{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4NZMC2SBBXWRAYNL5O4EXUFBNC","short_pith_number":"pith:4NZMC2SB","canonical_record":{"source":{"id":"2206.05558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T16:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"4456ebaa60b61fc62949522829e468459d8f51aa892aecf4fd27c7eda14cb14e","abstract_canon_sha256":"4f87a671130c5f62890a3af481e438a2029534682ec98e3d091477dcef26f9bc"},"schema_version":"1.0"},"canonical_sha256":"e372c16a410ded1061abebb84bd0a16885c460a52b929e61b6de7050d2660253","source":{"kind":"arxiv","id":"2206.05558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05558","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05558v1","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05558","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"pith_short_12","alias_value":"4NZMC2SBBXWR","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4NZMC2SBBXWRAYNL","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4NZMC2SB","created_at":"2026-07-05T04:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4NZMC2SBBXWRAYNL5O4EXUFBNC","target":"record","payload":{"canonical_record":{"source":{"id":"2206.05558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T16:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"4456ebaa60b61fc62949522829e468459d8f51aa892aecf4fd27c7eda14cb14e","abstract_canon_sha256":"4f87a671130c5f62890a3af481e438a2029534682ec98e3d091477dcef26f9bc"},"schema_version":"1.0"},"canonical_sha256":"e372c16a410ded1061abebb84bd0a16885c460a52b929e61b6de7050d2660253","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:00.498720Z","signature_b64":"zzfJFhlKvPiKs+Vf3tQ/hrg127DFF8diiN7AcOQq18pzkLYqfAEi1f8e+PfF858vUJvL/rL+//UuP0pVitrOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e372c16a410ded1061abebb84bd0a16885c460a52b929e61b6de7050d2660253","last_reissued_at":"2026-07-05T04:31:00.498377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:00.498377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.05558","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":"2026-07-05T04:31:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9wfG3k3qWDDVgSuKyEipEKnUN+mNeLT1U4SuZGG3d12RTrOqF4XoWlJJglympIbwopyc7Dfanh/gsG9c5lvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:30:18.996489Z"},"content_sha256":"64c452374b2f04e1ed2fad694ed0004140841740306879165370985f1cb36c99","schema_version":"1.0","event_id":"sha256:64c452374b2f04e1ed2fad694ed0004140841740306879165370985f1cb36c99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4NZMC2SBBXWRAYNL5O4EXUFBNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Communication-Efficient Robust Federated Learning with Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Heng Huang, Jian Pei, Junyi Li","submitted_at":"2022-06-11T16:21:17Z","abstract_excerpt":"Federated learning (FL) is a promising privacy-preserving machine learning paradigm over distributed located data. In FL, the data is kept locally by each user. This protects the user privacy, but also makes the server difficult to verify data quality, especially if the data are correctly labeled. Training with corrupted labels is harmful to the federated learning task; however, little attention has been paid to FL in the case of label noise. In this paper, we focus on this problem and propose a learning-based reweighting approach to mitigate the effect of noisy labels in FL. More precisely, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05558","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/2206.05558/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":"2026-07-05T04:31:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blaSnV0Ui7m54T/9ItIogui8qvSLzDdYXlg1zzZPbVv39CYg7x2oGMCU7x1dgV7Ykh+wkHaP4KJr7M3o+uscDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:30:18.997003Z"},"content_sha256":"8ff0bbd9b775fdf88475ac77cff255bb128180ea120f020701e9d4d7988209a5","schema_version":"1.0","event_id":"sha256:8ff0bbd9b775fdf88475ac77cff255bb128180ea120f020701e9d4d7988209a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC/bundle.json","state_url":"https://pith.science/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC/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":"2026-08-03T16:30:19Z","links":{"resolver":"https://pith.science/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC","bundle":"https://pith.science/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC/bundle.json","state":"https://pith.science/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NZMC2SBBXWRAYNL5O4EXUFBNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4NZMC2SBBXWRAYNL5O4EXUFBNC","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":"4f87a671130c5f62890a3af481e438a2029534682ec98e3d091477dcef26f9bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T16:21:17Z","title_canon_sha256":"4456ebaa60b61fc62949522829e468459d8f51aa892aecf4fd27c7eda14cb14e"},"schema_version":"1.0","source":{"id":"2206.05558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.05558","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.05558v1","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05558","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"pith_short_12","alias_value":"4NZMC2SBBXWR","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4NZMC2SBBXWRAYNL","created_at":"2026-07-05T04:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4NZMC2SB","created_at":"2026-07-05T04:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:8ff0bbd9b775fdf88475ac77cff255bb128180ea120f020701e9d4d7988209a5","target":"graph","created_at":"2026-07-05T04:31:00Z","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/2206.05558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) is a promising privacy-preserving machine learning paradigm over distributed located data. In FL, the data is kept locally by each user. This protects the user privacy, but also makes the server difficult to verify data quality, especially if the data are correctly labeled. Training with corrupted labels is harmful to the federated learning task; however, little attention has been paid to FL in the case of label noise. In this paper, we focus on this problem and propose a learning-based reweighting approach to mitigate the effect of noisy labels in FL. More precisely, w","authors_text":"Heng Huang, Jian Pei, Junyi Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T16:21:17Z","title":"Communication-Efficient Robust Federated Learning with Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05558","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":"sha256:64c452374b2f04e1ed2fad694ed0004140841740306879165370985f1cb36c99","target":"record","created_at":"2026-07-05T04:31:00Z","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":"4f87a671130c5f62890a3af481e438a2029534682ec98e3d091477dcef26f9bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-11T16:21:17Z","title_canon_sha256":"4456ebaa60b61fc62949522829e468459d8f51aa892aecf4fd27c7eda14cb14e"},"schema_version":"1.0","source":{"id":"2206.05558","kind":"arxiv","version":1}},"canonical_sha256":"e372c16a410ded1061abebb84bd0a16885c460a52b929e61b6de7050d2660253","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e372c16a410ded1061abebb84bd0a16885c460a52b929e61b6de7050d2660253","first_computed_at":"2026-07-05T04:31:00.498377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:00.498377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zzfJFhlKvPiKs+Vf3tQ/hrg127DFF8diiN7AcOQq18pzkLYqfAEi1f8e+PfF858vUJvL/rL+//UuP0pVitrOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:00.498720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.05558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64c452374b2f04e1ed2fad694ed0004140841740306879165370985f1cb36c99","sha256:8ff0bbd9b775fdf88475ac77cff255bb128180ea120f020701e9d4d7988209a5"],"state_sha256":"f35856663088a65cc86eb2b501e9822e739d484ed1ebfa5cea4abefa519ae309"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ywqym0+hqCtmX/XLPJJYZH2yL1CXRpKyVrEBgi0E+YM3LMDvM4VGpCkDlmum1ONzgpHEHymQpIbc8P9kSYBXBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:30:19.026175Z","bundle_sha256":"8f4341eef42a85f4a2e67210ef5b38b5aa4fb82d93754acf2f33715c7b6728b1"}}