{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SF3MZT5RL6JKZVNF3Y76NI7G5U","short_pith_number":"pith:SF3MZT5R","schema_version":"1.0","canonical_sha256":"9176cccfb15f92acd5a5de3fe6a3e6ed32ec7c28d50bb42ecb4c1eef49875ed2","source":{"kind":"arxiv","id":"2505.10941","version":1},"attestation_state":"computed","paper":{"title":"Privacy-Aware Lifelong Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elmar Rueckert, Ozan \\\"Ozdenizci, Robert Legenstein","submitted_at":"2025-05-16T07:27:00Z","abstract_excerpt":"Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge from pretrained models when requested, in order to comply with data privacy regulations on the right-to-be-forgotten. Enabling efficient lifelong learning with the capability to selectively unlearn sensitive information from models presents a critical and largely unaddressed challenge with contradicting objectives. We address this problem from the perspective o"},"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":"2505.10941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T07:27:00Z","cross_cats_sorted":[],"title_canon_sha256":"a3dc2468b5041b703af03a4ac68960e8afdcad8a7aacb8e3f71219840e60ed62","abstract_canon_sha256":"3730334cc364333be55409fa5511748c8a2ef001c6416a7ba6f9e9d94073448e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:08.275825Z","signature_b64":"xkPm60VxvwbDG+vCu/YkE6tkqrTxqeykVYBnZ+uz0dDGw0gPtQwD9lb0bmSXKJw0QBM9FO83HnI9D/7guJNmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9176cccfb15f92acd5a5de3fe6a3e6ed32ec7c28d50bb42ecb4c1eef49875ed2","last_reissued_at":"2026-07-05T11:04:08.275330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:08.275330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-Aware Lifelong Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elmar Rueckert, Ozan \\\"Ozdenizci, Robert Legenstein","submitted_at":"2025-05-16T07:27:00Z","abstract_excerpt":"Lifelong learning algorithms enable models to incrementally acquire new knowledge without forgetting previously learned information. Contrarily, the field of machine unlearning focuses on explicitly forgetting certain previous knowledge from pretrained models when requested, in order to comply with data privacy regulations on the right-to-be-forgotten. Enabling efficient lifelong learning with the capability to selectively unlearn sensitive information from models presents a critical and largely unaddressed challenge with contradicting objectives. We address this problem from the perspective o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10941","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/2505.10941/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":"2505.10941","created_at":"2026-07-05T11:04:08.275397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10941v1","created_at":"2026-07-05T11:04:08.275397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10941","created_at":"2026-07-05T11:04:08.275397+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF3MZT5RL6JK","created_at":"2026-07-05T11:04:08.275397+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF3MZT5RL6JKZVNF","created_at":"2026-07-05T11:04:08.275397+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF3MZT5R","created_at":"2026-07-05T11:04:08.275397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.12958","citing_title":"Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U","json":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U.json","graph_json":"https://pith.science/api/pith-number/SF3MZT5RL6JKZVNF3Y76NI7G5U/graph.json","events_json":"https://pith.science/api/pith-number/SF3MZT5RL6JKZVNF3Y76NI7G5U/events.json","paper":"https://pith.science/paper/SF3MZT5R"},"agent_actions":{"view_html":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U","download_json":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U.json","view_paper":"https://pith.science/paper/SF3MZT5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10941&json=true","fetch_graph":"https://pith.science/api/pith-number/SF3MZT5RL6JKZVNF3Y76NI7G5U/graph.json","fetch_events":"https://pith.science/api/pith-number/SF3MZT5RL6JKZVNF3Y76NI7G5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U/action/storage_attestation","attest_author":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U/action/author_attestation","sign_citation":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U/action/citation_signature","submit_replication":"https://pith.science/pith/SF3MZT5RL6JKZVNF3Y76NI7G5U/action/replication_record"}},"created_at":"2026-07-05T11:04:08.275397+00:00","updated_at":"2026-07-05T11:04:08.275397+00:00"}