{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QCKFNUOFTNYKHRGGJAUJBWQBNZ","short_pith_number":"pith:QCKFNUOF","canonical_record":{"source":{"id":"2509.04107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T11:11:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3d0be74e3a591b80622fdd66055bc6479021cbd2832e22c1f43f2e869acb3ec6","abstract_canon_sha256":"99ee70d3b4c415410e2881085a77037d4dac01b3f35d6e61a25a18d7e654b8a7"},"schema_version":"1.0"},"canonical_sha256":"809456d1c59b70a3c4c6482890da016e65bb6e893154ec15ae14e4a59599b094","source":{"kind":"arxiv","id":"2509.04107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04107","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04107v1","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04107","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"QCKFNUOFTNYK","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"QCKFNUOFTNYKHRGG","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"QCKFNUOF","created_at":"2026-07-05T12:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QCKFNUOFTNYKHRGGJAUJBWQBNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2509.04107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T11:11:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3d0be74e3a591b80622fdd66055bc6479021cbd2832e22c1f43f2e869acb3ec6","abstract_canon_sha256":"99ee70d3b4c415410e2881085a77037d4dac01b3f35d6e61a25a18d7e654b8a7"},"schema_version":"1.0"},"canonical_sha256":"809456d1c59b70a3c4c6482890da016e65bb6e893154ec15ae14e4a59599b094","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:53.582887Z","signature_b64":"DO5bK44x2GIxKDXz9BsG0+Eck/S9Uy23lDZ6Yy2I7kavuGmbGP7cqCIhpcAjMjy3euNN4ZT0OKIvQgF6kNW4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"809456d1c59b70a3c4c6482890da016e65bb6e893154ec15ae14e4a59599b094","last_reissued_at":"2026-07-05T12:04:53.582365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:53.582365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.04107","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":"2026-07-05T12:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jA8LXYRm706okjnG+bLWOWJvx857yQQKDIa1NecdElGLdvtHSqWJDALmzN92K7ZMekX3PNwh6DTgN5cSchY+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:06:48.996861Z"},"content_sha256":"664f84250a1b10228aa921734152e4b1c6ef2cb54852637be1a706d3bc63af17","schema_version":"1.0","event_id":"sha256:664f84250a1b10228aa921734152e4b1c6ef2cb54852637be1a706d3bc63af17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QCKFNUOFTNYKHRGGJAUJBWQBNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity","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":"2025-09-04T11:11:10Z","abstract_excerpt":"Federated Learning (FL) provides decentralised model training, which effectively tackles problems such as distributed data and privacy preservation. However, the generalisation of global models frequently faces challenges from data heterogeneity among clients. This challenge becomes even more pronounced when datasets are limited in size and class imbalance. To address data heterogeneity, we propose a novel method, \\textit{FedQuad}, that explicitly optimises smaller intra-class variance and larger inter-class variance across clients, thereby decreasing the negative impact of model aggregation o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04107","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/2509.04107/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":"2026-07-05T12:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+T0plAYZ4ectWfJqOmx3faPHcVQbC948G6TWxNyTjSsgOZMgI8WKbMmgkgzgrlgDKHli6Z4Q0YtXxVQQzzGaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:06:48.997419Z"},"content_sha256":"d0753893a04e37424122f9ce0e37019b4021e34c31cbc50e636ca8737bb64576","schema_version":"1.0","event_id":"sha256:d0753893a04e37424122f9ce0e37019b4021e34c31cbc50e636ca8737bb64576"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ/bundle.json","state_url":"https://pith.science/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ/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":"2026-08-06T08:06:48Z","links":{"resolver":"https://pith.science/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ","bundle":"https://pith.science/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ/bundle.json","state":"https://pith.science/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCKFNUOFTNYKHRGGJAUJBWQBNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QCKFNUOFTNYKHRGGJAUJBWQBNZ","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":"99ee70d3b4c415410e2881085a77037d4dac01b3f35d6e61a25a18d7e654b8a7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T11:11:10Z","title_canon_sha256":"3d0be74e3a591b80622fdd66055bc6479021cbd2832e22c1f43f2e869acb3ec6"},"schema_version":"1.0","source":{"id":"2509.04107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.04107","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2509.04107v1","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04107","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"QCKFNUOFTNYK","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"QCKFNUOFTNYKHRGG","created_at":"2026-07-05T12:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"QCKFNUOF","created_at":"2026-07-05T12:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:d0753893a04e37424122f9ce0e37019b4021e34c31cbc50e636ca8737bb64576","target":"graph","created_at":"2026-07-05T12:04:53Z","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/2509.04107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) provides decentralised model training, which effectively tackles problems such as distributed data and privacy preservation. However, the generalisation of global models frequently faces challenges from data heterogeneity among clients. This challenge becomes even more pronounced when datasets are limited in size and class imbalance. To address data heterogeneity, we propose a novel method, \\textit{FedQuad}, that explicitly optimises smaller intra-class variance and larger inter-class variance across clients, thereby decreasing the negative impact of model aggregation o","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":"2025-09-04T11:11:10Z","title":"FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04107","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":"sha256:664f84250a1b10228aa921734152e4b1c6ef2cb54852637be1a706d3bc63af17","target":"record","created_at":"2026-07-05T12:04:53Z","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":"99ee70d3b4c415410e2881085a77037d4dac01b3f35d6e61a25a18d7e654b8a7","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T11:11:10Z","title_canon_sha256":"3d0be74e3a591b80622fdd66055bc6479021cbd2832e22c1f43f2e869acb3ec6"},"schema_version":"1.0","source":{"id":"2509.04107","kind":"arxiv","version":1}},"canonical_sha256":"809456d1c59b70a3c4c6482890da016e65bb6e893154ec15ae14e4a59599b094","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"809456d1c59b70a3c4c6482890da016e65bb6e893154ec15ae14e4a59599b094","first_computed_at":"2026-07-05T12:04:53.582365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:53.582365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DO5bK44x2GIxKDXz9BsG0+Eck/S9Uy23lDZ6Yy2I7kavuGmbGP7cqCIhpcAjMjy3euNN4ZT0OKIvQgF6kNW4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:53.582887Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.04107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:664f84250a1b10228aa921734152e4b1c6ef2cb54852637be1a706d3bc63af17","sha256:d0753893a04e37424122f9ce0e37019b4021e34c31cbc50e636ca8737bb64576"],"state_sha256":"8125e928c77a3a0aa68cb0255144c57114f167e71633fabb1069a07f876541ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUKE/5ngNac6mHwfRQ98XKOoM/lv8R1TFoCBQE1mxVWwAC8SlZm4A1z3KKyh30P4W/ceNMBauYafGSMAFVBUCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:06:49.001741Z","bundle_sha256":"199f216809daf3ce9407da43d572ec42bd642edffa5f5f061d21d1f9760ffe42"}}