{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RKXIGNZKB3G4IQWMNX3HEYN3R4","short_pith_number":"pith:RKXIGNZK","schema_version":"1.0","canonical_sha256":"8aae83372a0ecdc442cc6df67261bb8f0214ec88ad70b602e3cb050700833dff","source":{"kind":"arxiv","id":"2306.08223","version":1},"attestation_state":"computed","paper":{"title":"Protecting User Privacy in Remote Conversational Systems: A Privacy-Preserving framework based on text sanitization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CR","authors_text":"Dongsheng Li, Hao Yu, Linbo Qiao, Liwen Peng, Yifu Gao, Zhigang Kan","submitted_at":"2023-06-14T03:28:51Z","abstract_excerpt":"Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural language processing researchers endeavor to employ them in solving existing or new research problems. Unfortunately, individuals can only access such powerful AIs through APIs, which ultimately leads to the transmission of raw data to the models' providers and increases the possibility of privacy data leakage. Current privacy-preserving methods for cloud-deploye"},"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":"2306.08223","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-06-14T03:28:51Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1875e8a99317b463682e3302825ab410f4eca6e1773a9fb488a71dc424704e19","abstract_canon_sha256":"c20e21420c387707bb7003a8b10882d211e3d4912e2728978e089df0d3a3deda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:49.567176Z","signature_b64":"eKsuFZ5IfYsDliBnfKvxdkzmhwumYunVkmY70C9bYgJG7gp2mGjj7+/TsP2Dd6zNEyj1a4Co0FqIFR6CtUnwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aae83372a0ecdc442cc6df67261bb8f0214ec88ad70b602e3cb050700833dff","last_reissued_at":"2026-07-05T06:20:49.566683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:49.566683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protecting User Privacy in Remote Conversational Systems: A Privacy-Preserving framework based on text sanitization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CR","authors_text":"Dongsheng Li, Hao Yu, Linbo Qiao, Liwen Peng, Yifu Gao, Zhigang Kan","submitted_at":"2023-06-14T03:28:51Z","abstract_excerpt":"Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural language processing researchers endeavor to employ them in solving existing or new research problems. Unfortunately, individuals can only access such powerful AIs through APIs, which ultimately leads to the transmission of raw data to the models' providers and increases the possibility of privacy data leakage. Current privacy-preserving methods for cloud-deploye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08223","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/2306.08223/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":"2306.08223","created_at":"2026-07-05T06:20:49.566743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08223v1","created_at":"2026-07-05T06:20:49.566743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08223","created_at":"2026-07-05T06:20:49.566743+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKXIGNZKB3G4","created_at":"2026-07-05T06:20:49.566743+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKXIGNZKB3G4IQWM","created_at":"2026-07-05T06:20:49.566743+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKXIGNZK","created_at":"2026-07-05T06:20:49.566743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05004","citing_title":"SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04067","citing_title":"Need to Know: Contextual-Integrity-Grounded Query Rewriting for Privacy-Conscious LLM Delegation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03399","citing_title":"Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2401.00870","citing_title":"ConfusionPrompt: Practical Private Inference for Online Large Language Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4","json":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4.json","graph_json":"https://pith.science/api/pith-number/RKXIGNZKB3G4IQWMNX3HEYN3R4/graph.json","events_json":"https://pith.science/api/pith-number/RKXIGNZKB3G4IQWMNX3HEYN3R4/events.json","paper":"https://pith.science/paper/RKXIGNZK"},"agent_actions":{"view_html":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4","download_json":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4.json","view_paper":"https://pith.science/paper/RKXIGNZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08223&json=true","fetch_graph":"https://pith.science/api/pith-number/RKXIGNZKB3G4IQWMNX3HEYN3R4/graph.json","fetch_events":"https://pith.science/api/pith-number/RKXIGNZKB3G4IQWMNX3HEYN3R4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4/action/storage_attestation","attest_author":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4/action/author_attestation","sign_citation":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4/action/citation_signature","submit_replication":"https://pith.science/pith/RKXIGNZKB3G4IQWMNX3HEYN3R4/action/replication_record"}},"created_at":"2026-07-05T06:20:49.566743+00:00","updated_at":"2026-07-05T06:20:49.566743+00:00"}