{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PIDVXWWAN6LTFSVUTHP3LDKJNE","short_pith_number":"pith:PIDVXWWA","schema_version":"1.0","canonical_sha256":"7a075bdac06f9732cab499dfb58d49692d1b8c4b5fe0ef847cfb952de55c91c1","source":{"kind":"arxiv","id":"2201.03169","version":5},"attestation_state":"computed","paper":{"title":"FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Wu, Lingzhi Gao, Zhenyuan Zhang","submitted_at":"2022-01-10T05:26:33Z","abstract_excerpt":"While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share their private models due to the inclusion of privacy-sensitive information. Knowledge distillation, which can extract model knowledge without accessing model parameters, is well-suited for this federated scenario. However, most distillation methods in federated learning (federated distillation) require a proxy dataset, which is difficult to obtain in the real world. Therefore, in this paper, we introduce a distribute"},"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":"2201.03169","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-10T05:26:33Z","cross_cats_sorted":[],"title_canon_sha256":"a14600416eaf0804a4ab8a05d35a52e27056390b9adfb8a9060e76cabcd56932","abstract_canon_sha256":"192b3dc16fab1b1bb7fe9c33d3a0f77280081800ee834dadf2f461950853cbb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:27.963308Z","signature_b64":"K46bFvqr4/bSHFbWh68gADllnF233mms3xcf7woiQYfnDM9w5ngcyGOHhYLKuGK5m3L6zIiCIDTdVkZKowqFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a075bdac06f9732cab499dfb58d49692d1b8c4b5fe0ef847cfb952de55c91c1","last_reissued_at":"2026-07-05T11:28:27.962821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:27.962821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Wu, Lingzhi Gao, Zhenyuan Zhang","submitted_at":"2022-01-10T05:26:33Z","abstract_excerpt":"While existing federated learning approaches primarily focus on aggregating local models to construct a global model, in realistic settings, some clients may be reluctant to share their private models due to the inclusion of privacy-sensitive information. Knowledge distillation, which can extract model knowledge without accessing model parameters, is well-suited for this federated scenario. However, most distillation methods in federated learning (federated distillation) require a proxy dataset, which is difficult to obtain in the real world. Therefore, in this paper, we introduce a distribute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03169","kind":"arxiv","version":5},"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/2201.03169/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":"2201.03169","created_at":"2026-07-05T11:28:27.962880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03169v5","created_at":"2026-07-05T11:28:27.962880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03169","created_at":"2026-07-05T11:28:27.962880+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIDVXWWAN6LT","created_at":"2026-07-05T11:28:27.962880+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIDVXWWAN6LTFSVU","created_at":"2026-07-05T11:28:27.962880+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIDVXWWA","created_at":"2026-07-05T11:28:27.962880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20456","citing_title":"Federated Learning-Distillation Alternation for Resource-Constrained IoT","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE","json":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE.json","graph_json":"https://pith.science/api/pith-number/PIDVXWWAN6LTFSVUTHP3LDKJNE/graph.json","events_json":"https://pith.science/api/pith-number/PIDVXWWAN6LTFSVUTHP3LDKJNE/events.json","paper":"https://pith.science/paper/PIDVXWWA"},"agent_actions":{"view_html":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE","download_json":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE.json","view_paper":"https://pith.science/paper/PIDVXWWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03169&json=true","fetch_graph":"https://pith.science/api/pith-number/PIDVXWWAN6LTFSVUTHP3LDKJNE/graph.json","fetch_events":"https://pith.science/api/pith-number/PIDVXWWAN6LTFSVUTHP3LDKJNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE/action/storage_attestation","attest_author":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE/action/author_attestation","sign_citation":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE/action/citation_signature","submit_replication":"https://pith.science/pith/PIDVXWWAN6LTFSVUTHP3LDKJNE/action/replication_record"}},"created_at":"2026-07-05T11:28:27.962880+00:00","updated_at":"2026-07-05T11:28:27.962880+00:00"}