{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PVEQZLEAD7EHAXNTPJZZQW56TD","short_pith_number":"pith:PVEQZLEA","canonical_record":{"source":{"id":"2506.21144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T10:59:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2f2126719b7d59406d991f406d62af511c2ee2c704d3611e4bd9a97b3382b66f","abstract_canon_sha256":"6420577c963cc187605dc1da2f2b2070849bf78073cd5d1c42e3347b482c722b"},"schema_version":"1.0"},"canonical_sha256":"7d490cac801fc8705db37a73985bbe98cfb546f7d8e654c5532a74e0e60764d0","source":{"kind":"arxiv","id":"2506.21144","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21144","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21144v1","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21144","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"pith_short_12","alias_value":"PVEQZLEAD7EH","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"PVEQZLEAD7EHAXNT","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"PVEQZLEA","created_at":"2026-07-05T11:27:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PVEQZLEAD7EHAXNTPJZZQW56TD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21144","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T10:59:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2f2126719b7d59406d991f406d62af511c2ee2c704d3611e4bd9a97b3382b66f","abstract_canon_sha256":"6420577c963cc187605dc1da2f2b2070849bf78073cd5d1c42e3347b482c722b"},"schema_version":"1.0"},"canonical_sha256":"7d490cac801fc8705db37a73985bbe98cfb546f7d8e654c5532a74e0e60764d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:40.483679Z","signature_b64":"wcRb9DEx9LDJiqV3vrO9E0EjJWhxNeHJgw7wroe4c5jdnDyVogj/lxUu19nYL9ni2NhHfC7NB0AlP+WUKszeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d490cac801fc8705db37a73985bbe98cfb546f7d8e654c5532a74e0e60764d0","last_reissued_at":"2026-07-05T11:27:40.483214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:40.483214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21144","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3O4W+/LqEyBQ4OSui/24wIX1Wv3ybCkhjjTVWq8YWL8NUPh1LJH6y+2no6F3ZHHi0mEGbDhJ+QdWU8F1QCSCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:34:38.343135Z"},"content_sha256":"c952901f6bd8136869f407a19fc4a2e4a3b9f84c275a048eee222003b102944e","schema_version":"1.0","event_id":"sha256:c952901f6bd8136869f407a19fc4a2e4a3b9f84c275a048eee222003b102944e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PVEQZLEAD7EHAXNTPJZZQW56TD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jian Liang, Kuangpu Guo, Yuguang Zhang, Yunbo Wang, Zhihe Lu","submitted_at":"2025-06-26T10:59:14Z","abstract_excerpt":"Federated learning (FL) enables collaborative model training across decentralized clients without sharing local data, but is challenged by heterogeneity in data, computation, and communication. Pretrained vision-language models (VLMs), with their strong generalization and lightweight tuning via prompts, offer a promising solution. However, existing federated prompt-learning methods rely only on text prompts and overlook joint label-domain distribution shifts. In this paper, we propose a personalized FL framework based on dual-prompt learning and cross fusion, termed pFedDC. Specifically, each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21144","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/2506.21144/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNtdzGUuGK4E0/qh8T39V8rFt2Jx7pzcunUZjaiOj/c5sf7M8cQ4NavlE5STj6SeoJiiOeOOuJ73S3xUtFiPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:34:38.343720Z"},"content_sha256":"8f7acc6e47b6e82c405ae823fb709066554c99b3d1721e7801b0f7f3906bcf6a","schema_version":"1.0","event_id":"sha256:8f7acc6e47b6e82c405ae823fb709066554c99b3d1721e7801b0f7f3906bcf6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PVEQZLEAD7EHAXNTPJZZQW56TD/bundle.json","state_url":"https://pith.science/pith/PVEQZLEAD7EHAXNTPJZZQW56TD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PVEQZLEAD7EHAXNTPJZZQW56TD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T23:34:38Z","links":{"resolver":"https://pith.science/pith/PVEQZLEAD7EHAXNTPJZZQW56TD","bundle":"https://pith.science/pith/PVEQZLEAD7EHAXNTPJZZQW56TD/bundle.json","state":"https://pith.science/pith/PVEQZLEAD7EHAXNTPJZZQW56TD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PVEQZLEAD7EHAXNTPJZZQW56TD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PVEQZLEAD7EHAXNTPJZZQW56TD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6420577c963cc187605dc1da2f2b2070849bf78073cd5d1c42e3347b482c722b","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T10:59:14Z","title_canon_sha256":"2f2126719b7d59406d991f406d62af511c2ee2c704d3611e4bd9a97b3382b66f"},"schema_version":"1.0","source":{"id":"2506.21144","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21144","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21144v1","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21144","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"pith_short_12","alias_value":"PVEQZLEAD7EH","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"pith_short_16","alias_value":"PVEQZLEAD7EHAXNT","created_at":"2026-07-05T11:27:40Z"},{"alias_kind":"pith_short_8","alias_value":"PVEQZLEA","created_at":"2026-07-05T11:27:40Z"}],"graph_snapshots":[{"event_id":"sha256:8f7acc6e47b6e82c405ae823fb709066554c99b3d1721e7801b0f7f3906bcf6a","target":"graph","created_at":"2026-07-05T11:27:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.21144/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) enables collaborative model training across decentralized clients without sharing local data, but is challenged by heterogeneity in data, computation, and communication. Pretrained vision-language models (VLMs), with their strong generalization and lightweight tuning via prompts, offer a promising solution. However, existing federated prompt-learning methods rely only on text prompts and overlook joint label-domain distribution shifts. In this paper, we propose a personalized FL framework based on dual-prompt learning and cross fusion, termed pFedDC. Specifically, each ","authors_text":"Jian Liang, Kuangpu Guo, Yuguang Zhang, Yunbo Wang, Zhihe Lu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T10:59:14Z","title":"Personalized Federated Learning via Dual-Prompt Optimization and Cross Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21144","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c952901f6bd8136869f407a19fc4a2e4a3b9f84c275a048eee222003b102944e","target":"record","created_at":"2026-07-05T11:27:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6420577c963cc187605dc1da2f2b2070849bf78073cd5d1c42e3347b482c722b","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T10:59:14Z","title_canon_sha256":"2f2126719b7d59406d991f406d62af511c2ee2c704d3611e4bd9a97b3382b66f"},"schema_version":"1.0","source":{"id":"2506.21144","kind":"arxiv","version":1}},"canonical_sha256":"7d490cac801fc8705db37a73985bbe98cfb546f7d8e654c5532a74e0e60764d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d490cac801fc8705db37a73985bbe98cfb546f7d8e654c5532a74e0e60764d0","first_computed_at":"2026-07-05T11:27:40.483214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:40.483214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wcRb9DEx9LDJiqV3vrO9E0EjJWhxNeHJgw7wroe4c5jdnDyVogj/lxUu19nYL9ni2NhHfC7NB0AlP+WUKszeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:40.483679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21144","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c952901f6bd8136869f407a19fc4a2e4a3b9f84c275a048eee222003b102944e","sha256:8f7acc6e47b6e82c405ae823fb709066554c99b3d1721e7801b0f7f3906bcf6a"],"state_sha256":"76b25678584dd9b34f8e3ae08ab00a5f2e43225cc487c4fd28b61d3e7f9706ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XQIlL2eDnjwaR1WsAcLWK0SI0gBiGOI5MGDP+Gtkivn6pUMQroz2OgQX/lWvUy5xI8wr9ioaD/lfFRB4fk2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:34:38.347492Z","bundle_sha256":"a965943a3aa8e843987b986b4856c461e3f5f2b7d8fae24914e9828fb08d6cc2"}}