{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TPEWTCDETVEIJF2I3QXNACSA3","short_pith_number":"pith:3TPEWTCD","schema_version":"1.0","canonical_sha256":"dcde4b4c4324ea4424ba46e176805206d104f757480486692d74fd2bc4c6e73a","source":{"kind":"arxiv","id":"2403.00041","version":2},"attestation_state":"computed","paper":{"title":"Global and Local Prompts Cooperation via Optimal Transport for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hongxia Li, Jingya Wang, Wei Huang, Ye Shi","submitted_at":"2024-02-29T11:43:04Z","abstract_excerpt":"Prompt learning in pretrained visual-language models has shown remarkable flexibility across various downstream tasks. Leveraging its inherent lightweight nature, recent research attempted to integrate the powerful pretrained models into federated learning frameworks to simultaneously reduce communication costs and promote local training on insufficient data. Despite these efforts, current federated prompt learning methods lack specialized designs to systematically address severe data heterogeneities, e.g., data distribution with both label and feature shifts involved. To address this challeng"},"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":"2403.00041","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-29T11:43:04Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"43adf29e7337e350c0a6d7b3d4d31c3cb912f112da7748d2061ba69d47bf6764","abstract_canon_sha256":"4337163e1c90eb482a6144bbc8521aae3370e01aa4070c4377c950c10d89f597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:49.356726Z","signature_b64":"EVFo0G1FJgVcphBTf0Wf9FfKU7volWq4KIDMvklyIZlU/x6RJgKCT4syLqth9L3dBwUWCu6LhdS3t4xD8FdSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcde4b4c4324ea4424ba46e176805206d104f757480486692d74fd2bc4c6e73a","last_reissued_at":"2026-07-05T08:03:49.356244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:49.356244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global and Local Prompts Cooperation via Optimal Transport for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hongxia Li, Jingya Wang, Wei Huang, Ye Shi","submitted_at":"2024-02-29T11:43:04Z","abstract_excerpt":"Prompt learning in pretrained visual-language models has shown remarkable flexibility across various downstream tasks. Leveraging its inherent lightweight nature, recent research attempted to integrate the powerful pretrained models into federated learning frameworks to simultaneously reduce communication costs and promote local training on insufficient data. Despite these efforts, current federated prompt learning methods lack specialized designs to systematically address severe data heterogeneities, e.g., data distribution with both label and feature shifts involved. To address this challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00041","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/2403.00041/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":"2403.00041","created_at":"2026-07-05T08:03:49.356305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00041v2","created_at":"2026-07-05T08:03:49.356305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00041","created_at":"2026-07-05T08:03:49.356305+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TPEWTCDETVE","created_at":"2026-07-05T08:03:49.356305+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TPEWTCDETVEIJF2","created_at":"2026-07-05T08:03:49.356305+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TPEWTCD","created_at":"2026-07-05T08:03:49.356305+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/3TPEWTCDETVEIJF2I3QXNACSA3","json":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3.json","graph_json":"https://pith.science/api/pith-number/3TPEWTCDETVEIJF2I3QXNACSA3/graph.json","events_json":"https://pith.science/api/pith-number/3TPEWTCDETVEIJF2I3QXNACSA3/events.json","paper":"https://pith.science/paper/3TPEWTCD"},"agent_actions":{"view_html":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3","download_json":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3.json","view_paper":"https://pith.science/paper/3TPEWTCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00041&json=true","fetch_graph":"https://pith.science/api/pith-number/3TPEWTCDETVEIJF2I3QXNACSA3/graph.json","fetch_events":"https://pith.science/api/pith-number/3TPEWTCDETVEIJF2I3QXNACSA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3/action/storage_attestation","attest_author":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3/action/author_attestation","sign_citation":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3/action/citation_signature","submit_replication":"https://pith.science/pith/3TPEWTCDETVEIJF2I3QXNACSA3/action/replication_record"}},"created_at":"2026-07-05T08:03:49.356305+00:00","updated_at":"2026-07-05T08:03:49.356305+00:00"}