{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TNH57T4SLRXRUHA7D5HF5HM2QU","short_pith_number":"pith:TNH57T4S","schema_version":"1.0","canonical_sha256":"9b4fdfcf925c6f1a1c1f1f4e5e9d9a8538c4a3642ce2fb98ca301af7d81fcb94","source":{"kind":"arxiv","id":"2405.14020","version":1},"attestation_state":"computed","paper":{"title":"Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dustin Scheinost, Hao Huang, Ling Han, Mar\\'ia Rodr\\'iguez Mart\\'inez, Mary-Anne Hartley","submitted_at":"2024-05-22T21:54:05Z","abstract_excerpt":"Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional approaches typically assume that data variations are random, which makes it difficult to adjust the model parameters accurately to remove patterns and characteristics from unlearned data. In this work, we present Unlearning Information Bottleneck (UIB), a novel information-theoretic framework designed to enhance the process of machine unlearning that effectively "},"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":"2405.14020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T21:54:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c42680b9d2656f659bab8b1ca87979a310afe1ffb9ea3423a483f2097802282","abstract_canon_sha256":"e3b433812271b57282927117b9b18c67cb731a40fb6354ea29d2a98ed498f746"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:09.398629Z","signature_b64":"/ZAyyum26BCro5YcHOXgrtLXPgbE8JTzzaa/spzbjAKeMrF1at0hAwAPz2NGonyjpez8PqGdw9tsxcUkteAhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4fdfcf925c6f1a1c1f1f4e5e9d9a8538c4a3642ce2fb98ca301af7d81fcb94","last_reissued_at":"2026-07-05T08:22:09.398220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:09.398220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dustin Scheinost, Hao Huang, Ling Han, Mar\\'ia Rodr\\'iguez Mart\\'inez, Mary-Anne Hartley","submitted_at":"2024-05-22T21:54:05Z","abstract_excerpt":"Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional approaches typically assume that data variations are random, which makes it difficult to adjust the model parameters accurately to remove patterns and characteristics from unlearned data. In this work, we present Unlearning Information Bottleneck (UIB), a novel information-theoretic framework designed to enhance the process of machine unlearning that effectively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14020","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/2405.14020/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":"2405.14020","created_at":"2026-07-05T08:22:09.398283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14020v1","created_at":"2026-07-05T08:22:09.398283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14020","created_at":"2026-07-05T08:22:09.398283+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNH57T4SLRXR","created_at":"2026-07-05T08:22:09.398283+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNH57T4SLRXRUHA7","created_at":"2026-07-05T08:22:09.398283+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNH57T4S","created_at":"2026-07-05T08:22:09.398283+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/TNH57T4SLRXRUHA7D5HF5HM2QU","json":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU.json","graph_json":"https://pith.science/api/pith-number/TNH57T4SLRXRUHA7D5HF5HM2QU/graph.json","events_json":"https://pith.science/api/pith-number/TNH57T4SLRXRUHA7D5HF5HM2QU/events.json","paper":"https://pith.science/paper/TNH57T4S"},"agent_actions":{"view_html":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU","download_json":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU.json","view_paper":"https://pith.science/paper/TNH57T4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14020&json=true","fetch_graph":"https://pith.science/api/pith-number/TNH57T4SLRXRUHA7D5HF5HM2QU/graph.json","fetch_events":"https://pith.science/api/pith-number/TNH57T4SLRXRUHA7D5HF5HM2QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU/action/storage_attestation","attest_author":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU/action/author_attestation","sign_citation":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU/action/citation_signature","submit_replication":"https://pith.science/pith/TNH57T4SLRXRUHA7D5HF5HM2QU/action/replication_record"}},"created_at":"2026-07-05T08:22:09.398283+00:00","updated_at":"2026-07-05T08:22:09.398283+00:00"}