{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VBAM5367NVXCFUHWKFLIRHB3WJ","short_pith_number":"pith:VBAM5367","canonical_record":{"source":{"id":"2505.07640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T15:11:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"145229d2aa2088347c47f9fad33a18171dba95d09240ca244da2675dd060be68","abstract_canon_sha256":"826eed508a8ea638aeba2dfb46ecf9a20276b581b9c79e6ed61741fcf9df1662"},"schema_version":"1.0"},"canonical_sha256":"a840ceefdf6d6e22d0f65156889c3bb270b8e19fc2ee1c178fe08511b0301b01","source":{"kind":"arxiv","id":"2505.07640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07640","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07640v1","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07640","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"VBAM5367NVXC","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"VBAM5367NVXCFUHW","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"VBAM5367","created_at":"2026-07-05T11:01:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VBAM5367NVXCFUHWKFLIRHB3WJ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T15:11:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"145229d2aa2088347c47f9fad33a18171dba95d09240ca244da2675dd060be68","abstract_canon_sha256":"826eed508a8ea638aeba2dfb46ecf9a20276b581b9c79e6ed61741fcf9df1662"},"schema_version":"1.0"},"canonical_sha256":"a840ceefdf6d6e22d0f65156889c3bb270b8e19fc2ee1c178fe08511b0301b01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:51.205645Z","signature_b64":"n7L+avquFFeq8lg9pNrtMt8LuGrcMme2q0vb4bJJ53eMCCtbn4+82dRwgm2Lul4UMsS6KdHf8nBbERFOgo/AAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a840ceefdf6d6e22d0f65156889c3bb270b8e19fc2ee1c178fe08511b0301b01","last_reissued_at":"2026-07-05T11:01:51.205142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:51.205142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07640","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DBjOBJ2wcwbJ4XcXltfqhPDwV4nV5lKeULV+kdpXgy30J5j524+p1nvJL2b1H+0pFkq1G658JZt0ATjrPDYCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:44:01.967622Z"},"content_sha256":"a48f52585ea79d200acbcc7d2c00ff25ca296367ce5b9d20528442e6251ba6d8","schema_version":"1.0","event_id":"sha256:a48f52585ea79d200acbcc7d2c00ff25ca296367ce5b9d20528442e6251ba6d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VBAM5367NVXCFUHWKFLIRHB3WJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Certified Data Removal Under High-dimensional Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Arian Maleki, Arnab Auddy, Haolin Zou, Kamiar Rahnama Rad, Yongchan Kwon","submitted_at":"2025-05-12T15:11:13Z","abstract_excerpt":"Machine unlearning focuses on the computationally efficient removal of specific training data from trained models, ensuring that the influence of forgotten data is effectively eliminated without the need for full retraining. Despite advances in low-dimensional settings, where the number of parameters \\( p \\) is much smaller than the sample size \\( n \\), extending similar theoretical guarantees to high-dimensional regimes remains challenging. We propose an unlearning algorithm that starts from the original model parameters and performs a theory-guided sequence of Newton steps \\( T \\in \\{ 1,2\\}\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07640","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/2505.07640/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfCWmYvTu7GgqusGTF7+rot4LgipVCX14h+LbFYbBBfEOC0M0ua67A5d543o5T/t2aW5iIzuds9Za2ZDh+BTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:44:01.968376Z"},"content_sha256":"814bee707ceba7e38cbad3910061fdc37c4ffbc511ab61a49a237503c26e7552","schema_version":"1.0","event_id":"sha256:814bee707ceba7e38cbad3910061fdc37c4ffbc511ab61a49a237503c26e7552"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VBAM5367NVXCFUHWKFLIRHB3WJ/bundle.json","state_url":"https://pith.science/pith/VBAM5367NVXCFUHWKFLIRHB3WJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VBAM5367NVXCFUHWKFLIRHB3WJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T16:44:01Z","links":{"resolver":"https://pith.science/pith/VBAM5367NVXCFUHWKFLIRHB3WJ","bundle":"https://pith.science/pith/VBAM5367NVXCFUHWKFLIRHB3WJ/bundle.json","state":"https://pith.science/pith/VBAM5367NVXCFUHWKFLIRHB3WJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VBAM5367NVXCFUHWKFLIRHB3WJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VBAM5367NVXCFUHWKFLIRHB3WJ","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":"826eed508a8ea638aeba2dfb46ecf9a20276b581b9c79e6ed61741fcf9df1662","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T15:11:13Z","title_canon_sha256":"145229d2aa2088347c47f9fad33a18171dba95d09240ca244da2675dd060be68"},"schema_version":"1.0","source":{"id":"2505.07640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07640","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07640v1","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07640","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"VBAM5367NVXC","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"VBAM5367NVXCFUHW","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"VBAM5367","created_at":"2026-07-05T11:01:51Z"}],"graph_snapshots":[{"event_id":"sha256:814bee707ceba7e38cbad3910061fdc37c4ffbc511ab61a49a237503c26e7552","target":"graph","created_at":"2026-07-05T11:01:51Z","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/2505.07640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine unlearning focuses on the computationally efficient removal of specific training data from trained models, ensuring that the influence of forgotten data is effectively eliminated without the need for full retraining. Despite advances in low-dimensional settings, where the number of parameters \\( p \\) is much smaller than the sample size \\( n \\), extending similar theoretical guarantees to high-dimensional regimes remains challenging. We propose an unlearning algorithm that starts from the original model parameters and performs a theory-guided sequence of Newton steps \\( T \\in \\{ 1,2\\}\\","authors_text":"Arian Maleki, Arnab Auddy, Haolin Zou, Kamiar Rahnama Rad, Yongchan Kwon","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T15:11:13Z","title":"Certified Data Removal Under High-dimensional Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07640","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:a48f52585ea79d200acbcc7d2c00ff25ca296367ce5b9d20528442e6251ba6d8","target":"record","created_at":"2026-07-05T11:01:51Z","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":"826eed508a8ea638aeba2dfb46ecf9a20276b581b9c79e6ed61741fcf9df1662","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-12T15:11:13Z","title_canon_sha256":"145229d2aa2088347c47f9fad33a18171dba95d09240ca244da2675dd060be68"},"schema_version":"1.0","source":{"id":"2505.07640","kind":"arxiv","version":1}},"canonical_sha256":"a840ceefdf6d6e22d0f65156889c3bb270b8e19fc2ee1c178fe08511b0301b01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a840ceefdf6d6e22d0f65156889c3bb270b8e19fc2ee1c178fe08511b0301b01","first_computed_at":"2026-07-05T11:01:51.205142Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:51.205142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7L+avquFFeq8lg9pNrtMt8LuGrcMme2q0vb4bJJ53eMCCtbn4+82dRwgm2Lul4UMsS6KdHf8nBbERFOgo/AAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:51.205645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a48f52585ea79d200acbcc7d2c00ff25ca296367ce5b9d20528442e6251ba6d8","sha256:814bee707ceba7e38cbad3910061fdc37c4ffbc511ab61a49a237503c26e7552"],"state_sha256":"9e617fa50d854fbdc401e1df41d09062fe2bf9771a50379039fd8645faffa3ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/jnoHiaywR45hMcY0Oa6vqY8EYtsXiQLplCSrfB0yHtb4Ohook2tCFzN9OFUXXR8uFwYEX4p6+oxB/Ud4fbuDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:44:01.973159Z","bundle_sha256":"d390469e7df4ab174579b785d437c218299a341bee449934ecdfdcdb8faee9dd"}}