{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OVBH7U4LE2DIPBTSNY5JT42RRX","short_pith_number":"pith:OVBH7U4L","schema_version":"1.0","canonical_sha256":"75427fd38b26868786726e3a99f3518de241206085e647c3458da4715e0d5930","source":{"kind":"arxiv","id":"2410.17050","version":1},"attestation_state":"computed","paper":{"title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Mohan Kankanhalli, Murari Mandal, Yash Sinha","submitted_at":"2024-10-22T14:30:03Z","abstract_excerpt":"The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy. Analogously, unlearning can potentially be achieved through anti-data samples (or anti-samples), unlearning method, and reversed loss function. While prior research has explored unlearning methods and reversed loss functions, the potential of anti-samples remains largely untapped. In this paper, we introduce UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for large language models (LLMs). Our contributions are threefold; first, we propose a nov"},"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":"2410.17050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T14:30:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"13543d2a595dd34716e963c6f0ecfc4df462ea894eb70bea663061be5a49ba54","abstract_canon_sha256":"27e3680679909020585cf6f7d31fd80bd07a59721a165179b0aea2245ccc00ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:11.473962Z","signature_b64":"Sat1cKrAGpmCJnrabQbrzz6zWvrcNlo8B4C6Bhv017SAhY/2t10+m3g7RAAtT4DnxzFhWYEjjQTWijUvnPt4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75427fd38b26868786726e3a99f3518de241206085e647c3458da4715e0d5930","last_reissued_at":"2026-07-05T09:24:11.473467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:11.473467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Mohan Kankanhalli, Murari Mandal, Yash Sinha","submitted_at":"2024-10-22T14:30:03Z","abstract_excerpt":"The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy. Analogously, unlearning can potentially be achieved through anti-data samples (or anti-samples), unlearning method, and reversed loss function. While prior research has explored unlearning methods and reversed loss functions, the potential of anti-samples remains largely untapped. In this paper, we introduce UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for large language models (LLMs). Our contributions are threefold; first, we propose a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17050","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/2410.17050/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":"2410.17050","created_at":"2026-07-05T09:24:11.473534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17050v1","created_at":"2026-07-05T09:24:11.473534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17050","created_at":"2026-07-05T09:24:11.473534+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVBH7U4LE2DI","created_at":"2026-07-05T09:24:11.473534+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVBH7U4LE2DIPBTS","created_at":"2026-07-05T09:24:11.473534+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVBH7U4L","created_at":"2026-07-05T09:24:11.473534+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19894","citing_title":"A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction","ref_index":203,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX","json":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX.json","graph_json":"https://pith.science/api/pith-number/OVBH7U4LE2DIPBTSNY5JT42RRX/graph.json","events_json":"https://pith.science/api/pith-number/OVBH7U4LE2DIPBTSNY5JT42RRX/events.json","paper":"https://pith.science/paper/OVBH7U4L"},"agent_actions":{"view_html":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX","download_json":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX.json","view_paper":"https://pith.science/paper/OVBH7U4L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17050&json=true","fetch_graph":"https://pith.science/api/pith-number/OVBH7U4LE2DIPBTSNY5JT42RRX/graph.json","fetch_events":"https://pith.science/api/pith-number/OVBH7U4LE2DIPBTSNY5JT42RRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX/action/storage_attestation","attest_author":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX/action/author_attestation","sign_citation":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX/action/citation_signature","submit_replication":"https://pith.science/pith/OVBH7U4LE2DIPBTSNY5JT42RRX/action/replication_record"}},"created_at":"2026-07-05T09:24:11.473534+00:00","updated_at":"2026-07-05T09:24:11.473534+00:00"}