{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AAYPTSLH4YVSR5KA67CG3OO2IW","short_pith_number":"pith:AAYPTSLH","schema_version":"1.0","canonical_sha256":"0030f9c967e62b28f540f7c46db9da45ab33d448617670811d7580903c9c8e67","source":{"kind":"arxiv","id":"2607.02447","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Yuan, Nan Yang, Shuai Wang, Xuanyu Chen","submitted_at":"2026-07-02T17:17:05Z","abstract_excerpt":"Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data. However, D-SSL faces the critical challenge of data heterogeneity, and there is limited theoretical understanding of how different D-SSL frameworks respond to this challenge. To fill this gap, we present a rigorous theoretical analysis of the robustness of D-SSL frameworks under non-IID (non-independent and identically distributed) settings. Our results show that pre-training with Masked Image Modeling (MIM) is inherently more robust to heterogeneous "},"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":"2607.02447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T17:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"88446fa13e17671b65ebf0803285fd9844acb4d96349efedc6165bd3d1021eb5","abstract_canon_sha256":"55027eaad90d72b55476788051516f7742d6fc5c1dbf5126758a752079c718ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:59.453469Z","signature_b64":"BM1obL0i8nEDv2RU9dc2mVUh8frwd+LpjzT/HprPgcqo9dV96rUhJHQoOmbqmUkbSn/iVx1J9qB1rNtLhgGRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0030f9c967e62b28f540f7c46db9da45ab33d448617670811d7580903c9c8e67","last_reissued_at":"2026-07-03T01:17:59.453090Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:59.453090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Yuan, Nan Yang, Shuai Wang, Xuanyu Chen","submitted_at":"2026-07-02T17:17:05Z","abstract_excerpt":"Recent research has introduced distributed self-supervised learning (D-SSL) approaches to leverage vast amounts of unlabeled decentralized data. However, D-SSL faces the critical challenge of data heterogeneity, and there is limited theoretical understanding of how different D-SSL frameworks respond to this challenge. To fill this gap, we present a rigorous theoretical analysis of the robustness of D-SSL frameworks under non-IID (non-independent and identically distributed) settings. Our results show that pre-training with Masked Image Modeling (MIM) is inherently more robust to heterogeneous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02447","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/2607.02447/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":"2607.02447","created_at":"2026-07-03T01:17:59.453145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02447v1","created_at":"2026-07-03T01:17:59.453145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02447","created_at":"2026-07-03T01:17:59.453145+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAYPTSLH4YVS","created_at":"2026-07-03T01:17:59.453145+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAYPTSLH4YVSR5KA","created_at":"2026-07-03T01:17:59.453145+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAYPTSLH","created_at":"2026-07-03T01:17:59.453145+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/AAYPTSLH4YVSR5KA67CG3OO2IW","json":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW.json","graph_json":"https://pith.science/api/pith-number/AAYPTSLH4YVSR5KA67CG3OO2IW/graph.json","events_json":"https://pith.science/api/pith-number/AAYPTSLH4YVSR5KA67CG3OO2IW/events.json","paper":"https://pith.science/paper/AAYPTSLH"},"agent_actions":{"view_html":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW","download_json":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW.json","view_paper":"https://pith.science/paper/AAYPTSLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02447&json=true","fetch_graph":"https://pith.science/api/pith-number/AAYPTSLH4YVSR5KA67CG3OO2IW/graph.json","fetch_events":"https://pith.science/api/pith-number/AAYPTSLH4YVSR5KA67CG3OO2IW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW/action/storage_attestation","attest_author":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW/action/author_attestation","sign_citation":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW/action/citation_signature","submit_replication":"https://pith.science/pith/AAYPTSLH4YVSR5KA67CG3OO2IW/action/replication_record"}},"created_at":"2026-07-03T01:17:59.453145+00:00","updated_at":"2026-07-03T01:17:59.453145+00:00"}