{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7G73G3QC5E6L7GZIGRUDU4KM3J","short_pith_number":"pith:7G73G3QC","schema_version":"1.0","canonical_sha256":"f9bfb36e02e93cbf9b2834683a714cda6308a5b14e0233a738ace7a7e1148e0c","source":{"kind":"arxiv","id":"2312.08648","version":1},"attestation_state":"computed","paper":{"title":"CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangming Shi, Shanshan Zheng, Xiangbo Yin, Yang Lu, Yanyun Qu, Yuan Xie","submitted_at":"2023-12-14T04:07:49Z","abstract_excerpt":"Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CL"},"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":"2312.08648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-14T04:07:49Z","cross_cats_sorted":[],"title_canon_sha256":"6e1e42767d6b59cc976e2f911efe037afb190644ec14656e3fc870567630064d","abstract_canon_sha256":"0558f64b5cd3c8131ef5eeb9105b51c9a02a74a2000e0f88e32c8145f5eb0a54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:07.517420Z","signature_b64":"ZZW0C1W2JPauq27P+2ueD2DwXH/SXU6YNzWxYEl4UJ/vXgzjyAt6y9FQe5O/FH6MzR6kXOV/M2lpQGNRE2w6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9bfb36e02e93cbf9b2834683a714cda6308a5b14e0233a738ace7a7e1148e0c","last_reissued_at":"2026-07-05T07:24:07.517022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:07.517022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiangming Shi, Shanshan Zheng, Xiangbo Yin, Yang Lu, Yanyun Qu, Yuan Xie","submitted_at":"2023-12-14T04:07:49Z","abstract_excerpt":"Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08648","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/2312.08648/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":"2312.08648","created_at":"2026-07-05T07:24:07.517085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08648v1","created_at":"2026-07-05T07:24:07.517085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08648","created_at":"2026-07-05T07:24:07.517085+00:00"},{"alias_kind":"pith_short_12","alias_value":"7G73G3QC5E6L","created_at":"2026-07-05T07:24:07.517085+00:00"},{"alias_kind":"pith_short_16","alias_value":"7G73G3QC5E6L7GZI","created_at":"2026-07-05T07:24:07.517085+00:00"},{"alias_kind":"pith_short_8","alias_value":"7G73G3QC","created_at":"2026-07-05T07:24:07.517085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14980","citing_title":"FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J","json":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J.json","graph_json":"https://pith.science/api/pith-number/7G73G3QC5E6L7GZIGRUDU4KM3J/graph.json","events_json":"https://pith.science/api/pith-number/7G73G3QC5E6L7GZIGRUDU4KM3J/events.json","paper":"https://pith.science/paper/7G73G3QC"},"agent_actions":{"view_html":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J","download_json":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J.json","view_paper":"https://pith.science/paper/7G73G3QC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08648&json=true","fetch_graph":"https://pith.science/api/pith-number/7G73G3QC5E6L7GZIGRUDU4KM3J/graph.json","fetch_events":"https://pith.science/api/pith-number/7G73G3QC5E6L7GZIGRUDU4KM3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J/action/storage_attestation","attest_author":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J/action/author_attestation","sign_citation":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J/action/citation_signature","submit_replication":"https://pith.science/pith/7G73G3QC5E6L7GZIGRUDU4KM3J/action/replication_record"}},"created_at":"2026-07-05T07:24:07.517085+00:00","updated_at":"2026-07-05T07:24:07.517085+00:00"}