{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F5WTHZDU6ZUIIIUQDCIXG723MY","short_pith_number":"pith:F5WTHZDU","schema_version":"1.0","canonical_sha256":"2f6d33e474f6688422901891737f5b661bb7474835b6ffff2735ebbcb11d86b3","source":{"kind":"arxiv","id":"2307.07393","version":1},"attestation_state":"computed","paper":{"title":"L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Shen, Mina Alibeigi, Nicholas D. Lane, Pedro Porto Buarque de Gusm\\~ao, Yan Gao, Yasar Abbas Ur Rehman","submitted_at":"2023-07-14T15:07:30Z","abstract_excerpt":"The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of the learned visual representations without needing to move data around. However, client bias and divergence during FL aggregation caused by data heterogeneity limits the performance of learned visual representations on downstream tasks. In this paper, we propose a new aggregation str"},"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":"2307.07393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-14T15:07:30Z","cross_cats_sorted":[],"title_canon_sha256":"ad901a1158538d75f2cbb392368f0a0d23d7a9d60b208d00331360d6055b8c2f","abstract_canon_sha256":"fa5df61091eb2099ee27d317791a1985441a1f838372407f8456bdd7919441ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:54.993501Z","signature_b64":"FFoZ9udohHtXqEBdKBz/yhptxcJUIMBJcopaZhb64mo3lD27QoGDGgIBV6aESRdKyHK3M5uWoTPp0BfMla5cCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f6d33e474f6688422901891737f5b661bb7474835b6ffff2735ebbcb11d86b3","last_reissued_at":"2026-07-05T06:30:54.992975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:54.992975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiajun Shen, Mina Alibeigi, Nicholas D. Lane, Pedro Porto Buarque de Gusm\\~ao, Yan Gao, Yasar Abbas Ur Rehman","submitted_at":"2023-07-14T15:07:30Z","abstract_excerpt":"The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data privacy guarantees while also advancing the quality and robustness of the learned visual representations without needing to move data around. However, client bias and divergence during FL aggregation caused by data heterogeneity limits the performance of learned visual representations on downstream tasks. In this paper, we propose a new aggregation str"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07393","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/2307.07393/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":"2307.07393","created_at":"2026-07-05T06:30:54.993041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07393v1","created_at":"2026-07-05T06:30:54.993041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07393","created_at":"2026-07-05T06:30:54.993041+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5WTHZDU6ZUI","created_at":"2026-07-05T06:30:54.993041+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5WTHZDU6ZUIIIUQ","created_at":"2026-07-05T06:30:54.993041+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5WTHZDU","created_at":"2026-07-05T06:30:54.993041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY","json":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY.json","graph_json":"https://pith.science/api/pith-number/F5WTHZDU6ZUIIIUQDCIXG723MY/graph.json","events_json":"https://pith.science/api/pith-number/F5WTHZDU6ZUIIIUQDCIXG723MY/events.json","paper":"https://pith.science/paper/F5WTHZDU"},"agent_actions":{"view_html":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY","download_json":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY.json","view_paper":"https://pith.science/paper/F5WTHZDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07393&json=true","fetch_graph":"https://pith.science/api/pith-number/F5WTHZDU6ZUIIIUQDCIXG723MY/graph.json","fetch_events":"https://pith.science/api/pith-number/F5WTHZDU6ZUIIIUQDCIXG723MY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY/action/storage_attestation","attest_author":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY/action/author_attestation","sign_citation":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY/action/citation_signature","submit_replication":"https://pith.science/pith/F5WTHZDU6ZUIIIUQDCIXG723MY/action/replication_record"}},"created_at":"2026-07-05T06:30:54.993041+00:00","updated_at":"2026-07-05T06:30:54.993041+00:00"}