{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OJRVELQIHKH4YVKNASI6EBL3VD","short_pith_number":"pith:OJRVELQI","schema_version":"1.0","canonical_sha256":"7263522e083a8fcc554d0491e2057ba8d6f0e15030b49f53d96c8c00ed642fd2","source":{"kind":"arxiv","id":"2307.04942","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Algorithms for Federated Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David I. Inouye, Ruqi Bai, Saurabh Bagchi","submitted_at":"2023-07-11T00:14:45Z","abstract_excerpt":"While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges. Additionally, we explore domain-based heterogeneity in clients' local datasets - a realistic Federated DG scenario. Prior Federated DG evaluations are limited in terms of the number or heterogeneity of clients and dataset diversity. To address this gap, we propose an Federated DG benchmark methodology that enables control of the number and heterogeneity of clients and provides metrics for dataset difficulty. We then "},"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":"2307.04942","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-11T00:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"1a9687b9c6bb23805c08802a258acfeb1f0fb9a7c8032d528cfb5b47fa8eb05a","abstract_canon_sha256":"c73c470956965b82073e6d9fd3df3d3dfb27f5d9786201affc13d09c5a1b13fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:41.532549Z","signature_b64":"nAR2T3Cpmp3VdOKr2kWzL5fbrNNY5GintWMjhcbh6IlJLEKDmw3yVBTKWcwLdgCK7UIVT6fJl90yPO1Swr1CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7263522e083a8fcc554d0491e2057ba8d6f0e15030b49f53d96c8c00ed642fd2","last_reissued_at":"2026-07-05T08:06:41.532036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:41.532036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Algorithms for Federated Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David I. Inouye, Ruqi Bai, Saurabh Bagchi","submitted_at":"2023-07-11T00:14:45Z","abstract_excerpt":"While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges. Additionally, we explore domain-based heterogeneity in clients' local datasets - a realistic Federated DG scenario. Prior Federated DG evaluations are limited in terms of the number or heterogeneity of clients and dataset diversity. To address this gap, we propose an Federated DG benchmark methodology that enables control of the number and heterogeneity of clients and provides metrics for dataset difficulty. We then "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04942","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/2307.04942/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":"2307.04942","created_at":"2026-07-05T08:06:41.532088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04942v2","created_at":"2026-07-05T08:06:41.532088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04942","created_at":"2026-07-05T08:06:41.532088+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJRVELQIHKH4","created_at":"2026-07-05T08:06:41.532088+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJRVELQIHKH4YVKN","created_at":"2026-07-05T08:06:41.532088+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJRVELQI","created_at":"2026-07-05T08:06:41.532088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11408","citing_title":"Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD","json":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD.json","graph_json":"https://pith.science/api/pith-number/OJRVELQIHKH4YVKNASI6EBL3VD/graph.json","events_json":"https://pith.science/api/pith-number/OJRVELQIHKH4YVKNASI6EBL3VD/events.json","paper":"https://pith.science/paper/OJRVELQI"},"agent_actions":{"view_html":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD","download_json":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD.json","view_paper":"https://pith.science/paper/OJRVELQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04942&json=true","fetch_graph":"https://pith.science/api/pith-number/OJRVELQIHKH4YVKNASI6EBL3VD/graph.json","fetch_events":"https://pith.science/api/pith-number/OJRVELQIHKH4YVKNASI6EBL3VD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD/action/storage_attestation","attest_author":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD/action/author_attestation","sign_citation":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD/action/citation_signature","submit_replication":"https://pith.science/pith/OJRVELQIHKH4YVKNASI6EBL3VD/action/replication_record"}},"created_at":"2026-07-05T08:06:41.532088+00:00","updated_at":"2026-07-05T08:06:41.532088+00:00"}