{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KVGEQWSFPTQXERUBCZQFVWA5OP","short_pith_number":"pith:KVGEQWSF","canonical_record":{"source":{"id":"2211.04742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T08:31:23Z","cross_cats_sorted":[],"title_canon_sha256":"c2a773dabcc8f38544784a5d99f7502f9b1ca84de055b147541321b3d1c8efd3","abstract_canon_sha256":"4776ff46201a9aa6117fb8bd6b9f2b4428a460d3b6a2c3b5d0c05a70d4eb866f"},"schema_version":"1.0"},"canonical_sha256":"554c485a457ce172468116605ad81d73e549c27ab41521956c578526eb7c1573","source":{"kind":"arxiv","id":"2211.04742","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04742","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04742v2","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04742","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"KVGEQWSFPTQX","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"KVGEQWSFPTQXERUB","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"KVGEQWSF","created_at":"2026-07-05T10:45:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KVGEQWSFPTQXERUBCZQFVWA5OP","target":"record","payload":{"canonical_record":{"source":{"id":"2211.04742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T08:31:23Z","cross_cats_sorted":[],"title_canon_sha256":"c2a773dabcc8f38544784a5d99f7502f9b1ca84de055b147541321b3d1c8efd3","abstract_canon_sha256":"4776ff46201a9aa6117fb8bd6b9f2b4428a460d3b6a2c3b5d0c05a70d4eb866f"},"schema_version":"1.0"},"canonical_sha256":"554c485a457ce172468116605ad81d73e549c27ab41521956c578526eb7c1573","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:02.586714Z","signature_b64":"29vs/mK6JadSh5jGeuIy/AZAiIdb4gL+xEtKSP8YNzCJ47/PHq0kztKzVdIEXjHRutPwmfSXPNZXsImGGsvUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"554c485a457ce172468116605ad81d73e549c27ab41521956c578526eb7c1573","last_reissued_at":"2026-07-05T10:45:02.586151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:02.586151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.04742","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":"2026-07-05T10:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOk1Ev6/rK3qgCyakYjT7j0MBfgZMUFx1nycn3dUS98BfhsD7yfk+8n0llwRrqDW47wfbaWBw4J0STL42LpwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:59:29.048562Z"},"content_sha256":"c4b5aea337db65aac6db7510c184a8149d0ea76fa1c8c88e879ee087427e861f","schema_version":"1.0","event_id":"sha256:c4b5aea337db65aac6db7510c184a8149d0ea76fa1c8c88e879ee087427e861f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KVGEQWSFPTQXERUBCZQFVWA5OP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Distillation for Federated Learning: a Practical Guide","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessio Mora, Irene Tenison, Irina Rish, Paolo Bellavista","submitted_at":"2022-11-09T08:31:23Z","abstract_excerpt":"Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however, have well known limits, i.e., model homogeneity, high communication cost, poor performance in presence of heterogeneous data distributions. Federated adaptations of regular Knowledge Distillation (KD) can solve or mitigate the weaknesses of parameter-averaging FL algorithms while possibly introducing other trade-offs. In this article, we originally present a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04742","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/2211.04742/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":"2026-07-05T10:45:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxkI4cpn76wC1roNzckzmc18HCD/VKPwXNh/rWg9N1gYLnpl5mIS1kZ/WYjdJ6XeDgWvHgT+HZHHFr5BWlfdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:59:29.050100Z"},"content_sha256":"8d2c90b4c345d2aeae4d44d43604e51caf0832b5aa43844255599999e2c494d1","schema_version":"1.0","event_id":"sha256:8d2c90b4c345d2aeae4d44d43604e51caf0832b5aa43844255599999e2c494d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KVGEQWSFPTQXERUBCZQFVWA5OP/bundle.json","state_url":"https://pith.science/pith/KVGEQWSFPTQXERUBCZQFVWA5OP