{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IJSMFV4PZ5B4AMIP4ADTYAEMPK","short_pith_number":"pith:IJSMFV4P","schema_version":"1.0","canonical_sha256":"4264c2d78fcf43c0310fe0073c008c7a97b336fdda83e5874f8c2a7fb301b203","source":{"kind":"arxiv","id":"2412.18460","version":2},"attestation_state":"computed","paper":{"title":"GeFL: Model-Agnostic Federated Learning with Generative Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Honggu Kang, Joonhyuk Kang, Seohyeon Cha","submitted_at":"2024-12-24T14:39:47Z","abstract_excerpt":"Federated learning (FL) is a distributed training paradigm that enables collaborative learning across clients without sharing local data, thereby preserving privacy. However, the increasing scale and complexity of modern deep models often exceed the computational or memory capabilities of edge devices. Furthermore, clients may be constrained to use heterogeneous model architectures due to hardware variability (e.g., ASICs, FPGAs) or proprietary requirements that prevent the disclosure or modification of local model structures. These practical considerations motivate the need for model-heteroge"},"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":"2412.18460","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-24T14:39:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca87d5aae4f905ff29aee8784162a8890c26f2c1080f57faabaa6deba4aa4627","abstract_canon_sha256":"7ea95246e3daf8b110d8555f56772b0fd29ac862a016f4c05b7c391a58d274d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:20.325180Z","signature_b64":"Ostg2UBAl8rt8guUMwV1/6tauqZolk7B7IdZ+6iBJKNnjcL32uob61uiOkaBnLnTX8Vtbw93SXoLHCi7YzS/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4264c2d78fcf43c0310fe0073c008c7a97b336fdda83e5874f8c2a7fb301b203","last_reissued_at":"2026-07-05T11:04:20.324666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:20.324666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeFL: Model-Agnostic Federated Learning with Generative Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Honggu Kang, Joonhyuk Kang, Seohyeon Cha","submitted_at":"2024-12-24T14:39:47Z","abstract_excerpt":"Federated learning (FL) is a distributed training paradigm that enables collaborative learning across clients without sharing local data, thereby preserving privacy. However, the increasing scale and complexity of modern deep models often exceed the computational or memory capabilities of edge devices. Furthermore, clients may be constrained to use heterogeneous model architectures due to hardware variability (e.g., ASICs, FPGAs) or proprietary requirements that prevent the disclosure or modification of local model structures. These practical considerations motivate the need for model-heteroge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18460","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/2412.18460/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":"2412.18460","created_at":"2026-07-05T11:04:20.324733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18460v2","created_at":"2026-07-05T11:04:20.324733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18460","created_at":"2026-07-05T11:04:20.324733+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJSMFV4PZ5B4","created_at":"2026-07-05T11:04:20.324733+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJSMFV4PZ5B4AMIP","created_at":"2026-07-05T11:04:20.324733+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJSMFV4P","created_at":"2026-07-05T11:04:20.324733+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/IJSMFV4PZ5B4AMIP4ADTYAEMPK","json":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK.json","graph_json":"https://pith.science/api/pith-number/IJSMFV4PZ5B4AMIP4ADTYAEMPK/graph.json","events_json":"https://pith.science/api/pith-number/IJSMFV4PZ5B4AMIP4ADTYAEMPK/events.json","paper":"https://pith.science/paper/IJSMFV4P"},"agent_actions":{"view_html":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK","download_json":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK.json","view_paper":"https://pith.science/paper/IJSMFV4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18460&json=true","fetch_graph":"https://pith.science/api/pith-number/IJSMFV4PZ5B4AMIP4ADTYAEMPK/graph.json","fetch_events":"https://pith.science/api/pith-number/IJSMFV4PZ5B4AMIP4ADTYAEMPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK/action/storage_attestation","attest_author":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK/action/author_attestation","sign_citation":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK/action/citation_signature","submit_replication":"https://pith.science/pith/IJSMFV4PZ5B4AMIP4ADTYAEMPK/action/replication_record"}},"created_at":"2026-07-05T11:04:20.324733+00:00","updated_at":"2026-07-05T11:04:20.324733+00:00"}