{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VQTTTNDZ3SWC3RGQ4BVNSJWJ32","short_pith_number":"pith:VQTTTNDZ","canonical_record":{"source":{"id":"2212.07414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T18:54:46Z","cross_cats_sorted":["cs.IT","eess.SP","math.IT","stat.ML"],"title_canon_sha256":"ff09efd23e2ff2c1ace1006222ebaf300004c70d8ad97564cc9124bb824bee6d","abstract_canon_sha256":"6548893988195319a6f905a0290d6797b2c26f2c5a9dec51974ae8d16a0b0ec9"},"schema_version":"1.0"},"canonical_sha256":"ac2739b479dcac2dc4d0e06ad926c9de8bff58175b13bc0d640ac06f1c3b0ca7","source":{"kind":"arxiv","id":"2212.07414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07414","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07414v1","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07414","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"VQTTTNDZ3SWC","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"VQTTTNDZ3SWC3RGQ","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"VQTTTNDZ","created_at":"2026-07-05T05:25:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VQTTTNDZ3SWC3RGQ4BVNSJWJ32","target":"record","payload":{"canonical_record":{"source":{"id":"2212.07414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T18:54:46Z","cross_cats_sorted":["cs.IT","eess.SP","math.IT","stat.ML"],"title_canon_sha256":"ff09efd23e2ff2c1ace1006222ebaf300004c70d8ad97564cc9124bb824bee6d","abstract_canon_sha256":"6548893988195319a6f905a0290d6797b2c26f2c5a9dec51974ae8d16a0b0ec9"},"schema_version":"1.0"},"canonical_sha256":"ac2739b479dcac2dc4d0e06ad926c9de8bff58175b13bc0d640ac06f1c3b0ca7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:24.897476Z","signature_b64":"JQsWsTMe2iJ1QNU1N3yI+PIxc3qXAP1lVWulk/o6x7hz0X6edE59ZvXwPFdSRjg0JQ0UAZrEF9ts8++T/184AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2739b479dcac2dc4d0e06ad926c9de8bff58175b13bc0d640ac06f1c3b0ca7","last_reissued_at":"2026-07-05T05:25:24.896961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:24.896961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.07414","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":"2026-07-05T05:25:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F4fCpuraVRtuLd9e8jM+Pxl4vZo6eGJAOD+S4Doqvcgyi5e/KXowJwT1TTJRqmZyXs9fwQKknpJOarojvp7WBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:58:55.099240Z"},"content_sha256":"39d68420fd39c919087decf4a63b1280d534ed36a4eb4321abdeb2dd52f1c677","schema_version":"1.0","event_id":"sha256:39d68420fd39c919087decf4a63b1280d534ed36a4eb4321abdeb2dd52f1c677"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VQTTTNDZ3SWC3RGQ4BVNSJWJ32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Over-the-Air FedGradNorm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","eess.SP","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cemil Vahapoglu, Matin Mortaheb, Sennur Ulukus","submitted_at":"2022-12-14T18:54:46Z","abstract_excerpt":"Multi-task learning (MTL) is a learning paradigm to learn multiple related tasks simultaneously with a single shared network where each task has a distinct personalized header network for fine-tuning. MTL can be integrated into a federated learning (FL) setting if tasks are distributed across clients and clients have a single shared network, leading to personalized federated learning (PFL). To cope with statistical heterogeneity in the federated setting across clients which can significantly degrade the learning performance, we use a distributed dynamic weighting approach. To perform the commu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07414","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/2212.07414/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":"2026-07-05T05:25:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gj8nHCP5Zpg/hZN4aDWZssGy7nFhccTvq1DU/A7/kF5Xrkt71w+bgN/ChvCK6et3kgz5HmU8p5v5yczcSDUYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:58:55.100475Z"},"content_sha256":"3bcd37772d09d13dfdb4aec7009a61240ab651d684daedea735480864e5a0fda","schema_version":"1.0","event_id":"sha256:3bcd37772d09d13dfdb4aec7009a61240ab651d684daedea735480864e5a0fda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32/bundle.json","state_url":"https://pith.science/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