{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YA6PRTFOACGPTLSCIAIHSDUSZ3","short_pith_number":"pith:YA6PRTFO","canonical_record":{"source":{"id":"2508.14062","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T10:26:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"744d232190ed12aa8daaed50dcd4c58d47cddf02a49629178ffe6ad53e2011df","abstract_canon_sha256":"a815fc45b6bc27223375ef6d56f4881d144c5d932f5ccb000feaf8c1cf2ef63a"},"schema_version":"1.0"},"canonical_sha256":"c03cf8ccae008cf9ae424010790e92cece6ed22aa9da9d8244ffb9cc0c9039f1","source":{"kind":"arxiv","id":"2508.14062","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14062","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14062v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14062","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"YA6PRTFOACGP","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"YA6PRTFOACGPTLSC","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"YA6PRTFO","created_at":"2026-07-05T11:56:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YA6PRTFOACGPTLSCIAIHSDUSZ3","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14062","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T10:26:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"744d232190ed12aa8daaed50dcd4c58d47cddf02a49629178ffe6ad53e2011df","abstract_canon_sha256":"a815fc45b6bc27223375ef6d56f4881d144c5d932f5ccb000feaf8c1cf2ef63a"},"schema_version":"1.0"},"canonical_sha256":"c03cf8ccae008cf9ae424010790e92cece6ed22aa9da9d8244ffb9cc0c9039f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:24.189115Z","signature_b64":"8ycbSERy/lfSlTPx6hvPq/ZMasS07r9jhjCBHtEYkKHZkiaXyRA4BWwVtL7zarJ98T81XYzDBvFlRvlWeyy9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c03cf8ccae008cf9ae424010790e92cece6ed22aa9da9d8244ffb9cc0c9039f1","last_reissued_at":"2026-07-05T11:56:24.188697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:24.188697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14062","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":"2026-07-05T11:56:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SBAI56v3DbVGQgnrAZfRPtgNOTX4chXLODAnBcv5cb4i5bCS4ndlyF1LQufLNOIz/wiXK26K7bs3cfVeW3qhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:13:35.695447Z"},"content_sha256":"00be08e225b05f55f17281678b4ed4272c45d0fe6ef4343c4d4b3d9b233af1b4","schema_version":"1.0","event_id":"sha256:00be08e225b05f55f17281678b4ed4272c45d0fe6ef4343c4d4b3d9b233af1b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YA6PRTFOACGPTLSCIAIHSDUSZ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akshaya Balaji, Badrinath Ramakrishnan","submitted_at":"2025-08-10T10:26:55Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning processes. This paper presents a comprehensive empirical analysis of data memorization in fine-tuned LLMs and introduces a novel multi-layered privacy protection framework. Through controlled experiments on modern LLM architectures including GPT-2, Phi-3, and Gemma-2, we demonstrate that fine-tuning with repeated sensitive data increases privacy leakage rates from ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14062","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/2508.14062/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":"2026-07-05T11:56:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhTYorL1HwO5zBouhVMwbxa/IMN0ZZqnW2qjdIq6WMnhfenZn0WzEzFxdgerNcs+7oM14ujb+siXkbYoYithAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:13:35.696022Z"},"content_sha256":"21a143d39393b3ee1941e98280a5aa0c0dd2cbbcfde77778190e43ff5c20b661","schema_version":"1.0","event_id":"sha256:21a143d39393b3ee1941e98280a5aa0c0dd2cbbcfde77778190e43ff5c20b661"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3/bundle.json","state_url":"https://pith.science/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3/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":"2026-08-08T07:13:35Z","links":{"resolver":"https://pith.science/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3","bundle":"https://pith.science/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3/bundle.json","state":"https://pith.science/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YA6PRTFOACGPTLSCIAIHSDUSZ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YA6PRTFOACGPTLSCIAIHSDUSZ3","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":"a815fc45b6bc27223375ef6d56f4881d144c5d932f5ccb000feaf8c1cf2ef63a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T10:26:55Z","title_canon_sha256":"744d232190ed12aa8daaed50dcd4c58d47cddf02a49629178ffe6ad53e2011df"},"schema_version":"1.0","source":{"id":"2508.14062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14062","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14062v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14062","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"YA6PRTFOACGP","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"YA6PRTFOACGPTLSC","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"YA6PRTFO","created_at":"2026-07-05T11:56:24Z"}],"graph_snapshots":[{"event_id":"sha256:21a143d39393b3ee1941e98280a5aa0c0dd2cbbcfde77778190e43ff5c20b661","target":"graph","created_at":"2026-07-05T11:56:24Z","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/2508.14062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, but their tendency to memorize training data poses significant privacy risks, particularly during fine-tuning processes. This paper presents a comprehensive empirical analysis of data memorization in fine-tuned LLMs and introduces a novel multi-layered privacy protection framework. Through controlled experiments on modern LLM architectures including GPT-2, Phi-3, and Gemma-2, we demonstrate that fine-tuning with repeated sensitive data increases privacy leakage rates from ba","authors_text":"Akshaya Balaji, Badrinath Ramakrishnan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T10:26:55Z","title":"Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14062","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":"sha256:00be08e225b05f55f17281678b4ed4272c45d0fe6ef4343c4d4b3d9b233af1b4","target":"record","created_at":"2026-07-05T11:56:24Z","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":"a815fc45b6bc27223375ef6d56f4881d144c5d932f5ccb000feaf8c1cf2ef63a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T10:26:55Z","title_canon_sha256":"744d232190ed12aa8daaed50dcd4c58d47cddf02a49629178ffe6ad53e2011df"},"schema_version":"1.0","source":{"id":"2508.14062","kind":"arxiv","version":1}},"canonical_sha256":"c03cf8ccae008cf9ae424010790e92cece6ed22aa9da9d8244ffb9cc0c9039f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c03cf8ccae008cf9ae424010790e92cece6ed22aa9da9d8244ffb9cc0c9039f1","first_computed_at":"2026-07-05T11:56:24.188697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:24.188697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ycbSERy/lfSlTPx6hvPq/ZMasS07r9jhjCBHtEYkKHZkiaXyRA4BWwVtL7zarJ98T81XYzDBvFlRvlWeyy9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:24.189115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00be08e225b05f55f17281678b4ed4272c45d0fe6ef4343c4d4b3d9b233af1b4","sha256:21a143d39393b3ee1941e98280a5aa0c0dd2cbbcfde77778190e43ff5c20b661"],"state_sha256":"6e3a623ef2083403b4cc5c47aca34cfd2cc1c9ff00099f9b5e37a02fd88ab058"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eY0uQQu0WlhkvZRX0ZEUpsbP/E2/Mj0YvdxmXBG81dTjBuliqUgzCGWlG44jwUbstjf1IRJOux7aDHBNM6V3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:13:35.703591Z","bundle_sha256":"a8cfea779dee982069fe04df60999008a81f2ba88d0fc40eee039a65381a23c3"}}