{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XYEOTESN5J7U7HMSGC777G3OLT","short_pith_number":"pith:XYEOTESN","schema_version":"1.0","canonical_sha256":"be08e9924dea7f4f9d9230bfff9b6e5cca4c85cdd10d3cc668261a9fcae4bd5b","source":{"kind":"arxiv","id":"2311.06805","version":1},"attestation_state":"computed","paper":{"title":"Tunable Soft Prompts are Messengers in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bolin Ding, Chenhe Dong, Yaliang Li, Ying Shen, Yuexiang Xie","submitted_at":"2023-11-12T11:01:10Z","abstract_excerpt":"Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources, alleviating privacy concerns that arise from directly sharing local data. However, the lack of model privacy protection in FL becomes an unneglectable challenge, especially when people want to federally finetune models based on a proprietary large language model. In this study, we propose a novel FL training approach that accomplishes information exchange among participants via tunable soft prompts. These soft prompts, updated and transmitted between the serv"},"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":"2311.06805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-12T11:01:10Z","cross_cats_sorted":[],"title_canon_sha256":"611851a18f485b6a2d16238d031cfd01ed2eebc19695e59f8146ce9972192ec2","abstract_canon_sha256":"716a30f5c2998b2de13e5d8a8f2df1e81a8ded994653f98c094effa9741fd985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:03.927262Z","signature_b64":"3hbiG52uY+BGFTz4e/FHWitXiUZE/c6fdSuJFTfANmUQhixSyjlf5Y1s/hmfhVF7J35GfHB1gkBDndHYZBlKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be08e9924dea7f4f9d9230bfff9b6e5cca4c85cdd10d3cc668261a9fcae4bd5b","last_reissued_at":"2026-07-05T07:12:03.926789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:03.926789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tunable Soft Prompts are Messengers in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bolin Ding, Chenhe Dong, Yaliang Li, Ying Shen, Yuexiang Xie","submitted_at":"2023-11-12T11:01:10Z","abstract_excerpt":"Federated learning (FL) enables multiple participants to collaboratively train machine learning models using decentralized data sources, alleviating privacy concerns that arise from directly sharing local data. However, the lack of model privacy protection in FL becomes an unneglectable challenge, especially when people want to federally finetune models based on a proprietary large language model. In this study, we propose a novel FL training approach that accomplishes information exchange among participants via tunable soft prompts. These soft prompts, updated and transmitted between the serv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06805","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/2311.06805/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":"2311.06805","created_at":"2026-07-05T07:12:03.926852+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06805v1","created_at":"2026-07-05T07:12:03.926852+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06805","created_at":"2026-07-05T07:12:03.926852+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYEOTESN5J7U","created_at":"2026-07-05T07:12:03.926852+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYEOTESN5J7U7HMS","created_at":"2026-07-05T07:12:03.926852+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYEOTESN","created_at":"2026-07-05T07:12:03.926852+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18911","citing_title":"Enhancing Model Privacy in Federated Learning with Random Masking and Quantization","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT","json":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT.json","graph_json":"https://pith.science/api/pith-number/XYEOTESN5J7U7HMSGC777G3OLT/graph.json","events_json":"https://pith.science/api/pith-number/XYEOTESN5J7U7HMSGC777G3OLT/events.json","paper":"https://pith.science/paper/XYEOTESN"},"agent_actions":{"view_html":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT","download_json":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT.json","view_paper":"https://pith.science/paper/XYEOTESN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06805&json=true","fetch_graph":"https://pith.science/api/pith-number/XYEOTESN5J7U7HMSGC777G3OLT/graph.json","fetch_events":"https://pith.science/api/pith-number/XYEOTESN5J7U7HMSGC777G3OLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT/action/storage_attestation","attest_author":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT/action/author_attestation","sign_citation":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT/action/citation_signature","submit_replication":"https://pith.science/pith/XYEOTESN5J7U7HMSGC777G3OLT/action/replication_record"}},"created_at":"2026-07-05T07:12:03.926852+00:00","updated_at":"2026-07-05T07:12:03.926852+00:00"}