decentralized federated learning (FL). Hyper-gradients in decentralized FL quantifies how the performance of globally shared optimal model is influenced by the perturbations in clients' hyper-parameters. In prior work, clients trace this influence through the communication of Hessian matrices over a static undirected network, resulting in (i) excessive communication costs and (ii) inability to make use of more efficient and robust networks, namely, time-varying directed networks. To solve these issues, we introduc"},"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":"2210.02129","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-10-05T10:23:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2d5de78156e1cc370341f5046f8ba96fd153f86afc7e6575b601e9ef1a43375c","abstract_canon_sha256":"9011e0d131c324e36dce2132c1d24b1883409bbb6fac4a73039f639f59efd449"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:53.386960Z","signature_b64":"e6LcqXstL0CTgdk4ks4ZkQE6JZkHbBadMpKEbao7cTT6VLnTDS1dVOe5+UZnUrkAsUdH54TmJs2wjkg7zA60AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddcf90e06ca1961cb3fc3e13c156d74dfe34fd45ab9a6a8a2b43bdfb82db98e2","last_reissued_at":"2026-07-05T06:19:53.386502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:53.386502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Hyper-Gradient Computation over Time-Varying Directed Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Naoyuki Terashita, Satoshi Hara","submitted_at":"2022-10-05T10:23:45Z","abstract_excerpt":"This paper addresses the communication issues when estimating hyper-gradients in decentralized federated learning (FL). Hyper-gradients in decentralized FL quantifies how the performance of globally shared optimal model is influenced by the perturbations in clients' hyper-parameters. In prior work, clients trace this influence through the communication of Hessian matrices over a static undirected network, resulting in (i) excessive communication costs and (ii) inability to make use of more efficient and robust networks, namely, time-varying directed networks. To solve these issues, we introduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02129","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/2210.02129/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":"2210.02129","created_at":"2026-07-05T06:19:53.386555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.02129v3","created_at":"2026-07-05T06:19:53.386555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02129","created_at":"2026-07-05T06:19:53.386555+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XHZBYDMUGLB","created_at":"2026-07-05T06:19:53.386555+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XHZBYDMUGLBZM74","created_at":"2026-07-05T06:19:53.386555+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XHZBYDM","created_at":"2026-07-05T06:19:53.386555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06931","citing_title":"DICE: Data Influence Cascade in Decentralized Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX","json":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX.json","graph_json":"https://pith.science/api/pith-number/3XHZBYDMUGLBZM74HYJ4CVWXJX/graph.json","events_json":"https://pith.science/api/pith-number/3XHZBYDMUGLBZM74HYJ4CVWXJX/events.json","paper":"https://pith.science/paper/3XHZBYDM"},"agent_actions":{"view_html":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX","download_json":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX.json","view_paper":"https://pith.science/paper/3XHZBYDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.02129&json=true","fetch_graph":"https://pith.science/api/pith-number/3XHZBYDMUGLBZM74HYJ4CVWXJX/graph.json","fetch_events":"https://pith.science/api/pith-number/3XHZBYDMUGLBZM74HYJ4CVWXJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX/action/storage_attestation","attest_author":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX/action/author_attestation","sign_citation":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX/action/citation_signature","submit_replication":"https://pith.science/pith/3XHZBYDMUGLBZM74HYJ4CVWXJX/action/replication_record"}},"created_at":"2026-07-05T06:19:53.386555+00:00","updated_at":"2026-07-05T06:19:53.386555+00:00"}