{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V5YKQTZ7MC5EOICD6KHYGJOSRT","short_pith_number":"pith:V5YKQTZ7","canonical_record":{"source":{"id":"2208.11669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-24T17:05:47Z","cross_cats_sorted":["cs.CR","eess.IV","q-bio.QM"],"title_canon_sha256":"fbf559fdfb119cee841a4cb3b06eb93f2ceb135cd189e4b08c8c7d4d3459ab1d","abstract_canon_sha256":"81568879bd94c6d7636458a04522e2bff56e874543cc3471c8bfc066380ffe9b"},"schema_version":"1.0"},"canonical_sha256":"af70a84f3f60ba472043f28f8325d28cea8e0ffab1e7d39be651eb6dab8d73bf","source":{"kind":"arxiv","id":"2208.11669","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11669","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11669v1","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11669","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"pith_short_12","alias_value":"V5YKQTZ7MC5E","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"pith_short_16","alias_value":"V5YKQTZ7MC5EOICD","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"pith_short_8","alias_value":"V5YKQTZ7","created_at":"2026-07-05T04:51:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V5YKQTZ7MC5EOICD6KHYGJOSRT","target":"record","payload":{"canonical_record":{"source":{"id":"2208.11669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-24T17:05:47Z","cross_cats_sorted":["cs.CR","eess.IV","q-bio.QM"],"title_canon_sha256":"fbf559fdfb119cee841a4cb3b06eb93f2ceb135cd189e4b08c8c7d4d3459ab1d","abstract_canon_sha256":"81568879bd94c6d7636458a04522e2bff56e874543cc3471c8bfc066380ffe9b"},"schema_version":"1.0"},"canonical_sha256":"af70a84f3f60ba472043f28f8325d28cea8e0ffab1e7d39be651eb6dab8d73bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:17.779561Z","signature_b64":"lPTy4J+MPGX56kve4AiDVGGGlGcjTI94Ka6eF/5xKptPUBzj1CAuYK3MpRs8oR+AR72MhfndaVUK5xoEOm9nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af70a84f3f60ba472043f28f8325d28cea8e0ffab1e7d39be651eb6dab8d73bf","last_reissued_at":"2026-07-05T04:51:17.779115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:17.779115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.11669","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":"2026-07-05T04:51:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWzzoF5D1wywa0F94q8qOxJE/LGAnSWC15HUHU2XDTH54VnMt264+bpDncVQNt3lQ09G4t6PHrcwSL4zemVrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:23:21.458091Z"},"content_sha256":"4bed4fa0fa5a820f55e5ce20065d967116b851b21821412b9156c165272ec622","schema_version":"1.0","event_id":"sha256:4bed4fa0fa5a820f55e5ce20065d967116b851b21821412b9156c165272ec622"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V5YKQTZ7MC5EOICD6KHYGJOSRT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Sparsified Federated Neuroimaging Models via Weight Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","eess.IV","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dimitris Stripelis, Greg Ver Steeg, Jos\\'e Luis Ambite, Nikhil Dhinagar, Paul Thompson, Umang Gupta","submitted_at":"2022-08-24T17:05:47Z","abstract_excerpt":"Federated training of large deep neural networks can often be restrictive due to the increasing costs of communicating the updates with increasing model sizes. Various model pruning techniques have been designed in centralized settings to reduce inference times. Combining centralized pruning techniques with federated training seems intuitive for reducing communication costs -- by pruning the model parameters right before the communication step. Moreover, such a progressive model pruning approach during training can also reduce training times/costs. To this end, we propose FedSparsify, which pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11669","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/2208.11669/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":"2026-07-05T04:51:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mM+i91qMkwtybKa7LQBVhBAj/fVSCDZ+puVNHXiCDMI9zKG8sIu7f3dqXbMlt8W4vt2LOJvwZi04TcW+2TabCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:23:21.458627Z"},"content_sha256":"db6df45b79b1ae2b8d645e376cb322b9e6e0373c99030c2017689a991cc67099","schema_version":"1.0","event_id":"sha256:db6df45b79b1ae2b8d645e376cb322b9e6e0373c99030c2017689a991cc67099"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT/bundle.json","state_url":"https