{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IOIGLYLZBUG5I44RZO5SMLE7W5","short_pith_number":"pith:IOIGLYLZ","schema_version":"1.0","canonical_sha256":"439065e1790d0dd47391cbbb262c9fb7689677159de6566cf6d0b81f02fcc280","source":{"kind":"arxiv","id":"2405.20681","version":3},"attestation_state":"computed","paper":{"title":"No Free Lunch Theorem for Privacy-Preserving LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Hai Jin, Lixin Fan, Qiang Yang, Wei Chen, Xiaojin Zhang, Yahao Pang, Yan Kang","submitted_at":"2024-05-31T08:22:53Z","abstract_excerpt":"Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productivity, reduce costs, and enable us to focus on more valuable tasks. Furthermore, LLMs possess the capacity to sift through extensive datasets, uncover underlying patterns, and furnish critical insights that propel the frontiers of technology and science. However, LLMs also pose privacy concerns. Users' interactions with LLMs may expose their sensitive personal or company information. A lack of robust privacy safeguards"},"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":"2405.20681","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-05-31T08:22:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"988158aff1b2f6276141e3bd9afc1f333f85e0269c2c505e2d48cb8babe64435","abstract_canon_sha256":"98cc2c24febff2509dcf291554f3c3393e261cc01e0162c7e4cfb6acb59d4856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:19.750613Z","signature_b64":"E57jo7+KDHtogFJVnOoZrlGTRx7jukRUIL7ZF47jTqEuukRVzO7FWMCVZOZ7aT98FjuGoE/WTa3dk5faCEFtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"439065e1790d0dd47391cbbb262c9fb7689677159de6566cf6d0b81f02fcc280","last_reissued_at":"2026-07-05T10:21:19.750061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:19.750061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Free Lunch Theorem for Privacy-Preserving LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Hai Jin, Lixin Fan, Qiang Yang, Wei Chen, Xiaojin Zhang, Yahao Pang, Yan Kang","submitted_at":"2024-05-31T08:22:53Z","abstract_excerpt":"Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productivity, reduce costs, and enable us to focus on more valuable tasks. Furthermore, LLMs possess the capacity to sift through extensive datasets, uncover underlying patterns, and furnish critical insights that propel the frontiers of technology and science. However, LLMs also pose privacy concerns. Users' interactions with LLMs may expose their sensitive personal or company information. A lack of robust privacy safeguards"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20681","kind":"arxiv","version":3},"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/2405.20681/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":"2405.20681","created_at":"2026-07-05T10:21:19.750129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20681v3","created_at":"2026-07-05T10:21:19.750129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20681","created_at":"2026-07-05T10:21:19.750129+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOIGLYLZBUG5","created_at":"2026-07-05T10:21:19.750129+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOIGLYLZBUG5I44R","created_at":"2026-07-05T10:21:19.750129+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOIGLYLZ","created_at":"2026-07-05T10:21:19.750129+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/IOIGLYLZBUG5I44RZO5SMLE7W5","json":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5.json","graph_json":"https://pith.science/api/pith-number/IOIGLYLZBUG5I44RZO5SMLE7W5/graph.json","events_json":"https://pith.science/api/pith-number/IOIGLYLZBUG5I44RZO5SMLE7W5/events.json","paper":"https://pith.science/paper/IOIGLYLZ"},"agent_actions":{"view_html":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5","download_json":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5.json","view_paper":"https://pith.science/paper/IOIGLYLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20681&json=true","fetch_graph":"https://pith.science/api/pith-number/IOIGLYLZBUG5I44RZO5SMLE7W5/graph.json","fetch_events":"https://pith.science/api/pith-number/IOIGLYLZBUG5I44RZO5SMLE7W5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5/action/storage_attestation","attest_author":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5/action/author_attestation","sign_citation":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5/action/citation_signature","submit_replication":"https://pith.science/pith/IOIGLYLZBUG5I44RZO5SMLE7W5/action/replication_record"}},"created_at":"2026-07-05T10:21:19.750129+00:00","updated_at":"2026-07-05T10:21:19.750129+00:00"}