{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RVAO3WRK6MTEA3RQASZBN65BMS","short_pith_number":"pith:RVAO3WRK","canonical_record":{"source":{"id":"2002.10077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T05:12:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e09abb2ea501dd5a1e3db8ac2e49e2e7b2c6ed00732276da7fb4d7b15cb6ce4e","abstract_canon_sha256":"a914c136e9423fe335c7ddb61241ef28b1ba51334bab3017ee8c5b1f1ce07a29"},"schema_version":"1.0"},"canonical_sha256":"8d40edda2af326406e3004b216fba164bfbfc1c55b47e1797be82602d2226cf4","source":{"kind":"arxiv","id":"2002.10077","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.10077","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2002.10077v2","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10077","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"RVAO3WRK6MTE","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"RVAO3WRK6MTEA3RQ","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"RVAO3WRK","created_at":"2026-07-05T02:17:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RVAO3WRK6MTEA3RQASZBN65BMS","target":"record","payload":{"canonical_record":{"source":{"id":"2002.10077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T05:12:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e09abb2ea501dd5a1e3db8ac2e49e2e7b2c6ed00732276da7fb4d7b15cb6ce4e","abstract_canon_sha256":"a914c136e9423fe335c7ddb61241ef28b1ba51334bab3017ee8c5b1f1ce07a29"},"schema_version":"1.0"},"canonical_sha256":"8d40edda2af326406e3004b216fba164bfbfc1c55b47e1797be82602d2226cf4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:20.376223Z","signature_b64":"jnMF19qkfrr4tfNgl9M6ua3IjPJNnC2NK4vfVEM+uV4mRsYH+5OnZslrW5ZG7zQoONNfx8J5Q5xChHCSZhjoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d40edda2af326406e3004b216fba164bfbfc1c55b47e1797be82602d2226cf4","last_reissued_at":"2026-07-05T02:17:20.375700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:20.375700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.10077","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5qG0TabGvg19POct0gEbBRavBHT3xpFxDZw8YUW5U/Oin+NqWunArDiWeFoe2uPi03OPnjS9pvUgppdFssUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:54.272116Z"},"content_sha256":"649c96d508d966107d5800827054e474fe585b83c221c2f7109581e6c378be9d","schema_version":"1.0","event_id":"sha256:649c96d508d966107d5800827054e474fe585b83c221c2f7109581e6c378be9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RVAO3WRK6MTEA3RQASZBN65BMS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Data Deletion from Machine Learning Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"James Zou, Kamalika Chaudhuri, Mary Anne Smart, Zachary Izzo","submitted_at":"2020-02-24T05:12:03Z","abstract_excerpt":"Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU's General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10077","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/2002.10077/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":"2026-07-05T02:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kkoTcLt1HKca6OdW/LNJLXPAYNNCk2aWoYMf5hR8zC7tmcgDVDja8jQp5Y0oqdv64d16ZgUxlkDJAeZNi0FQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:54.272641Z"},"content_sha256":"4bbad5cf00e6fe00a9fc6e80dd512f21429211655394d19b24ecf0156a2b24db","schema_version":"1.0","event_id":"sha256:4bbad5cf00e6fe00a9fc6e80dd512f21429211655394d19b24ecf0156a2b24db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVAO3WRK6MTEA3RQASZBN65BMS/bundle.json","state_url":"https://pith.science/pith/RVAO3WRK6MTEA3RQASZBN65BMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVAO3WRK6MTEA3RQASZBN65BMS/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":"2026-08-08T13:15:54Z","links":{"resolver":"https://pith.science/pith/RVAO3WRK6MTEA3RQASZBN65BMS","bundle":"https://pith.science/pith/RVAO3WRK6MTEA3RQASZBN65BMS/bundle.json","state":"https://pith.science/pith/RVAO3WRK6MTEA3RQASZBN65BMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVAO3WRK6MTEA3RQASZBN65BMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RVAO3WRK6MTEA3RQASZBN65BMS","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":"a914c136e9423fe335c7ddb61241ef28b1ba51334bab3017ee8c5b1f1ce07a29","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T05:12:03Z","title_canon_sha256":"e09abb2ea501dd5a1e3db8ac2e49e2e7b2c6ed00732276da7fb4d7b15cb6ce4e"},"schema_version":"1.0","source":{"id":"2002.10077","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.10077","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2002.10077v2","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10077","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"RVAO3WRK6MTE","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"RVAO3WRK6MTEA3RQ","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"RVAO3WRK","created_at":"2026-07-05T02:17:20Z"}],"graph_snapshots":[{"event_id":"sha256:4bbad5cf00e6fe00a9fc6e80dd512f21429211655394d19b24ecf0156a2b24db","target":"graph","created_at":"2026-07-05T02:17:20Z","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/2002.10077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU's General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature d","authors_text":"James Zou, Kamalika Chaudhuri, Mary Anne Smart, Zachary Izzo","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T05:12:03Z","title":"Approximate Data Deletion from Machine Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10077","kind":"arxiv","version":2},"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":"sha256:649c96d508d966107d5800827054e474fe585b83c221c2f7109581e6c378be9d","target":"record","created_at":"2026-07-05T02:17:20Z","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":"a914c136e9423fe335c7ddb61241ef28b1ba51334bab3017ee8c5b1f1ce07a29","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-24T05:12:03Z","title_canon_sha256":"e09abb2ea501dd5a1e3db8ac2e49e2e7b2c6ed00732276da7fb4d7b15cb6ce4e"},"schema_version":"1.0","source":{"id":"2002.10077","kind":"arxiv","version":2}},"canonical_sha256":"8d40edda2af326406e3004b216fba164bfbfc1c55b47e1797be82602d2226cf4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d40edda2af326406e3004b216fba164bfbfc1c55b47e1797be82602d2226cf4","first_computed_at":"2026-07-05T02:17:20.375700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:20.375700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jnMF19qkfrr4tfNgl9M6ua3IjPJNnC2NK4vfVEM+uV4mRsYH+5OnZslrW5ZG7zQoONNfx8J5Q5xChHCSZhjoDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:20.376223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.10077","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:649c96d508d966107d5800827054e474fe585b83c221c2f7109581e6c378be9d","sha256:4bbad5cf00e6fe00a9fc6e80dd512f21429211655394d19b24ecf0156a2b24db"],"state_sha256":"a912b234a69a130d973a26117bacacee12f33c97a90932c8cb4f2f2af40cd5fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kfbzPvWcNmwZ3SoFu2lZCgVg2owMv2DHXM5uoUnJMr+G+WhZAY4Qz+5uTnc68+U9imKOxVOD/BbvnhUAVQI5AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:54.277004Z","bundle_sha256":"196aa2bfa433a250884b95d48e681b47d587e8fb80ee77f4de0f5463d603282c"}}