{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LG2RT4RCXM5SVUE3236C3LQC5E","short_pith_number":"pith:LG2RT4RC","canonical_record":{"source":{"id":"2409.09510","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T19:18:26Z","cross_cats_sorted":[],"title_canon_sha256":"229a4489754f0e70db3e4ee46f64dde93b823662b8618dc5c4273aa97269aa55","abstract_canon_sha256":"7f6e999bb37bf199b0f6b73aaa1cb160dd2a6bec05a582d57d4ff5c368f7cd1a"},"schema_version":"1.0"},"canonical_sha256":"59b519f222bb3b2ad09bd6fc2dae02e92eb76833bc475b4efbbb06be16c29939","source":{"kind":"arxiv","id":"2409.09510","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09510","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09510v2","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09510","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"LG2RT4RCXM5S","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"LG2RT4RCXM5SVUE3","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"LG2RT4RC","created_at":"2026-07-05T11:27:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LG2RT4RCXM5SVUE3236C3LQC5E","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09510","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T19:18:26Z","cross_cats_sorted":[],"title_canon_sha256":"229a4489754f0e70db3e4ee46f64dde93b823662b8618dc5c4273aa97269aa55","abstract_canon_sha256":"7f6e999bb37bf199b0f6b73aaa1cb160dd2a6bec05a582d57d4ff5c368f7cd1a"},"schema_version":"1.0"},"canonical_sha256":"59b519f222bb3b2ad09bd6fc2dae02e92eb76833bc475b4efbbb06be16c29939","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:20.357969Z","signature_b64":"lyA03iqzBs6jHSveA+mjdE9xn9eh7IHhuIE/h+p9QzjZaDoNRWmoMl7BYL0W+cdRicEPIfBRb7GnIKIfdT0EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b519f222bb3b2ad09bd6fc2dae02e92eb76833bc475b4efbbb06be16c29939","last_reissued_at":"2026-07-05T11:27:20.357490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:20.357490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09510","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66Brae/RP6Bya9xDS4bdPsoaIM/E9nBArvWhs/hK2XaDf9BrjxxFeP2lJs+ZCTjWCVT4eDikfFkf9X3AOLADBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:45:30.303624Z"},"content_sha256":"085e8b376576d932666f77659daa570c8f520fe5c4629d572f20a55847743b42","schema_version":"1.0","event_id":"sha256:085e8b376576d932666f77659daa570c8f520fe5c4629d572f20a55847743b42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LG2RT4RCXM5SVUE3236C3LQC5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alireza Salemi, Hamed Zamani","submitted_at":"2024-09-14T19:18:26Z","abstract_excerpt":"Despite its substantial impact on various search, recommendation, and question answering tasks, privacy-preserving methods for personalizing large language models (LLMs) have received relatively limited exploration. There is one primary approach in this area through retrieval-augmented generation (RAG), which generates personalized outputs by enriching the input prompt with information retrieved from the user's personal data. This paper studies an orthogonal approach to RAG that involves learning user-dependent LLM parameters through parameter-efficient fine-tuning (PEFT). This paper presents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09510","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/2409.09510/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":"2026-07-05T11:27:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L3MqJt/2GUiq7FRiTo7XC6sycfMbFmysWkxZlUPZQRCitpNIOw3r6ZSPqwza9n51uMgVlA1Or0wab6bNWKdaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:45:30.304121Z"},"content_sha256":"f35b3483fd3582ea64afe4a7d08513484a01cf145843f5c19dea66af0f6476e0","schema_version":"1.0","event_id":"sha256:f35b3483fd3582ea64afe4a7d08513484a01cf145843f5c19dea66af0f6476e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LG2RT4RCXM5SVUE3236C3LQC5E/bundle.json","state_url":"https://pith.science/pith/LG2RT4RCXM5SVUE3236C3LQC5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LG2RT4RCXM5SVUE3236C3LQC5E/