{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MIUEM72DLYLXURNVJ73DTOSI3N","short_pith_number":"pith:MIUEM72D","schema_version":"1.0","canonical_sha256":"6228467f435e177a45b54ff639ba48db4a57b5bf3db298d94e0deb346d951ec8","source":{"kind":"arxiv","id":"2103.04628","version":1},"attestation_state":"computed","paper":{"title":"Personalized Federated Learning using Hypernetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik","submitted_at":"2021-03-08T09:29:08Z","abstract_excerpt":"Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, whil"},"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":"2103.04628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-08T09:29:08Z","cross_cats_sorted":[],"title_canon_sha256":"d4d227aaee325eb5177d86e72dcde8fac4db66f429189d30724e101637e7d1af","abstract_canon_sha256":"ed0c52208276400b7b38e6d093c8c6e6a9db7a9f1f65b2c816a0553f843f8ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:07.679991Z","signature_b64":"5904PL69b+1+vEmaLsfkajKny6PKvPJmfhAAGcdjshAzRB2LaOFOIvFli5g/ofclkmC1boCnFCPITDKuzepbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6228467f435e177a45b54ff639ba48db4a57b5bf3db298d94e0deb346d951ec8","last_reissued_at":"2026-07-05T02:21:07.679539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:07.679539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Federated Learning using Hypernetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik","submitted_at":"2021-03-08T09:29:08Z","abstract_excerpt":"Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04628","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/2103.04628/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":"2103.04628","created_at":"2026-07-05T02:21:07.679593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.04628v1","created_at":"2026-07-05T02:21:07.679593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04628","created_at":"2026-07-05T02:21:07.679593+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIUEM72DLYLX","created_at":"2026-07-05T02:21:07.679593+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIUEM72DLYLXURNV","created_at":"2026-07-05T02:21:07.679593+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIUEM72D","created_at":"2026-07-05T02:21:07.679593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08857","citing_title":"RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N","json":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N.json","graph_json":"https://pith.science/api/pith-number/MIUEM72DLYLXURNVJ73DTOSI3N/graph.json","events_json":"https://pith.science/api/pith-number/MIUEM72DLYLXURNVJ73DTOSI3N/events.json","paper":"https://pith.science/paper/MIUEM72D"},"agent_actions":{"view_html":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N","download_json":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N.json","view_paper":"https://pith.science/paper/MIUEM72D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.04628&json=true","fetch_graph":"https://pith.science/api/pith-number/MIUEM72DLYLXURNVJ73DTOSI3N/graph.json","fetch_events":"https://pith.science/api/pith-number/MIUEM72DLYLXURNVJ73DTOSI3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N/action/storage_attestation","attest_author":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N/action/author_attestation","sign_citation":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N/action/citation_signature","submit_replication":"https://pith.science/pith/MIUEM72DLYLXURNVJ73DTOSI3N/action/replication_record"}},"created_at":"2026-07-05T02:21:07.679593+00:00","updated_at":"2026-07-05T02:21:07.679593+00:00"}