{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HZTLKSVUIFKSXWA3AZAUROT5Z6","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":"aafeefc9e8e60a0452b617d3e52fc034486e9c204cb3c1a68fee22155276cd9c","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T12:11:26Z","title_canon_sha256":"8852c3796dcad477e1cdd04f04bdfb42ba3eb1c15d8cd49d64998d24871b84cc"},"schema_version":"1.0","source":{"id":"2403.14339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14339","created_at":"2026-07-05T07:59:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14339v1","created_at":"2026-07-05T07:59:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14339","created_at":"2026-07-05T07:59:07Z"},{"alias_kind":"pith_short_12","alias_value":"HZTLKSVUIFKS","created_at":"2026-07-05T07:59:07Z"},{"alias_kind":"pith_short_16","alias_value":"HZTLKSVUIFKSXWA3","created_at":"2026-07-05T07:59:07Z"},{"alias_kind":"pith_short_8","alias_value":"HZTLKSVU","created_at":"2026-07-05T07:59:07Z"}],"graph_snapshots":[{"event_id":"sha256:8e5deaaec84c8751e722d906054480088f4b46985f5c7f6fbe58f858ab008bfd","target":"graph","created_at":"2026-07-05T07:59:07Z","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/2403.14339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Cesare Campagnano, Daniel Trippa, Fabrizio Silvestri, Gabriele Tolomei, Maria Sofia Bucarelli","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T12:11:26Z","title":"$\\nabla \\tau$: Gradient-based and Task-Agnostic machine Unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14339","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:fd8f641bca58d3a6fdfbd98ee65a879b949cb6417b12fec0aedaa966981b588f","target":"record","created_at":"2026-07-05T07:59:07Z","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":"aafeefc9e8e60a0452b617d3e52fc034486e9c204cb3c1a68fee22155276cd9c","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T12:11:26Z","title_canon_sha256":"8852c3796dcad477e1cdd04f04bdfb42ba3eb1c15d8cd49d64998d24871b84cc"},"schema_version":"1.0","source":{"id":"2403.14339","kind":"arxiv","version":1}},"canonical_sha256":"3e66b54ab441552bd81b064148ba7dcf86637f393527df4fe4c947d528882f30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e66b54ab441552bd81b064148ba7dcf86637f393527df4fe4c947d528882f30","first_computed_at":"2026-07-05T07:59:07.180861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:07.180861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"McYRmA901wQEpPFxby5OWgP85k9X1jdS14yh8irf2pa9DKuhn3xoETrVOBXAP4dAIImlG18L7pha4/qZC/1mCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:07.181310Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd8f641bca58d3a6fdfbd98ee65a879b949cb6417b12fec0aedaa966981b588f","sha256:8e5deaaec84c8751e722d906054480088f4b46985f5c7f6fbe58f858ab008bfd"],"state_sha256":"1114090361636ea2e45f0e149bf7ae7b680a393df058035f7022d7b9cce07ea6"}