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":"2026-08-07T16:45:30Z","links":{"resolver":"https://pith.science/pith/LG2RT4RCXM5SVUE3236C3LQC5E","bundle":"https://pith.science/pith/LG2RT4RCXM5SVUE3236C3LQC5E/bundle.json","state":"https://pith.science/pith/LG2RT4RCXM5SVUE3236C3LQC5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LG2RT4RCXM5SVUE3236C3LQC5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LG2RT4RCXM5SVUE3236C3LQC5E","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":"7f6e999bb37bf199b0f6b73aaa1cb160dd2a6bec05a582d57d4ff5c368f7cd1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T19:18:26Z","title_canon_sha256":"229a4489754f0e70db3e4ee46f64dde93b823662b8618dc5c4273aa97269aa55"},"schema_version":"1.0","source":{"id":"2409.09510","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09510","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09510v2","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09510","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"pith_short_12","alias_value":"LG2RT4RCXM5S","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"pith_short_16","alias_value":"LG2RT4RCXM5SVUE3","created_at":"2026-07-05T11:27:20Z"},{"alias_kind":"pith_short_8","alias_value":"LG2RT4RC","created_at":"2026-07-05T11:27:20Z"}],"graph_snapshots":[{"event_id":"sha256:f35b3483fd3582ea64afe4a7d08513484a01cf145843f5c19dea66af0f6476e0","target":"graph","created_at":"2026-07-05T11:27:20Z","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/2409.09510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite its substantial impact on various search, recommendation, and question answering tasks, privacy-preserving methods for personalizing large language models (LLMs) have received relatively limited exploration. There is one primary approach in this area through retrieval-augmented generation (RAG), which generates personalized outputs by enriching the input prompt with information retrieved from the user's personal data. This paper studies an orthogonal approach to RAG that involves learning user-dependent LLM parameters through parameter-efficient fine-tuning (PEFT). This paper presents ","authors_text":"Alireza Salemi, Hamed Zamani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T19:18:26Z","title":"Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09510","kind":"arxiv","version":2},"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":"sha256:085e8b376576d932666f77659daa570c8f520fe5c4629d572f20a55847743b42","target":"record","created_at":"2026-07-05T11:27:20Z","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":"7f6e999bb37bf199b0f6b73aaa1cb160dd2a6bec05a582d57d4ff5c368f7cd1a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T19:18:26Z","title_canon_sha256":"229a4489754f0e70db3e4ee46f64dde93b823662b8618dc5c4273aa97269aa55"},"schema_version":"1.0","source":{"id":"2409.09510","kind":"arxiv","version":2}},"canonical_sha256":"59b519f222bb3b2ad09bd6fc2dae02e92eb76833bc475b4efbbb06be16c29939","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59b519f222bb3b2ad09bd6fc2dae02e92eb76833bc475b4efbbb06be16c29939","first_computed_at":"2026-07-05T11:27:20.357490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:20.357490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lyA03iqzBs6jHSveA+mjdE9xn9eh7IHhuIE/h+p9QzjZaDoNRWmoMl7BYL0W+cdRicEPIfBRb7GnIKIfdT0EBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:20.357969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09510","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:085e8b376576d932666f77659daa570c8f520fe5c4629d572f20a55847743b42","sha256:f35b3483fd3582ea64afe4a7d08513484a01cf145843f5c19dea66af0f6476e0"],"state_sha256":"fbeb233203853443ffc4edbd9f26a7324cf1b69d59496b1e2d01d7eaf3cd24dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UJA2H3mYYNSeSEMYKpenhp3+sG0PAcU2/+r/XSkWO2h9oc5NRRBSzXtdtWGx/6/RahBtL7ZmLiQen5W9h8jrAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:45:30.307795Z","bundle_sha256":"10fcd448e8e21ea12796868fc4f56db9fc3536d9d34ea0f3246654a6499b7851"}}