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KVGEQWSFPTQXERUBCZQFVWA5OP/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":"2026-08-06T08:59:29Z","links":{"resolver":"https://pith.science/pith/KVGEQWSFPTQXERUBCZQFVWA5OP","bundle":"https://pith.science/pith/KVGEQWSFPTQXERUBCZQFVWA5OP/bundle.json","state":"https://pith.science/pith/KVGEQWSFPTQXERUBCZQFVWA5OP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KVGEQWSFPTQXERUBCZQFVWA5OP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KVGEQWSFPTQXERUBCZQFVWA5OP","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":"4776ff46201a9aa6117fb8bd6b9f2b4428a460d3b6a2c3b5d0c05a70d4eb866f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T08:31:23Z","title_canon_sha256":"c2a773dabcc8f38544784a5d99f7502f9b1ca84de055b147541321b3d1c8efd3"},"schema_version":"1.0","source":{"id":"2211.04742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04742","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04742v2","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04742","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"pith_short_12","alias_value":"KVGEQWSFPTQX","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"pith_short_16","alias_value":"KVGEQWSFPTQXERUB","created_at":"2026-07-05T10:45:02Z"},{"alias_kind":"pith_short_8","alias_value":"KVGEQWSF","created_at":"2026-07-05T10:45:02Z"}],"graph_snapshots":[{"event_id":"sha256:8d2c90b4c345d2aeae4d44d43604e51caf0832b5aa43844255599999e2c494d1","target":"graph","created_at":"2026-07-05T10:45:02Z","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/2211.04742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data. The most used algorithms for FL are parameter-averaging based schemes (e.g., Federated Averaging) that, however, have well known limits, i.e., model homogeneity, high communication cost, poor performance in presence of heterogeneous data distributions. Federated adaptations of regular Knowledge Distillation (KD) can solve or mitigate the weaknesses of parameter-averaging FL algorithms while possibly introducing other trade-offs. In this article, we originally present a","authors_text":"Alessio Mora, Irene Tenison, Irina Rish, Paolo Bellavista","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T08:31:23Z","title":"Knowledge Distillation for Federated Learning: a Practical Guide"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04742","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:c4b5aea337db65aac6db7510c184a8149d0ea76fa1c8c88e879ee087427e861f","target":"record","created_at":"2026-07-05T10:45:02Z","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":"4776ff46201a9aa6117fb8bd6b9f2b4428a460d3b6a2c3b5d0c05a70d4eb866f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-09T08:31:23Z","title_canon_sha256":"c2a773dabcc8f38544784a5d99f7502f9b1ca84de055b147541321b3d1c8efd3"},"schema_version":"1.0","source":{"id":"2211.04742","kind":"arxiv","version":2}},"canonical_sha256":"554c485a457ce172468116605ad81d73e549c27ab41521956c578526eb7c1573","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"554c485a457ce172468116605ad81d73e549c27ab41521956c578526eb7c1573","first_computed_at":"2026-07-05T10:45:02.586151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:02.586151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"29vs/mK6JadSh5jGeuIy/AZAiIdb4gL+xEtKSP8YNzCJ47/PHq0kztKzVdIEXjHRutPwmfSXPNZXsImGGsvUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:02.586714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4b5aea337db65aac6db7510c184a8149d0ea76fa1c8c88e879ee087427e861f","sha256:8d2c90b4c345d2aeae4d44d43604e51caf0832b5aa43844255599999e2c494d1"],"state_sha256":"37709e57ca3409f554d10ca4e14fb26965b10ad24ee31d69e18c7518e3ae93b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLz9oGZSJ/LEW2xxyr/tCEs1vghXuvmuU6m9Wwwyo0eqrGAMugFMf9DXovXPWh2gAA1Bv7teZ+QEJzTyjwj4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:59:29.060381Z","bundle_sha256":"32ba209e68660e0a9095371109697c3d334aa4781c13aa9827b3cc0092e19bc9"}}