{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O4PVF6TSM6SFLIPOTLOXEZH6BG","short_pith_number":"pith:O4PVF6TS","canonical_record":{"source":{"id":"2207.04330","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T19:47:52Z","cross_cats_sorted":["cs.DC","math.OC","stat.ML"],"title_canon_sha256":"00d61bf7d954b45ec2bec775e5e3aaeb4d45da8b111cbd120b7824541a653584","abstract_canon_sha256":"37baf08fa7deeb4c87ba8d8919d85644f373860401df59b85018fdb00d91f218"},"schema_version":"1.0"},"canonical_sha256":"771f52fa7267a455a1ee9add7264fe09ae32afa81ca2cc40dd951f094a5aeec0","source":{"kind":"arxiv","id":"2207.04330","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04330","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04330v6","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04330","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"O4PVF6TSM6SF","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"pith_short_16","alias_value":"O4PVF6TSM6SFLIPO","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"pith_short_8","alias_value":"O4PVF6TS","created_at":"2026-07-05T04:59:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O4PVF6TSM6SFLIPOTLOXEZH6BG","target":"record","payload":{"canonical_record":{"source":{"id":"2207.04330","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T19:47:52Z","cross_cats_sorted":["cs.DC","math.OC","stat.ML"],"title_canon_sha256":"00d61bf7d954b45ec2bec775e5e3aaeb4d45da8b111cbd120b7824541a653584","abstract_canon_sha256":"37baf08fa7deeb4c87ba8d8919d85644f373860401df59b85018fdb00d91f218"},"schema_version":"1.0"},"canonical_sha256":"771f52fa7267a455a1ee9add7264fe09ae32afa81ca2cc40dd951f094a5aeec0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:41.588170Z","signature_b64":"56YESyN51kO4tf1PPyIBnPrHdamXX4UFvqu14+lkzQI/4a2JA2C7kCudFhp7FAkhGO/6/tx0jqXwlIoKmKTDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"771f52fa7267a455a1ee9add7264fe09ae32afa81ca2cc40dd951f094a5aeec0","last_reissued_at":"2026-07-05T04:59:41.587681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:41.587681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.04330","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uswMtZKN5clHaWMI9ImoSoxnxnapXOfxVW+eJYz5MTijxwrb08ji/LijmmubXaEIB4ElRlY4H+GD+yvH9qEpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:05:48.109382Z"},"content_sha256":"3392f5a6857a2582dca907153b6997341e72535d3640ab5d255eaf07a615da16","schema_version":"1.0","event_id":"sha256:3392f5a6857a2582dca907153b6997341e72535d3640ab5d255eaf07a615da16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O4PVF6TSM6SFLIPOTLOXEZH6BG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Model Federated Learning with Provable Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gauri Joshi, Neelkamal Bhuyan, Sharayu Moharir","submitted_at":"2022-07-09T19:47:52Z","abstract_excerpt":"Federated Learning (FL) is a variant of distributed learning where edge devices collaborate to learn a model without sharing their data with the central server or each other. We refer to the process of training multiple independent models simultaneously in a federated setting using a common pool of clients as multi-model FL. In this work, we propose two variants of the popular FedAvg algorithm for multi-model FL, with provable convergence guarantees. We further show that for the same amount of computation, multi-model FL can have better performance than training each model separately. We suppl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04330","kind":"arxiv","version":6},"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/2207.04330/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":"2026-07-05T04:59:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BsF+0xcUVGzk9OwRu4iZZhevS9pD+JC2/yDFjw9EqQ+nf+pdFMbES8JrNZ8RaemapweY3qmdmysW6+YeoKYVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:05:48.109907Z"},"content_sha256":"eda6d8179f1e798c4e7ea56aa50ba7f69dbef43e916b95f2cf53c4da125af9d4","schema_version":"1.0","event_id":"sha256:eda6d8179f1e798c4e7ea56aa50ba7f69dbef43e916b95f2cf53c4da125af9d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG/bundle.json","state_url":"https://pith.science/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG/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":"2026-08-06T05:05:48Z","links":{"resolver":"https://pith.science/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG","bundle":"https://pith.science/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG/bundle.json","state":"https://pith.science/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4PVF6TSM6SFLIPOTLOXEZH6BG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4PVF6TSM6SFLIPOTLOXEZH6BG","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":"37baf08fa7deeb4c87ba8d8919d85644f373860401df59b85018fdb00d91f218","cross_cats_sorted":["cs.DC","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T19:47:52Z","title_canon_sha256":"00d61bf7d954b45ec2bec775e5e3aaeb4d45da8b111cbd120b7824541a653584"},"schema_version":"1.0","source":{"id":"2207.04330","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04330","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04330v6","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04330","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"O4PVF6TSM6SF","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"pith_short_16","alias_value":"O4PVF6TSM6SFLIPO","created_at":"2026-07-05T04:59:41Z"},{"alias_kind":"pith_short_8","alias_value":"O4PVF6TS","created_at":"2026-07-05T04:59:41Z"}],"graph_snapshots":[{"event_id":"sha256:eda6d8179f1e798c4e7ea56aa50ba7f69dbef43e916b95f2cf53c4da125af9d4","target":"graph","created_at":"2026-07-05T04:59:41Z","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/2207.04330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) is a variant of distributed learning where edge devices collaborate to learn a model without sharing their data with the central server or each other. We refer to the process of training multiple independent models simultaneously in a federated setting using a common pool of clients as multi-model FL. In this work, we propose two variants of the popular FedAvg algorithm for multi-model FL, with provable convergence guarantees. We further show that for the same amount of computation, multi-model FL can have better performance than training each model separately. We suppl","authors_text":"Gauri Joshi, Neelkamal Bhuyan, Sharayu Moharir","cross_cats":["cs.DC","math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T19:47:52Z","title":"Multi-Model Federated Learning with Provable Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04330","kind":"arxiv","version":6},"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":"sha256:3392f5a6857a2582dca907153b6997341e72535d3640ab5d255eaf07a615da16","target":"record","created_at":"2026-07-05T04:59:41Z","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":"37baf08fa7deeb4c87ba8d8919d85644f373860401df59b85018fdb00d91f218","cross_cats_sorted":["cs.DC","math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-09T19:47:52Z","title_canon_sha256":"00d61bf7d954b45ec2bec775e5e3aaeb4d45da8b111cbd120b7824541a653584"},"schema_version":"1.0","source":{"id":"2207.04330","kind":"arxiv","version":6}},"canonical_sha256":"771f52fa7267a455a1ee9add7264fe09ae32afa81ca2cc40dd951f094a5aeec0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"771f52fa7267a455a1ee9add7264fe09ae32afa81ca2cc40dd951f094a5aeec0","first_computed_at":"2026-07-05T04:59:41.587681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:41.587681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"56YESyN51kO4tf1PPyIBnPrHdamXX4UFvqu14+lkzQI/4a2JA2C7kCudFhp7FAkhGO/6/tx0jqXwlIoKmKTDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:41.588170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.04330","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3392f5a6857a2582dca907153b6997341e72535d3640ab5d255eaf07a615da16","sha256:eda6d8179f1e798c4e7ea56aa50ba7f69dbef43e916b95f2cf53c4da125af9d4"],"state_sha256":"4e29c1e902928b5a11d50eab0f15aa1452d53237c7a910991dec52dd4b03c003"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjUYSJxDVS02orte/II8FuxYvt5ihSNGG9k32piY4lnJtcm5QxuUeozoL65DF8rj/8T7YE1y46yAZyBMxiotBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:05:48.114284Z","bundle_sha256":"66f742089542341001914e2785bbfed7135b4a5f227c05511707499850a3530a"}}