{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:72TFOUH4OEMCVPWDKFIDUV5NOR","short_pith_number":"pith:72TFOUH4","schema_version":"1.0","canonical_sha256":"fea65750fc71182abec351503a57ad746cd1990dd4f1e362252538adc9e2031f","source":{"kind":"arxiv","id":"2608.00623","version":1},"attestation_state":"computed","paper":{"title":"Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Di Wu, Guocong Quan, Miao Hu, Wang Luo, Wei-Jin Huang, Xunkai Li, Yinlin Zhu, Yi Zhang","submitted_at":"2026-08-01T12:29:38Z","abstract_excerpt":"Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains. Federated multimodal graph learning (FMGL) extends federated graph learning (FGL) to MAGs, enabling collaborative optimization across decentralized MAGs without exposing raw data. However, naively applying existing FGL methods to FMGL is insufficient, as they fail to navigate the multifaceted heterogeneity inherent in decentralized MAGs, including task heterogeneity across diverse client obj"},"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":"2608.00623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-01T12:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"cf98f05b127ca54cda4b9f40fa75e18bd7fd21e359e787795c4541a568a4ac79","abstract_canon_sha256":"fccfe7b4bc87aea2eaf17ac1a5ffcc188600016d3a19e927b6d89322c147e939"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:38:07.075812Z","signature_b64":"EsuaQpDlTjklBpwxLeDkmEue+YgNrSBIInzW/JSlPnEgRi6ujxhjJHttvmu8lh0t6irGjvR0j4vvgWU7YpGwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fea65750fc71182abec351503a57ad746cd1990dd4f1e362252538adc9e2031f","last_reissued_at":"2026-08-04T00:38:07.074432Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:38:07.074432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Di Wu, Guocong Quan, Miao Hu, Wang Luo, Wei-Jin Huang, Xunkai Li, Yinlin Zhu, Yi Zhang","submitted_at":"2026-08-01T12:29:38Z","abstract_excerpt":"Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains. Federated multimodal graph learning (FMGL) extends federated graph learning (FGL) to MAGs, enabling collaborative optimization across decentralized MAGs without exposing raw data. However, naively applying existing FGL methods to FMGL is insufficient, as they fail to navigate the multifaceted heterogeneity inherent in decentralized MAGs, including task heterogeneity across diverse client obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00623","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/2608.00623/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":"2608.00623","created_at":"2026-08-04T00:38:07.075623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00623v1","created_at":"2026-08-04T00:38:07.075623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00623","created_at":"2026-08-04T00:38:07.075623+00:00"},{"alias_kind":"pith_short_12","alias_value":"72TFOUH4OEMC","created_at":"2026-08-04T00:38:07.075623+00:00"},{"alias_kind":"pith_short_16","alias_value":"72TFOUH4OEMCVPWD","created_at":"2026-08-04T00:38:07.075623+00:00"},{"alias_kind":"pith_short_8","alias_value":"72TFOUH4","created_at":"2026-08-04T00:38:07.075623+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/72TFOUH4OEMCVPWDKFIDUV5NOR","json":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR.json","graph_json":"https://pith.science/api/pith-number/72TFOUH4OEMCVPWDKFIDUV5NOR/graph.json","events_json":"https://pith.science/api/pith-number/72TFOUH4OEMCVPWDKFIDUV5NOR/events.json","paper":"https://pith.science/paper/72TFOUH4"},"agent_actions":{"view_html":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR","download_json":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR.json","view_paper":"https://pith.science/paper/72TFOUH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00623&json=true","fetch_graph":"https://pith.science/api/pith-number/72TFOUH4OEMCVPWDKFIDUV5NOR/graph.json","fetch_events":"https://pith.science/api/pith-number/72TFOUH4OEMCVPWDKFIDUV5NOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR/action/storage_attestation","attest_author":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR/action/author_attestation","sign_citation":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR/action/citation_signature","submit_replication":"https://pith.science/pith/72TFOUH4OEMCVPWDKFIDUV5NOR/action/replication_record"}},"created_at":"2026-08-04T00:38:07.075623+00:00","updated_at":"2026-08-04T00:38:07.075623+00:00"}