{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CXHUWOCPEHDMBMZWP5L323E4DL","short_pith_number":"pith:CXHUWOCP","schema_version":"1.0","canonical_sha256":"15cf4b384f21c6c0b3367f57bd6c9c1af7c2a697819017ceb799ba4b2561c3e3","source":{"kind":"arxiv","id":"2402.10058","version":2},"attestation_state":"computed","paper":{"title":"Towards Safer Large Language Models through Machine Unlearning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyao Dou, Meng Jiang, Yijun Tian, Zhaoxuan Tan, Zheyuan Liu","submitted_at":"2024-02-15T16:28:34Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter challenges in generating harmful content when faced with problematic prompts. To address this problem, existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output. While these methods can be effective, they frequently impact the model utility in responding to normal prompts. To address this gap, we introduce Se"},"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":"2402.10058","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-15T16:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"c34458fadb397feac711d34aec58228ff36e3e12c579270ce64903127aa53196","abstract_canon_sha256":"3732a8da24e81f598c4fe05ec36f675d66e85ff3ba76d8c1e7f65e2c1755e031"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:24.769136Z","signature_b64":"BUXIFhgl05ifU/mpGcK7kq1l97JzNzBJBmAEtwHKYlry9DktHrw51D9As+c0cYK4Heh7fM1N67jo+KsDtt/CBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15cf4b384f21c6c0b3367f57bd6c9c1af7c2a697819017ceb799ba4b2561c3e3","last_reissued_at":"2026-07-05T08:27:24.768699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:24.768699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Safer Large Language Models through Machine Unlearning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyao Dou, Meng Jiang, Yijun Tian, Zhaoxuan Tan, Zheyuan Liu","submitted_at":"2024-02-15T16:28:34Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter challenges in generating harmful content when faced with problematic prompts. To address this problem, existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output. While these methods can be effective, they frequently impact the model utility in responding to normal prompts. To address this gap, we introduce Se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10058","kind":"arxiv","version":2},"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/2402.10058/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":"2402.10058","created_at":"2026-07-05T08:27:24.768760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10058v2","created_at":"2026-07-05T08:27:24.768760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10058","created_at":"2026-07-05T08:27:24.768760+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXHUWOCPEHDM","created_at":"2026-07-05T08:27:24.768760+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXHUWOCPEHDMBMZW","created_at":"2026-07-05T08:27:24.768760+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXHUWOCP","created_at":"2026-07-05T08:27:24.768760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.07406","citing_title":"Machine Unlearning: A Comprehensive Survey","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15687","citing_title":"ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07666","citing_title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","ref_index":139,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08800","citing_title":"PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05909","citing_title":"Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07962","citing_title":"Is your algorithm unlearning or untraining?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13777","citing_title":"From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":174,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL","json":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL.json","graph_json":"https://pith.science/api/pith-number/CXHUWOCPEHDMBMZWP5L323E4DL/graph.json","events_json":"https://pith.science/api/pith-number/CXHUWOCPEHDMBMZWP5L323E4DL/events.json","paper":"https://pith.science/paper/CXHUWOCP"},"agent_actions":{"view_html":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL","download_json":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL.json","view_paper":"https://pith.science/paper/CXHUWOCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10058&json=true","fetch_graph":"https://pith.science/api/pith-number/CXHUWOCPEHDMBMZWP5L323E4DL/graph.json","fetch_events":"https://pith.science/api/pith-number/CXHUWOCPEHDMBMZWP5L323E4DL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL/action/storage_attestation","attest_author":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL/action/author_attestation","sign_citation":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL/action/citation_signature","submit_replication":"https://pith.science/pith/CXHUWOCPEHDMBMZWP5L323E4DL/action/replication_record"}},"created_at":"2026-07-05T08:27:24.768760+00:00","updated_at":"2026-07-05T08:27:24.768760+00:00"}