{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QY5UE2SHXDMWAL544CBTJ5W3BM","short_pith_number":"pith:QY5UE2SH","canonical_record":{"source":{"id":"2412.15010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T16:22:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2ec326837de38b539a21fb5034cb2c4fcb3b352ce7fcadb11d2553988dabb436","abstract_canon_sha256":"03ead9a22b1c423060edf7b4ea50c79d451fdf40b8db373b1529a5ad787f6c18"},"schema_version":"1.0"},"canonical_sha256":"863b426a47b8d9602fbce08334f6db0b163abed6882a31020065657dd9ea5db2","source":{"kind":"arxiv","id":"2412.15010","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15010","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15010v2","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15010","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"QY5UE2SHXDMW","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"QY5UE2SHXDMWAL54","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"QY5UE2SH","created_at":"2026-07-05T12:07:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QY5UE2SHXDMWAL544CBTJ5W3BM","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T16:22:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2ec326837de38b539a21fb5034cb2c4fcb3b352ce7fcadb11d2553988dabb436","abstract_canon_sha256":"03ead9a22b1c423060edf7b4ea50c79d451fdf40b8db373b1529a5ad787f6c18"},"schema_version":"1.0"},"canonical_sha256":"863b426a47b8d9602fbce08334f6db0b163abed6882a31020065657dd9ea5db2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:36.822676Z","signature_b64":"wqW/G7svGHngDH7OGSlHUYKN/JCGPhKXAnDuDc3CDMHSJpwicn1sMtRPsL7F7bMSdJ/vCfFbsTIp1XiN7nnPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"863b426a47b8d9602fbce08334f6db0b163abed6882a31020065657dd9ea5db2","last_reissued_at":"2026-07-05T12:07:36.822163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:36.822163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15010","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvFnzywlQ+EA9vDP0OKm6l/K+6OE37SDbcMitLq/xLZ8lk/3xId6okNLivRfJcSG8iOTjrAp9kpj0SkzQ5TCAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:09:28.994980Z"},"content_sha256":"cff85865936406707718341f17e2885648c6e5baac5e449c8ac695463948c9c6","schema_version":"1.0","event_id":"sha256:cff85865936406707718341f17e2885648c6e5baac5e449c8ac695463948c9c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QY5UE2SHXDMWAL544CBTJ5W3BM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Nicolas Pugeault, Ozgu Goksu","submitted_at":"2024-12-19T16:22:37Z","abstract_excerpt":"Federated Learning offers a solution for decentralised model training, addressing the difficulties associated with distributed data and privacy in machine learning. However, the fact of data heterogeneity in federated learning frequently hinders the global model's generalisation, leading to low performance and adaptability to unseen data. This problem is particularly critical for specialised applications such as medical imaging, where both the data and the number of clients are limited. In this paper, we empirically demonstrate that inconsistencies in client-side training distributions substan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15010","kind":"arxiv","version":2},"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/2412.15010/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":"2026-07-05T12:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sm+rn2yTyRMq5eK5vnaI3POx8GuQe5cOcx3+9qjP0HPX9z+TQG/+l/jJmiFmtRl/seiTSlch4oSSVZdYjDcYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:09:28.995492Z"},"content_sha256":"2c9a13b4ff4340ef768a07ef2e7a1ac72d37aeffa4743ca82b8e49c9263639d8","schema_version":"1.0","event_id":"sha256:2c9a13b4ff4340ef768a07ef2e7a1ac72d37aeffa4743ca82b8e49c9263639d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QY5UE2SHXDMWAL544CBTJ5W3BM/bundle.json","state_url":"https://pith.science/pith/QY5UE2SHXDMWAL544CBTJ5W3BM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QY5UE2SHXDMWAL544CBTJ5W3BM/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":"2026-08-09T20:09:28Z","links":{"resolver":"https://pith.science/pith/QY5UE2SHXDMWAL544CBTJ5W3BM","bundle":"https://pith.science/pith/QY5UE2SHXDMWAL544CBTJ5W3BM/bundle.json","state":"https://pith.science/pith/QY5UE2SHXDMWAL544CBTJ5W3BM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QY5UE2SHXDMWAL544CBTJ5W3BM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QY5UE2SHXDMWAL544CBTJ5W3BM","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":"03ead9a22b1c423060edf7b4ea50c79d451fdf40b8db373b1529a5ad787f6c18","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T16:22:37Z","title_canon_sha256":"2ec326837de38b539a21fb5034cb2c4fcb3b352ce7fcadb11d2553988dabb436"},"schema_version":"1.0","source":{"id":"2412.15010","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15010","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15010v2","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15010","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"QY5UE2SHXDMW","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"QY5UE2SHXDMWAL54","created_at":"2026-07-05T12:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"QY5UE2SH","created_at":"2026-07-05T12:07:36Z"}],"graph_snapshots":[{"event_id":"sha256:2c9a13b4ff4340ef768a07ef2e7a1ac72d37aeffa4743ca82b8e49c9263639d8","target":"graph","created_at":"2026-07-05T12:07:36Z","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/2412.15010/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning offers a solution for decentralised model training, addressing the difficulties associated with distributed data and privacy in machine learning. However, the fact of data heterogeneity in federated learning frequently hinders the global model's generalisation, leading to low performance and adaptability to unseen data. This problem is particularly critical for specialised applications such as medical imaging, where both the data and the number of clients are limited. In this paper, we empirically demonstrate that inconsistencies in client-side training distributions substan","authors_text":"Nicolas Pugeault, Ozgu Goksu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T16:22:37Z","title":"Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15010","kind":"arxiv","version":2},"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:cff85865936406707718341f17e2885648c6e5baac5e449c8ac695463948c9c6","target":"record","created_at":"2026-07-05T12:07:36Z","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":"03ead9a22b1c423060edf7b4ea50c79d451fdf40b8db373b1529a5ad787f6c18","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-19T16:22:37Z","title_canon_sha256":"2ec326837de38b539a21fb5034cb2c4fcb3b352ce7fcadb11d2553988dabb436"},"schema_version":"1.0","source":{"id":"2412.15010","kind":"arxiv","version":2}},"canonical_sha256":"863b426a47b8d9602fbce08334f6db0b163abed6882a31020065657dd9ea5db2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"863b426a47b8d9602fbce08334f6db0b163abed6882a31020065657dd9ea5db2","first_computed_at":"2026-07-05T12:07:36.822163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:36.822163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqW/G7svGHngDH7OGSlHUYKN/JCGPhKXAnDuDc3CDMHSJpwicn1sMtRPsL7F7bMSdJ/vCfFbsTIp1XiN7nnPDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:36.822676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15010","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cff85865936406707718341f17e2885648c6e5baac5e449c8ac695463948c9c6","sha256:2c9a13b4ff4340ef768a07ef2e7a1ac72d37aeffa4743ca82b8e49c9263639d8"],"state_sha256":"cb8cf48905373d1751985502baa6c333238cf739b622b3a5a3a7deecfa27a7fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6epOscXKbMVtycAbzRFfu7ZsT5ATFrp5wGrJDYGR9dH9O2BIdYcG9fB6rQeSK3N67WJXX6+jt9psf4ktkMmgBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:09:28.999465Z","bundle_sha256":"5e9d4bf5b3bb30d9000e24b05cf2dd05334461582b6f74af4d5a96b3f42df6f7"}}