://pith.science/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT/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":"2026-08-04T14:23:21Z","links":{"resolver":"https://pith.science/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT","bundle":"https://pith.science/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT/bundle.json","state":"https://pith.science/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5YKQTZ7MC5EOICD6KHYGJOSRT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V5YKQTZ7MC5EOICD6KHYGJOSRT","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":"81568879bd94c6d7636458a04522e2bff56e874543cc3471c8bfc066380ffe9b","cross_cats_sorted":["cs.CR","eess.IV","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-24T17:05:47Z","title_canon_sha256":"fbf559fdfb119cee841a4cb3b06eb93f2ceb135cd189e4b08c8c7d4d3459ab1d"},"schema_version":"1.0","source":{"id":"2208.11669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11669","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11669v1","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11669","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"pith_short_12","alias_value":"V5YKQTZ7MC5E","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"pith_short_16","alias_value":"V5YKQTZ7MC5EOICD","created_at":"2026-07-05T04:51:17Z"},{"alias_kind":"pith_short_8","alias_value":"V5YKQTZ7","created_at":"2026-07-05T04:51:17Z"}],"graph_snapshots":[{"event_id":"sha256:db6df45b79b1ae2b8d645e376cb322b9e6e0373c99030c2017689a991cc67099","target":"graph","created_at":"2026-07-05T04:51:17Z","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/2208.11669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated training of large deep neural networks can often be restrictive due to the increasing costs of communicating the updates with increasing model sizes. Various model pruning techniques have been designed in centralized settings to reduce inference times. Combining centralized pruning techniques with federated training seems intuitive for reducing communication costs -- by pruning the model parameters right before the communication step. Moreover, such a progressive model pruning approach during training can also reduce training times/costs. To this end, we propose FedSparsify, which pe","authors_text":"Dimitris Stripelis, Greg Ver Steeg, Jos\\'e Luis Ambite, Nikhil Dhinagar, Paul Thompson, Umang Gupta","cross_cats":["cs.CR","eess.IV","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-24T17:05:47Z","title":"Towards Sparsified Federated Neuroimaging Models via Weight Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11669","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":"sha256:4bed4fa0fa5a820f55e5ce20065d967116b851b21821412b9156c165272ec622","target":"record","created_at":"2026-07-05T04:51:17Z","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":"81568879bd94c6d7636458a04522e2bff56e874543cc3471c8bfc066380ffe9b","cross_cats_sorted":["cs.CR","eess.IV","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-24T17:05:47Z","title_canon_sha256":"fbf559fdfb119cee841a4cb3b06eb93f2ceb135cd189e4b08c8c7d4d3459ab1d"},"schema_version":"1.0","source":{"id":"2208.11669","kind":"arxiv","version":1}},"canonical_sha256":"af70a84f3f60ba472043f28f8325d28cea8e0ffab1e7d39be651eb6dab8d73bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af70a84f3f60ba472043f28f8325d28cea8e0ffab1e7d39be651eb6dab8d73bf","first_computed_at":"2026-07-05T04:51:17.779115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:17.779115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lPTy4J+MPGX56kve4AiDVGGGlGcjTI94Ka6eF/5xKptPUBzj1CAuYK3MpRs8oR+AR72MhfndaVUK5xoEOm9nCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:17.779561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.11669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bed4fa0fa5a820f55e5ce20065d967116b851b21821412b9156c165272ec622","sha256:db6df45b79b1ae2b8d645e376cb322b9e6e0373c99030c2017689a991cc67099"],"state_sha256":"3882722be167de804bba508ddeee49785b316fa3b312c341179ce950800b5cbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5EJX5USgfk9ByAsX9bbWyWkSjRshrxRGd26G2hCTrgFCD6rEfujdoJzm+NPQD2rCBOGImPEOnU7EbLiZR9kCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:23:21.475268Z","bundle_sha256":"6b8c72218d37c9201c4bb6829c9f62f4650cd69104379aa231211eaf786a729a"}}