{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MSR764HL4BGQEYP7TV7ILKCU2L","short_pith_number":"pith:MSR764HL","schema_version":"1.0","canonical_sha256":"64a3ff70ebe04d0261ff9d7e85a854d2e5db26dc0fd8e8f62e5e6076bea8b6ca","source":{"kind":"arxiv","id":"2506.06112","version":1},"attestation_state":"computed","paper":{"title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cheng-Long Wang, Di Wang, Qi Li, Yinzhi Cao, Zihang Xiang","submitted_at":"2025-06-06T14:22:18Z","abstract_excerpt":"Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely used to externally assess successful unlearning. However, existing methods face two key limitations: (1) maximizing MIA effectiveness (e.g., via online attacks) requires prohibitive computational resources, often exceeding retraining costs; (2) MIAs, designed for binary inclusion tests, struggle to capture granular changes in approximate unlearning. To address"},"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":"2506.06112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T14:22:18Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"c9434d359ee8e64cdcf751399b856a74cfc50988a0eb78d8dd6fd87402ea4fa6","abstract_canon_sha256":"dac7fdd4003ca8a0c8859f68a7243bbea28dd1f04096125303b539553e97736e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:25.688703Z","signature_b64":"h4n1LUh7LB3KVkntmxbHuFg362+US9S/e22PeAG95W81m8C9HyNUkUmhZ/z9bk1uiDPqLoP5ZDcm5EAaYtGIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64a3ff70ebe04d0261ff9d7e85a854d2e5db26dc0fd8e8f62e5e6076bea8b6ca","last_reissued_at":"2026-07-05T11:17:25.688183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:25.688183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cheng-Long Wang, Di Wang, Qi Li, Yinzhi Cao, Zihang Xiang","submitted_at":"2025-06-06T14:22:18Z","abstract_excerpt":"Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks (MIAs) are widely used to externally assess successful unlearning. However, existing methods face two key limitations: (1) maximizing MIA effectiveness (e.g., via online attacks) requires prohibitive computational resources, often exceeding retraining costs; (2) MIAs, designed for binary inclusion tests, struggle to capture granular changes in approximate unlearning. To address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06112","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/2506.06112/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":"2506.06112","created_at":"2026-07-05T11:17:25.688244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06112v1","created_at":"2026-07-05T11:17:25.688244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06112","created_at":"2026-07-05T11:17:25.688244+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSR764HL4BGQ","created_at":"2026-07-05T11:17:25.688244+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSR764HL4BGQEYP7","created_at":"2026-07-05T11:17:25.688244+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSR764HL","created_at":"2026-07-05T11:17:25.688244+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/MSR764HL4BGQEYP7TV7ILKCU2L","json":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L.json","graph_json":"https://pith.science/api/pith-number/MSR764HL4BGQEYP7TV7ILKCU2L/graph.json","events_json":"https://pith.science/api/pith-number/MSR764HL4BGQEYP7TV7ILKCU2L/events.json","paper":"https://pith.science/paper/MSR764HL"},"agent_actions":{"view_html":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L","download_json":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L.json","view_paper":"https://pith.science/paper/MSR764HL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06112&json=true","fetch_graph":"https://pith.science/api/pith-number/MSR764HL4BGQEYP7TV7ILKCU2L/graph.json","fetch_events":"https://pith.science/api/pith-number/MSR764HL4BGQEYP7TV7ILKCU2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L/action/storage_attestation","attest_author":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L/action/author_attestation","sign_citation":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L/action/citation_signature","submit_replication":"https://pith.science/pith/MSR764HL4BGQEYP7TV7ILKCU2L/action/replication_record"}},"created_at":"2026-07-05T11:17:25.688244+00:00","updated_at":"2026-07-05T11:17:25.688244+00:00"}