{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2R36W7G5SEFRVTZLPOBDKS4MG3","short_pith_number":"pith:2R36W7G5","canonical_record":{"source":{"id":"2505.24728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T15:52:05Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"e50f4653cbb51afd45b3dc0433a4025b1a938906d9abcc1b50382f9ebdddda03","abstract_canon_sha256":"40c7d78b72d9a8b757fda1bbdca103ef4ac6f76ae66b95ad55727864ac354c6a"},"schema_version":"1.0"},"canonical_sha256":"d477eb7cdd910b1acf2b7b82354b8c36c439472094fa69f98f2cb0f6303c3024","source":{"kind":"arxiv","id":"2505.24728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24728","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24728v1","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24728","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"2R36W7G5SEFR","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"2R36W7G5SEFRVTZL","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"2R36W7G5","created_at":"2026-07-05T11:12:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2R36W7G5SEFRVTZLPOBDKS4MG3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24728","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T15:52:05Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"e50f4653cbb51afd45b3dc0433a4025b1a938906d9abcc1b50382f9ebdddda03","abstract_canon_sha256":"40c7d78b72d9a8b757fda1bbdca103ef4ac6f76ae66b95ad55727864ac354c6a"},"schema_version":"1.0"},"canonical_sha256":"d477eb7cdd910b1acf2b7b82354b8c36c439472094fa69f98f2cb0f6303c3024","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:55.669629Z","signature_b64":"APglAy6pMpeFez4Y9umkMxYJbmPA1k49RX171bCEwhqe/w6nbhfA3+9avnrE3LA7/hsA98B9vwUWzxAPAtRaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d477eb7cdd910b1acf2b7b82354b8c36c439472094fa69f98f2cb0f6303c3024","last_reissued_at":"2026-07-05T11:12:55.669075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:55.669075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24728","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6gBWzomjuiLnS6rme6s3kJ0zFIGGC5fRssHYakjxTwgGf7YDzM25lIPfVxQQfkTMs7Jc2Xv7Hf2mD92RbWCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:06:27.910272Z"},"content_sha256":"a02879308ad0d53c9c44613d7cf4d3535a36e605f3fc34e5a41df247efbfcec2","schema_version":"1.0","event_id":"sha256:a02879308ad0d53c9c44613d7cf4d3535a36e605f3fc34e5a41df247efbfcec2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2R36W7G5SEFRVTZLPOBDKS4MG3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Federated Learning against Model Perturbation in Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Dongzi Jin, Yingyu Li, Yong Xiao","submitted_at":"2025-05-30T15:52:05Z","abstract_excerpt":"Federated Learning (FL) is a promising paradigm for realizing edge intelligence, allowing collaborative learning among distributed edge devices by sharing models instead of raw data. However, the shared models are often assumed to be ideal, which would be inevitably violated in practice due to various perturbations, leading to significant performance degradation. To overcome this challenge, we propose a novel method, termed Sharpness-Aware Minimization-based Robust Federated Learning (SMRFL), which aims to improve model robustness against perturbations by exploring the geometrical property of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24728","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/2505.24728/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tez7PaOnkg4ioWNKsbsYnlWSLepnmQx8gLtK3fGnyrlEe/HLGHy7bPoHVApcHuZWo2XV+gxNh8ikZhCTR0UBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:06:27.911488Z"},"content_sha256":"6670ba5edad125f47dacdee1f188b1f7da664dfd20a79c640c63c37bd3b83665","schema_version":"1.0","event_id":"sha256:6670ba5edad125f47dacdee1f188b1f7da664dfd20a79c640c63c37bd3b83665"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2R36W7G5SEFRVTZLPOBDKS4MG3/bundle.json","state_url":"https://pith.science/pith/2R36W7G5SEFRVTZLPOBDKS4MG3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2R36W7G5SEFRVTZLPOBDKS4MG3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T04:06:27Z","links":{"resolver":"https://pith.science/pith/2R36W7G5SEFRVTZLPOBDKS4MG3","bundle":"https://pith.science/pith/2R36W7G5SEFRVTZLPOBDKS4MG3/bundle.json","state":"https://pith.science/pith/2R36W7G5SEFRVTZLPOBDKS4MG3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2R36W7G5SEFRVTZLPOBDKS4MG3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2R36W7G5SEFRVTZLPOBDKS4MG3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"40c7d78b72d9a8b757fda1bbdca103ef4ac6f76ae66b95ad55727864ac354c6a","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T15:52:05Z","title_canon_sha256":"e50f4653cbb51afd45b3dc0433a4025b1a938906d9abcc1b50382f9ebdddda03"},"schema_version":"1.0","source":{"id":"2505.24728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24728","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24728v1","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24728","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"2R36W7G5SEFR","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"2R36W7G5SEFRVTZL","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"2R36W7G5","created_at":"2026-07-05T11:12:55Z"}],"graph_snapshots":[{"event_id":"sha256:6670ba5edad125f47dacdee1f188b1f7da664dfd20a79c640c63c37bd3b83665","target":"graph","created_at":"2026-07-05T11:12:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.24728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) is a promising paradigm for realizing edge intelligence, allowing collaborative learning among distributed edge devices by sharing models instead of raw data. However, the shared models are often assumed to be ideal, which would be inevitably violated in practice due to various perturbations, leading to significant performance degradation. To overcome this challenge, we propose a novel method, termed Sharpness-Aware Minimization-based Robust Federated Learning (SMRFL), which aims to improve model robustness against perturbations by exploring the geometrical property of ","authors_text":"Dongzi Jin, Yingyu Li, Yong Xiao","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T15:52:05Z","title":"Robust Federated Learning against Model Perturbation in Edge Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24728","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a02879308ad0d53c9c44613d7cf4d3535a36e605f3fc34e5a41df247efbfcec2","target":"record","created_at":"2026-07-05T11:12:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"40c7d78b72d9a8b757fda1bbdca103ef4ac6f76ae66b95ad55727864ac354c6a","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T15:52:05Z","title_canon_sha256":"e50f4653cbb51afd45b3dc0433a4025b1a938906d9abcc1b50382f9ebdddda03"},"schema_version":"1.0","source":{"id":"2505.24728","kind":"arxiv","version":1}},"canonical_sha256":"d477eb7cdd910b1acf2b7b82354b8c36c439472094fa69f98f2cb0f6303c3024","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d477eb7cdd910b1acf2b7b82354b8c36c439472094fa69f98f2cb0f6303c3024","first_computed_at":"2026-07-05T11:12:55.669075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:55.669075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"APglAy6pMpeFez4Y9umkMxYJbmPA1k49RX171bCEwhqe/w6nbhfA3+9avnrE3LA7/hsA98B9vwUWzxAPAtRaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:55.669629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a02879308ad0d53c9c44613d7cf4d3535a36e605f3fc34e5a41df247efbfcec2","sha256:6670ba5edad125f47dacdee1f188b1f7da664dfd20a79c640c63c37bd3b83665"],"state_sha256":"719e760a6c35ac2cc323112a300e857077c086c1d6f0c0e1153b613e1487263b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"52j4hihw7WMPg6t3qPg+IK7jKap5cWOUhhzvQ1iuXWXD3CcmzvvdPPuuecPV18GdGJut0H7CBw5UgvFoYiD2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:06:27.916637Z","bundle_sha256":"6c16990c2d1abaa1d3a13057a46ca8bd14b4f3a2e54ed5395b4c2d2c527bee0b"}}