{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WI7AX2HOZ2BMFB7YYQPQQURRVJ","short_pith_number":"pith:WI7AX2HO","canonical_record":{"source":{"id":"2205.10920","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-22T20:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"51286b3f27e9d2cd841f6150f0e3c7803cf0e83ccf056df6ab860bac3690aebc","abstract_canon_sha256":"2330645d851f1b83a7cb51508254157e9dc1fbfc2fef83755a6049234aa103c8"},"schema_version":"1.0"},"canonical_sha256":"b23e0be8eece82c287f8c41f085231aa519366ad1a5bb8a027e8479d695b29d3","source":{"kind":"arxiv","id":"2205.10920","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10920","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10920v4","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10920","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"WI7AX2HOZ2BM","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"pith_short_16","alias_value":"WI7AX2HOZ2BMFB7Y","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"pith_short_8","alias_value":"WI7AX2HO","created_at":"2026-07-05T06:23:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WI7AX2HOZ2BMFB7YYQPQQURRVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2205.10920","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-22T20:08:14Z","cross_cats_sorted":[],"title_canon_sha256":"51286b3f27e9d2cd841f6150f0e3c7803cf0e83ccf056df6ab860bac3690aebc","abstract_canon_sha256":"2330645d851f1b83a7cb51508254157e9dc1fbfc2fef83755a6049234aa103c8"},"schema_version":"1.0"},"canonical_sha256":"b23e0be8eece82c287f8c41f085231aa519366ad1a5bb8a027e8479d695b29d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:53.824968Z","signature_b64":"eTwDmjtnsEF31pDVOe47E9AP5gCHS0dQtlobRHpRkRhLG8EGdqtC+UG8ayHbA4FISv+EggsioGebsIig2SARDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b23e0be8eece82c287f8c41f085231aa519366ad1a5bb8a027e8479d695b29d3","last_reissued_at":"2026-07-05T06:23:53.824540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:53.824540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.10920","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTIMhyHCeBwhvaQM5ICH1BSIFIf/0okNL6f4NYwjEuh5VgPe7hAmX8rJCiiSxtt2b6Ga70H2a8JE1rZqC6drCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:58:32.438032Z"},"content_sha256":"262563a293146ffc450f8b158f4d931ec024a33603f1b89f614caaae70a2a1be","schema_version":"1.0","event_id":"sha256:262563a293146ffc450f8b158f4d931ec024a33603f1b89f614caaae70a2a1be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WI7AX2HOZ2BMFB7YYQPQQURRVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Test-Time Robust Personalization for Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Liangze Jiang, Tao Lin","submitted_at":"2022-05-22T20:08:14Z","abstract_excerpt":"Federated Learning (FL) is a machine learning paradigm where many clients collaboratively learn a shared global model with decentralized training data. Personalized FL additionally adapts the global model to different clients, achieving promising results on consistent local training and test distributions. However, for real-world personalized FL applications, it is crucial to go one step further: robustifying FL models under the evolving local test set during deployment, where various distribution shifts can arise. In this work, we identify the pitfalls of existing works under test-time distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10920","kind":"arxiv","version":4},"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/2205.10920/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":"2026-07-05T06:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T0mM76lSGhTYE0Hjh0f9IGkPwTeI1l3dVzoUxv4ivcFpPUO/bcBC04OiBq9GSLh13iAZzBSX924ZgYr36kpTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:58:32.438425Z"},"content_sha256":"4198d9bf8f616bba51f9c58e51f60886949480666a0a3de5c141db3ace4ea12e","schema_version":"1.0","event_id":"sha256:4198d9bf8f616bba51f9c58e51f60886949480666a0a3de5c141db3ace4ea12e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ/bundle.json","state_url":"https://pith.science/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ/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":"2026-07-07T08:58:32Z","links":{"resolver":"https://pith.science/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ","bundle":"https://pith.science/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ/bundle.json","state":"https://pith.science/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WI7AX2HOZ2BMFB7YYQPQQURRVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WI7AX2HOZ2BMFB7YYQPQQURRVJ","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":"2330645d851f1b83a7cb51508254157e9dc1fbfc2fef83755a6049234aa103c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-22T20:08:14Z","title_canon_sha256":"51286b3f27e9d2cd841f6150f0e3c7803cf0e83ccf056df6ab860bac3690aebc"},"schema_version":"1.0","source":{"id":"2205.10920","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10920","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10920v4","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10920","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"WI7AX2HOZ2BM","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"pith_short_16","alias_value":"WI7AX2HOZ2BMFB7Y","created_at":"2026-07-05T06:23:53Z"},{"alias_kind":"pith_short_8","alias_value":"WI7AX2HO","created_at":"2026-07-05T06:23:53Z"}],"graph_snapshots":[{"event_id":"sha256:4198d9bf8f616bba51f9c58e51f60886949480666a0a3de5c141db3ace4ea12e","target":"graph","created_at":"2026-07-05T06:23:53Z","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/2205.10920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) is a machine learning paradigm where many clients collaboratively learn a shared global model with decentralized training data. Personalized FL additionally adapts the global model to different clients, achieving promising results on consistent local training and test distributions. However, for real-world personalized FL applications, it is crucial to go one step further: robustifying FL models under the evolving local test set during deployment, where various distribution shifts can arise. In this work, we identify the pitfalls of existing works under test-time distri","authors_text":"Liangze Jiang, Tao Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-22T20:08:14Z","title":"Test-Time Robust Personalization for Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10920","kind":"arxiv","version":4},"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":"sha256:262563a293146ffc450f8b158f4d931ec024a33603f1b89f614caaae70a2a1be","target":"record","created_at":"2026-07-05T06:23:53Z","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":"2330645d851f1b83a7cb51508254157e9dc1fbfc2fef83755a6049234aa103c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-22T20:08:14Z","title_canon_sha256":"51286b3f27e9d2cd841f6150f0e3c7803cf0e83ccf056df6ab860bac3690aebc"},"schema_version":"1.0","source":{"id":"2205.10920","kind":"arxiv","version":4}},"canonical_sha256":"b23e0be8eece82c287f8c41f085231aa519366ad1a5bb8a027e8479d695b29d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b23e0be8eece82c287f8c41f085231aa519366ad1a5bb8a027e8479d695b29d3","first_computed_at":"2026-07-05T06:23:53.824540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:53.824540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTwDmjtnsEF31pDVOe47E9AP5gCHS0dQtlobRHpRkRhLG8EGdqtC+UG8ayHbA4FISv+EggsioGebsIig2SARDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:53.824968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10920","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:262563a293146ffc450f8b158f4d931ec024a33603f1b89f614caaae70a2a1be","sha256:4198d9bf8f616bba51f9c58e51f60886949480666a0a3de5c141db3ace4ea12e"],"state_sha256":"1d747c60cf11ca9344841c1eb13ff57a83e3cf89d4d6e9e8f49e03fc01240e4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pORTGFcWxHZiPPLgI5cfbL8Tza9exn2/Rz7I4rNmcLdhG+3Bj7mj6BzW2EiZEoRE57aba/V/xIPwG6TKrs2sAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:58:32.440389Z","bundle_sha256":"a87a8ecc20d591cd0b1fad7dbd05c4d874beb73fee4d48fc0e995e339061718b"}}