{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7JCCPH4SHI35FZUL7UVILT3KM","short_pith_number":"pith:O7JCCPH4","schema_version":"1.0","canonical_sha256":"77d2213cfc91d1be97345fe9542e7b533a62b4d944a1afe66d7fc23144883b34","source":{"kind":"arxiv","id":"2404.01232","version":2},"attestation_state":"computed","paper":{"title":"Open-Vocabulary Federated Learning with Multimodal Prototyping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dong Wang, Huimin Zeng, Zhenrui Yue","submitted_at":"2024-04-01T16:51:13Z","abstract_excerpt":"Existing federated learning (FL) studies usually assume the training label space and test label space are identical. However, in real-world applications, this assumption is too ideal to be true. A new user could come up with queries that involve data from unseen classes, and such open-vocabulary queries would directly defect such FL systems. Therefore, in this work, we explicitly focus on the under-explored open-vocabulary challenge in FL. That is, for a new user, the global server shall understand her/his query that involves arbitrary unknown classes. To address this problem, we leverage the "},"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":"2404.01232","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T16:51:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"70805af02d270fd2ef7ff8bc2e5e71c9b9c171473a4c26fb56a9f40625f27b05","abstract_canon_sha256":"e668780214881e43a707d51eb7e40495212d3222b02e2cb41c2bb905d49139fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:30.657719Z","signature_b64":"8uE5kUdzIGeYNPoOioZ/Wv5zEWchb1DC6TQQXvgWD7FpXiR+r37/ls7Z7lzmuPl1zu/Bc7O5t/9p7PTgv/ylDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77d2213cfc91d1be97345fe9542e7b533a62b4d944a1afe66d7fc23144883b34","last_reissued_at":"2026-07-05T08:03:30.657091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:30.657091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Vocabulary Federated Learning with Multimodal Prototyping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dong Wang, Huimin Zeng, Zhenrui Yue","submitted_at":"2024-04-01T16:51:13Z","abstract_excerpt":"Existing federated learning (FL) studies usually assume the training label space and test label space are identical. However, in real-world applications, this assumption is too ideal to be true. A new user could come up with queries that involve data from unseen classes, and such open-vocabulary queries would directly defect such FL systems. Therefore, in this work, we explicitly focus on the under-explored open-vocabulary challenge in FL. That is, for a new user, the global server shall understand her/his query that involves arbitrary unknown classes. To address this problem, we leverage the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01232","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/2404.01232/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":"2404.01232","created_at":"2026-07-05T08:03:30.657162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01232v2","created_at":"2026-07-05T08:03:30.657162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01232","created_at":"2026-07-05T08:03:30.657162+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7JCCPH4SHI3","created_at":"2026-07-05T08:03:30.657162+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7JCCPH4SHI35FZU","created_at":"2026-07-05T08:03:30.657162+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7JCCPH4","created_at":"2026-07-05T08:03:30.657162+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01856","citing_title":"Boosting Multimodal Federated Learning via Chained Modality Optimization","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM","json":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM.json","graph_json":"https://pith.science/api/pith-number/O7JCCPH4SHI35FZUL7UVILT3KM/graph.json","events_json":"https://pith.science/api/pith-number/O7JCCPH4SHI35FZUL7UVILT3KM/events.json","paper":"https://pith.science/paper/O7JCCPH4"},"agent_actions":{"view_html":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM","download_json":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM.json","view_paper":"https://pith.science/paper/O7JCCPH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01232&json=true","fetch_graph":"https://pith.science/api/pith-number/O7JCCPH4SHI35FZUL7UVILT3KM/graph.json","fetch_events":"https://pith.science/api/pith-number/O7JCCPH4SHI35FZUL7UVILT3KM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM/action/storage_attestation","attest_author":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM/action/author_attestation","sign_citation":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM/action/citation_signature","submit_replication":"https://pith.science/pith/O7JCCPH4SHI35FZUL7UVILT3KM/action/replication_record"}},"created_at":"2026-07-05T08:03:30.657162+00:00","updated_at":"2026-07-05T08:03:30.657162+00:00"}