{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YLZUOJCD4GNT64NRJWMK2WUK4L","short_pith_number":"pith:YLZUOJCD","schema_version":"1.0","canonical_sha256":"c2f3472443e19b3f71b14d98ad5a8ae2f08d8357f0374b69ff031e68a81eb0f4","source":{"kind":"arxiv","id":"2405.09771","version":2},"attestation_state":"computed","paper":{"title":"Harmonizing Generalization and Personalization in Federated Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongxia Li, Jingya Wang, Tianyu Cui, Ye Shi","submitted_at":"2024-05-16T02:22:09Z","abstract_excerpt":"Federated Prompt Learning (FPL) incorporates large pre-trained Vision-Language models (VLM) into federated learning through prompt tuning. The transferable representations and remarkable generalization capacity of VLM make them highly compatible with the integration of federated learning. Addressing data heterogeneity in federated learning requires personalization, but excessive focus on it across clients could compromise the model's ability to generalize effectively. To preserve the impressive generalization capability of VLM, it is crucial to strike a balance between personalization and gene"},"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":"2405.09771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T02:22:09Z","cross_cats_sorted":[],"title_canon_sha256":"ab5851c6e75656092ad35deb298b067b14d2f2a254928c5ed43d92338c2e8ec2","abstract_canon_sha256":"680db13f1c69fa099c08a308580bda1167e238b5296e11bd85958e67689b05b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:34.345306Z","signature_b64":"3UBWxbrKg87W/trLYsrJhctrvDiYOU43rQdyBx96tZfuEdM92rmL8+kGHqKQwkQZGD5o+ODM3Z66uvXVJFEmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f3472443e19b3f71b14d98ad5a8ae2f08d8357f0374b69ff031e68a81eb0f4","last_reissued_at":"2026-07-05T09:01:34.344857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:34.344857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harmonizing Generalization and Personalization in Federated Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongxia Li, Jingya Wang, Tianyu Cui, Ye Shi","submitted_at":"2024-05-16T02:22:09Z","abstract_excerpt":"Federated Prompt Learning (FPL) incorporates large pre-trained Vision-Language models (VLM) into federated learning through prompt tuning. The transferable representations and remarkable generalization capacity of VLM make them highly compatible with the integration of federated learning. Addressing data heterogeneity in federated learning requires personalization, but excessive focus on it across clients could compromise the model's ability to generalize effectively. To preserve the impressive generalization capability of VLM, it is crucial to strike a balance between personalization and gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09771","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/2405.09771/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":"2405.09771","created_at":"2026-07-05T09:01:34.344911+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09771v2","created_at":"2026-07-05T09:01:34.344911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09771","created_at":"2026-07-05T09:01:34.344911+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLZUOJCD4GNT","created_at":"2026-07-05T09:01:34.344911+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLZUOJCD4GNT64NR","created_at":"2026-07-05T09:01:34.344911+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLZUOJCD","created_at":"2026-07-05T09:01:34.344911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28347","citing_title":"FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L","json":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L.json","graph_json":"https://pith.science/api/pith-number/YLZUOJCD4GNT64NRJWMK2WUK4L/graph.json","events_json":"https://pith.science/api/pith-number/YLZUOJCD4GNT64NRJWMK2WUK4L/events.json","paper":"https://pith.science/paper/YLZUOJCD"},"agent_actions":{"view_html":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L","download_json":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L.json","view_paper":"https://pith.science/paper/YLZUOJCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09771&json=true","fetch_graph":"https://pith.science/api/pith-number/YLZUOJCD4GNT64NRJWMK2WUK4L/graph.json","fetch_events":"https://pith.science/api/pith-number/YLZUOJCD4GNT64NRJWMK2WUK4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L/action/storage_attestation","attest_author":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L/action/author_attestation","sign_citation":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L/action/citation_signature","submit_replication":"https://pith.science/pith/YLZUOJCD4GNT64NRJWMK2WUK4L/action/replication_record"}},"created_at":"2026-07-05T09:01:34.344911+00:00","updated_at":"2026-07-05T09:01:34.344911+00:00"}