{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZTLKSVUIFKSXWA3AZAUROT5Z6","short_pith_number":"pith:HZTLKSVU","schema_version":"1.0","canonical_sha256":"3e66b54ab441552bd81b064148ba7dcf86637f393527df4fe4c947d528882f30","source":{"kind":"arxiv","id":"2403.14339","version":1},"attestation_state":"computed","paper":{"title":"$\\nabla \\tau$: Gradient-based and Task-Agnostic machine Unlearning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Cesare Campagnano, Daniel Trippa, Fabrizio Silvestri, Gabriele Tolomei, Maria Sofia Bucarelli","submitted_at":"2024-03-21T12:11:26Z","abstract_excerpt":"Machine Unlearning, the process of selectively eliminating the influence of certain data examples used during a model's training, has gained significant attention as a means for practitioners to comply with recent data protection regulations. However, existing unlearning methods face critical drawbacks, including their prohibitively high cost, often associated with a large number of hyperparameters, and the limitation of forgetting only relatively small data portions. This often makes retraining the model from scratch a quicker and more effective solution. In this study, we introduce Gradient-"},"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":"2403.14339","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T12:11:26Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"8852c3796dcad477e1cdd04f04bdfb42ba3eb1c15d8cd49d64998d24871b84cc","abstract_canon_sha256":"aafeefc9e8e60a0452b617d3e52fc034486e9c204cb3c1a68fee22155276cd9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:07.181310Z","signature_b64":"McYRmA901wQEpPFxby5OWgP85k9X1jdS14yh8irf2pa9DKuhn3xoETrVOBXAP4dAIImlG18L7pha4/qZC/1mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e66b54ab441552bd81b064148ba7dcf86637f393527df4fe4c947d528882f30","last_reissued_at":"2026-07-05T07:59:07.180861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:07.180861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\nabla \\tau$: Gradient-based and Task-Agnostic machine Unlearning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Cesare Campagnano, Daniel Trippa, Fabrizio Silvestri, Gabriele Tolomei, Maria Sofia Bucarelli","submitted_at":"2024-03-21T12:11:26Z","abstract_excerpt":"Machine Unlearning, the process of selectively eliminating the influence of certain data examples used during a model's training, has gained significant attention as a means for practitioners to comply with recent data protection regulations. However, existing unlearning methods face critical drawbacks, including their prohibitively high cost, often associated with a large number of hyperparameters, and the limitation of forgetting only relatively small data portions. This often makes retraining the model from scratch a quicker and more effective solution. In this study, we introduce Gradient-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14339","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/2403.14339/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":"2403.14339","created_at":"2026-07-05T07:59:07.180919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14339v1","created_at":"2026-07-05T07:59:07.180919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14339","created_at":"2026-07-05T07:59:07.180919+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZTLKSVUIFKS","created_at":"2026-07-05T07:59:07.180919+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZTLKSVUIFKSXWA3","created_at":"2026-07-05T07:59:07.180919+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZTLKSVU","created_at":"2026-07-05T07:59:07.180919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02422","citing_title":"Superior resilience to poisoning and amenability to unlearning in quantum machine learning","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6","json":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6.json","graph_json":"https://pith.science/api/pith-number/HZTLKSVUIFKSXWA3AZAUROT5Z6/graph.json","events_json":"https://pith.science/api/pith-number/HZTLKSVUIFKSXWA3AZAUROT5Z6/events.json","paper":"https://pith.science/paper/HZTLKSVU"},"agent_actions":{"view_html":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6","download_json":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6.json","view_paper":"https://pith.science/paper/HZTLKSVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14339&json=true","fetch_graph":"https://pith.science/api/pith-number/HZTLKSVUIFKSXWA3AZAUROT5Z6/graph.json","fetch_events":"https://pith.science/api/pith-number/HZTLKSVUIFKSXWA3AZAUROT5Z6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6/action/storage_attestation","attest_author":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6/action/author_attestation","sign_citation":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6/action/citation_signature","submit_replication":"https://pith.science/pith/HZTLKSVUIFKSXWA3AZAUROT5Z6/action/replication_record"}},"created_at":"2026-07-05T07:59:07.180919+00:00","updated_at":"2026-07-05T07:59:07.180919+00:00"}