{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CGXHKH2ONFMGHLT4OXCOWVEJRR","short_pith_number":"pith:CGXHKH2O","schema_version":"1.0","canonical_sha256":"11ae751f4e695863ae7c75c4eb54898c602947819486db31ca4d09caedb6662a","source":{"kind":"arxiv","id":"2608.07157","version":1},"attestation_state":"computed","paper":{"title":"Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Alicia Troncoso Lora, Alireza Moayedikia","submitted_at":"2026-08-07T12:26:03Z","abstract_excerpt":"Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone. A natural next step, allocating capacity by each client's data heterogeneity as estimated from the updates the server already observes, has been repeatedly suggested. We ask whether that step is possible, using HAS-FL, an adaptive capacity-allocation framework, as a test case. Our findings are threefold. First, validated against ground-truth label-distribution divergence on reproducible partitions, update-divergence est"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.07157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T12:26:03Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"e0da655c340399c03111d2c1b4d07ab729d881e3df01a7b41bc00bd22c057693","abstract_canon_sha256":"90c2d4c4f7a473917d08221c45399d318e738be4013a11968c35a7aa9c945497"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:14:28.681346Z","signature_b64":"P2O86l6R/xsha4gp1/MVSaC/3ODgcrwruZoIWXjr987cUGdK/ZjfdGOHfIt4qWdgC4KDy01FsFmi7b4/EjWTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11ae751f4e695863ae7c75c4eb54898c602947819486db31ca4d09caedb6662a","last_reissued_at":"2026-08-10T01:14:28.677871Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:14:28.677871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capacity Confounds and Coverage Guarantees in Adaptive Sub-model Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Alicia Troncoso Lora, Alireza Moayedikia","submitted_at":"2026-08-07T12:26:03Z","abstract_excerpt":"Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone. A natural next step, allocating capacity by each client's data heterogeneity as estimated from the updates the server already observes, has been repeatedly suggested. We ask whether that step is possible, using HAS-FL, an adaptive capacity-allocation framework, as a test case. Our findings are threefold. First, validated against ground-truth label-distribution divergence on reproducible partitions, update-divergence est"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07157","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/2608.07157/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.07157","created_at":"2026-08-10T01:14:28.679114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07157v1","created_at":"2026-08-10T01:14:28.679114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07157","created_at":"2026-08-10T01:14:28.679114+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGXHKH2ONFMG","created_at":"2026-08-10T01:14:28.679114+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGXHKH2ONFMGHLT4","created_at":"2026-08-10T01:14:28.679114+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGXHKH2O","created_at":"2026-08-10T01:14:28.679114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR","json":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR.json","graph_json":"https://pith.science/api/pith-number/CGXHKH2ONFMGHLT4OXCOWVEJRR/graph.json","events_json":"https://pith.science/api/pith-number/CGXHKH2ONFMGHLT4OXCOWVEJRR/events.json","paper":"https://pith.science/paper/CGXHKH2O"},"agent_actions":{"view_html":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR","download_json":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR.json","view_paper":"https://pith.science/paper/CGXHKH2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07157&json=true","fetch_graph":"https://pith.science/api/pith-number/CGXHKH2ONFMGHLT4OXCOWVEJRR/graph.json","fetch_events":"https://pith.science/api/pith-number/CGXHKH2ONFMGHLT4OXCOWVEJRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR/action/storage_attestation","attest_author":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR/action/author_attestation","sign_citation":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR/action/citation_signature","submit_replication":"https://pith.science/pith/CGXHKH2ONFMGHLT4OXCOWVEJRR/action/replication_record"}},"created_at":"2026-08-10T01:14:28.679114+00:00","updated_at":"2026-08-10T01:14:28.679114+00:00"}