{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QAOOJPLBV7ODK5QN5TFV7JP6XR","short_pith_number":"pith:QAOOJPLB","schema_version":"1.0","canonical_sha256":"801ce4bd61afdc35760deccb5fa5febc6fcd7f39ff61b87b485943785f8cea34","source":{"kind":"arxiv","id":"2003.10933","version":3},"attestation_state":"computed","paper":{"title":"Learn to Forget: Machine Unlearning via Neuron Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianfeng Ma, Jian Liu, Kui Ren, Philip Yu, Ximeng Liu, Yang Liu, Zhongyuan Jiang, Zhuo Ma","submitted_at":"2020-03-24T15:46:38Z","abstract_excerpt":"Nowadays, machine learning models, especially neural networks, become prevalent in many real-world applications.These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to withdraw; and it is well-known that a neural network memorizes its training data. This contradicts the \"right to be forgotten\" clause of GDPR, potentially leading to law violations. To this end, machine unlearning becomes a popular research topic, which allows users to eliminate memorization of their private data from a trained machine learning model.In this pap"},"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":"2003.10933","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-24T15:46:38Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"08d0dc9cead4f563e8dde6854d85427b7dd20f8f6ef49948ae2cccc9232a3dca","abstract_canon_sha256":"9d99b61a032e402d6b8b8661c280ec00fd8c7b5e856906dc491241e2f3e83faa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:07.684176Z","signature_b64":"HD+kBHtF7U7K4L0QAFJ4OORktFx4TIwqg2DjA3bBpEeYEkIlGEk6zAiQlAW861eQMMqY3tP3PP2WIeuGYkzMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"801ce4bd61afdc35760deccb5fa5febc6fcd7f39ff61b87b485943785f8cea34","last_reissued_at":"2026-07-05T03:02:07.683757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:07.683757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn to Forget: Machine Unlearning via Neuron Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianfeng Ma, Jian Liu, Kui Ren, Philip Yu, Ximeng Liu, Yang Liu, Zhongyuan Jiang, Zhuo Ma","submitted_at":"2020-03-24T15:46:38Z","abstract_excerpt":"Nowadays, machine learning models, especially neural networks, become prevalent in many real-world applications.These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to withdraw; and it is well-known that a neural network memorizes its training data. This contradicts the \"right to be forgotten\" clause of GDPR, potentially leading to law violations. To this end, machine unlearning becomes a popular research topic, which allows users to eliminate memorization of their private data from a trained machine learning model.In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10933","kind":"arxiv","version":3},"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/2003.10933/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":"2003.10933","created_at":"2026-07-05T03:02:07.683819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.10933v3","created_at":"2026-07-05T03:02:07.683819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10933","created_at":"2026-07-05T03:02:07.683819+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAOOJPLBV7OD","created_at":"2026-07-05T03:02:07.683819+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAOOJPLBV7ODK5QN","created_at":"2026-07-05T03:02:07.683819+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAOOJPLB","created_at":"2026-07-05T03:02:07.683819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04713","citing_title":"Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01047","citing_title":"LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR","json":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR.json","graph_json":"https://pith.science/api/pith-number/QAOOJPLBV7ODK5QN5TFV7JP6XR/graph.json","events_json":"https://pith.science/api/pith-number/QAOOJPLBV7ODK5QN5TFV7JP6XR/events.json","paper":"https://pith.science/paper/QAOOJPLB"},"agent_actions":{"view_html":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR","download_json":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR.json","view_paper":"https://pith.science/paper/QAOOJPLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.10933&json=true","fetch_graph":"https://pith.science/api/pith-number/QAOOJPLBV7ODK5QN5TFV7JP6XR/graph.json","fetch_events":"https://pith.science/api/pith-number/QAOOJPLBV7ODK5QN5TFV7JP6XR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR/action/storage_attestation","attest_author":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR/action/author_attestation","sign_citation":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR/action/citation_signature","submit_replication":"https://pith.science/pith/QAOOJPLBV7ODK5QN5TFV7JP6XR/action/replication_record"}},"created_at":"2026-07-05T03:02:07.683819+00:00","updated_at":"2026-07-05T03:02:07.683819+00:00"}