{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LYZVNUHFMODHEUJLRUVJ3UB3XY","short_pith_number":"pith:LYZVNUHF","canonical_record":{"source":{"id":"2404.11056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-17T04:08:38Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"4030a41dece4332f582b5e6bd4fb6bfa05bd8ff12b4ca6bac46dadce32c33d28","abstract_canon_sha256":"f7b467bc3a265f8cdce0c88a85711a8ac6d589cfb0315a59a62cb04dbac4dd12"},"schema_version":"1.0"},"canonical_sha256":"5e3356d0e5638672512b8d2a9dd03bbe24ec82af360a7cb05d8cb58e8def1108","source":{"kind":"arxiv","id":"2404.11056","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11056","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11056v1","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11056","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"LYZVNUHFMODH","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"LYZVNUHFMODHEUJL","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"LYZVNUHF","created_at":"2026-07-05T08:09:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LYZVNUHFMODHEUJLRUVJ3UB3XY","target":"record","payload":{"canonical_record":{"source":{"id":"2404.11056","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-17T04:08:38Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"4030a41dece4332f582b5e6bd4fb6bfa05bd8ff12b4ca6bac46dadce32c33d28","abstract_canon_sha256":"f7b467bc3a265f8cdce0c88a85711a8ac6d589cfb0315a59a62cb04dbac4dd12"},"schema_version":"1.0"},"canonical_sha256":"5e3356d0e5638672512b8d2a9dd03bbe24ec82af360a7cb05d8cb58e8def1108","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:02.722396Z","signature_b64":"hT7xFEJIqKwycAmRQfmWUyEgFfRggfxCJ8abM67ZTEzMuhAzqstOhAHM15kbPTVlMCzV3r6cmtK2lBN4UVnkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e3356d0e5638672512b8d2a9dd03bbe24ec82af360a7cb05d8cb58e8def1108","last_reissued_at":"2026-07-05T08:09:02.721997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:02.721997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.11056","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":"2026-07-05T08:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7yhuNb3rydMmx49LKWoKRHRQcU2/Xiod0wq812Pg0QKdTAmHQSCakCBU15MLtm2156WCaBu0VvGyqJ0TXwnnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:44:43.067196Z"},"content_sha256":"7c8b86c65d9cad0734e33f4e97660d913813a2a637e0251aa8cca9483fb02f35","schema_version":"1.0","event_id":"sha256:7c8b86c65d9cad0734e33f4e97660d913813a2a637e0251aa8cca9483fb02f35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LYZVNUHFMODHEUJLRUVJ3UB3XY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LMEraser: Large Model Unlearning through Adaptive Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cong Wang, Jie Xu, Xiaohua Jia, Zihan Wu","submitted_at":"2024-04-17T04:08:38Z","abstract_excerpt":"To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \\textbf{L}arge \\textbf{M}odels, called \\textbf{LM}Eraser. Existing unlearning research suffers from entangled training data and complex model architectures, incurring extremely high computational costs for large models. LMEraser takes a divide-and-conquer strategy with a prompt tuning architecture to isolate data influence. The training dataset is partitioned into public and private datasets. Public data are used to train the backbone of the model. Private "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11056","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/2404.11056/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":"2026-07-05T08:09:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pdIVZmpWsuyqrSHUtGSG5AdAD6mQkAmbKCLBfMQO+f7nzv7hx8DIBRtjL2Ru+wIG+io4VJ3KKoitjTKcBy+9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:44:43.067708Z"},"content_sha256":"b6488b39e9567c64539c3d4048ee488053774ab9ad9e781354fd9a48777355e7","schema_version":"1.0","event_id":"sha256:b6488b39e9567c64539c3d4048ee488053774ab9ad9e781354fd9a48777355e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY/bundle.json","state_url":"https://pith.science/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY/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":"2026-08-19T09:44:43Z","links":{"resolver":"https://pith.science/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY","bundle":"https://pith.science/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY/bundle.json","state":"https://pith.science/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYZVNUHFMODHEUJLRUVJ3UB3XY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LYZVNUHFMODHEUJLRUVJ3UB3XY","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":"f7b467bc3a265f8cdce0c88a85711a8ac6d589cfb0315a59a62cb04dbac4dd12","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-17T04:08:38Z","title_canon_sha256":"4030a41dece4332f582b5e6bd4fb6bfa05bd8ff12b4ca6bac46dadce32c33d28"},"schema_version":"1.0","source":{"id":"2404.11056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.11056","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"arxiv_version","alias_value":"2404.11056v1","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11056","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"pith_short_12","alias_value":"LYZVNUHFMODH","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"pith_short_16","alias_value":"LYZVNUHFMODHEUJL","created_at":"2026-07-05T08:09:02Z"},{"alias_kind":"pith_short_8","alias_value":"LYZVNUHF","created_at":"2026-07-05T08:09:02Z"}],"graph_snapshots":[{"event_id":"sha256:b6488b39e9567c64539c3d4048ee488053774ab9ad9e781354fd9a48777355e7","target":"graph","created_at":"2026-07-05T08:09:02Z","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/2404.11056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \\textbf{L}arge \\textbf{M}odels, called \\textbf{LM}Eraser. Existing unlearning research suffers from entangled training data and complex model architectures, incurring extremely high computational costs for large models. LMEraser takes a divide-and-conquer strategy with a prompt tuning architecture to isolate data influence. The training dataset is partitioned into public and private datasets. Public data are used to train the backbone of the model. Private ","authors_text":"Cong Wang, Jie Xu, Xiaohua Jia, Zihan Wu","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-17T04:08:38Z","title":"LMEraser: Large Model Unlearning through Adaptive Prompt Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11056","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":"sha256:7c8b86c65d9cad0734e33f4e97660d913813a2a637e0251aa8cca9483fb02f35","target":"record","created_at":"2026-07-05T08:09:02Z","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":"f7b467bc3a265f8cdce0c88a85711a8ac6d589cfb0315a59a62cb04dbac4dd12","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-17T04:08:38Z","title_canon_sha256":"4030a41dece4332f582b5e6bd4fb6bfa05bd8ff12b4ca6bac46dadce32c33d28"},"schema_version":"1.0","source":{"id":"2404.11056","kind":"arxiv","version":1}},"canonical_sha256":"5e3356d0e5638672512b8d2a9dd03bbe24ec82af360a7cb05d8cb58e8def1108","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e3356d0e5638672512b8d2a9dd03bbe24ec82af360a7cb05d8cb58e8def1108","first_computed_at":"2026-07-05T08:09:02.721997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:02.721997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hT7xFEJIqKwycAmRQfmWUyEgFfRggfxCJ8abM67ZTEzMuhAzqstOhAHM15kbPTVlMCzV3r6cmtK2lBN4UVnkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:02.722396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.11056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c8b86c65d9cad0734e33f4e97660d913813a2a637e0251aa8cca9483fb02f35","sha256:b6488b39e9567c64539c3d4048ee488053774ab9ad9e781354fd9a48777355e7"],"state_sha256":"5d4e3074da85e35fdc7c7361bd6b5e17b6534553892ea257c9c27aa385d86d8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"prXxrsYZTQO6WNTJPgmjM30pY0KZuIECABPamRgE0JcKKbdihLOxojmQxO9wftvVprSdBECQ9luxLzbuKGTyDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:44:43.072717Z","bundle_sha256":"9b6d3547a42e67d8122bc3853b8a24010e1bc8e6c47f2007ac13b958330efbe3"}}