32/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":"2026-08-10T21:58:55Z","links":{"resolver":"https://pith.science/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32","bundle":"https://pith.science/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32/bundle.json","state":"https://pith.science/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQTTTNDZ3SWC3RGQ4BVNSJWJ32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VQTTTNDZ3SWC3RGQ4BVNSJWJ32","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":"6548893988195319a6f905a0290d6797b2c26f2c5a9dec51974ae8d16a0b0ec9","cross_cats_sorted":["cs.IT","eess.SP","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T18:54:46Z","title_canon_sha256":"ff09efd23e2ff2c1ace1006222ebaf300004c70d8ad97564cc9124bb824bee6d"},"schema_version":"1.0","source":{"id":"2212.07414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.07414","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"arxiv_version","alias_value":"2212.07414v1","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07414","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"pith_short_12","alias_value":"VQTTTNDZ3SWC","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"pith_short_16","alias_value":"VQTTTNDZ3SWC3RGQ","created_at":"2026-07-05T05:25:24Z"},{"alias_kind":"pith_short_8","alias_value":"VQTTTNDZ","created_at":"2026-07-05T05:25:24Z"}],"graph_snapshots":[{"event_id":"sha256:3bcd37772d09d13dfdb4aec7009a61240ab651d684daedea735480864e5a0fda","target":"graph","created_at":"2026-07-05T05:25:24Z","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/2212.07414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning (MTL) is a learning paradigm to learn multiple related tasks simultaneously with a single shared network where each task has a distinct personalized header network for fine-tuning. MTL can be integrated into a federated learning (FL) setting if tasks are distributed across clients and clients have a single shared network, leading to personalized federated learning (PFL). To cope with statistical heterogeneity in the federated setting across clients which can significantly degrade the learning performance, we use a distributed dynamic weighting approach. To perform the commu","authors_text":"Cemil Vahapoglu, Matin Mortaheb, Sennur Ulukus","cross_cats":["cs.IT","eess.SP","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T18:54:46Z","title":"Hierarchical Over-the-Air FedGradNorm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07414","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":"sha256:39d68420fd39c919087decf4a63b1280d534ed36a4eb4321abdeb2dd52f1c677","target":"record","created_at":"2026-07-05T05:25:24Z","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":"6548893988195319a6f905a0290d6797b2c26f2c5a9dec51974ae8d16a0b0ec9","cross_cats_sorted":["cs.IT","eess.SP","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T18:54:46Z","title_canon_sha256":"ff09efd23e2ff2c1ace1006222ebaf300004c70d8ad97564cc9124bb824bee6d"},"schema_version":"1.0","source":{"id":"2212.07414","kind":"arxiv","version":1}},"canonical_sha256":"ac2739b479dcac2dc4d0e06ad926c9de8bff58175b13bc0d640ac06f1c3b0ca7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac2739b479dcac2dc4d0e06ad926c9de8bff58175b13bc0d640ac06f1c3b0ca7","first_computed_at":"2026-07-05T05:25:24.896961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:24.896961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JQsWsTMe2iJ1QNU1N3yI+PIxc3qXAP1lVWulk/o6x7hz0X6edE59ZvXwPFdSRjg0JQ0UAZrEF9ts8++T/184AA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:24.897476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.07414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39d68420fd39c919087decf4a63b1280d534ed36a4eb4321abdeb2dd52f1c677","sha256:3bcd37772d09d13dfdb4aec7009a61240ab651d684daedea735480864e5a0fda"],"state_sha256":"105262dd332d4c27c05d0daf7c195338a77257a56574fb73d318d20639182ac5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TpSvM8D2TGBMr8zu3VcQbjML/cFrH8KRLwFlYZ5lZx+kOUoCWOxGo9xyA7UZodRIYNlj+uDIDVwipP9sBO1cBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:58:55.106708Z","bundle_sha256":"5c7ed55dc3a496b2862c7ef53c9cdaafd6c6ca571b5db7eece063cf9fda07ac0"}}