{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UMEVFO3ZQCEGFLVALD5QALMA74","short_pith_number":"pith:UMEVFO3Z","canonical_record":{"source":{"id":"2201.06640","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T21:49:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bb92a2c4da98f9bdd61c9875c4b674b54cb2c7a3497f8c38338fd7774212288e","abstract_canon_sha256":"9ecf8c40a0688418022baac9130513b7cb10383d88106f2bb23915801da1da97"},"schema_version":"1.0"},"canonical_sha256":"a30952bb79808862aea058fb002d80ff3d377f73a4c586a4b39042c62bf6e52c","source":{"kind":"arxiv","id":"2201.06640","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06640","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06640v3","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06640","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"UMEVFO3ZQCEG","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"pith_short_16","alias_value":"UMEVFO3ZQCEGFLVA","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"pith_short_8","alias_value":"UMEVFO3Z","created_at":"2026-07-05T05:44:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UMEVFO3ZQCEGFLVALD5QALMA74","target":"record","payload":{"canonical_record":{"source":{"id":"2201.06640","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T21:49:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"bb92a2c4da98f9bdd61c9875c4b674b54cb2c7a3497f8c38338fd7774212288e","abstract_canon_sha256":"9ecf8c40a0688418022baac9130513b7cb10383d88106f2bb23915801da1da97"},"schema_version":"1.0"},"canonical_sha256":"a30952bb79808862aea058fb002d80ff3d377f73a4c586a4b39042c62bf6e52c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:37.279238Z","signature_b64":"6aVtJNqXLVx2vtCtADZFhVnWO0/azTptde/eR94O/0cMjjSDktPxiR39sZF1cT9uI+P3eItmoOp3OLlzktaoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30952bb79808862aea058fb002d80ff3d377f73a4c586a4b39042c62bf6e52c","last_reissued_at":"2026-07-05T05:44:37.278733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:37.278733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.06640","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5KnO8wXvFYJwwXPP38QlXl+RbQdHilKmWHsaVEj6udpqF04bde20a/B1GP7LkWHIDt1UNO8mfzoXRK25OWsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:01:12.896282Z"},"content_sha256":"607ae3f3f38c306943fbe69f36f445fe313073260ac38d668491d214f770c515","schema_version":"1.0","event_id":"sha256:607ae3f3f38c306943fbe69f36f445fe313073260ac38d668491d214f770c515"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UMEVFO3ZQCEGFLVALD5QALMA74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Adversarial Evaluations for Inexact Machine Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amartya Sanyal, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Ser-Nam Lim, Shashwat Goel","submitted_at":"2022-01-17T21:49:21Z","abstract_excerpt":"Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms.\n  In this work, we first outline some necessary criteria for evaluation methods and sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06640","kind":"arxiv","version":3},"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/2201.06640/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":"2026-07-05T05:44:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50zWaiWqrYc+FhyLPlGvM5IyuXaisOYh0Lpyv0ka3xwl8Z7NeOb5VrJ/1YopBPE0L0sW7QGCopIgINAUGeuLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:01:12.898606Z"},"content_sha256":"8b5d322dbad6f723ccbca8bad010ce0aff280336971adc6107ddb3b48bb79faa","schema_version":"1.0","event_id":"sha256:8b5d322dbad6f723ccbca8bad010ce0aff280336971adc6107ddb3b48bb79faa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UMEVFO3ZQCEGFLVALD5QALMA74/bundle.json","state_url":"https://pith.science/pith/UMEVFO3ZQCEGFLVALD5QALMA74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UMEVFO3ZQCEGFLVALD5QALMA74/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":"2026-08-08T04:01:12Z","links":{"resolver":"https://pith.science/pith/UMEVFO3ZQCEGFLVALD5QALMA74","bundle":"https://pith.science/pith/UMEVFO3ZQCEGFLVALD5QALMA74/bundle.json","state":"https://pith.science/pith/UMEVFO3ZQCEGFLVALD5QALMA74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UMEVFO3ZQCEGFLVALD5QALMA74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UMEVFO3ZQCEGFLVALD5QALMA74","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":"9ecf8c40a0688418022baac9130513b7cb10383d88106f2bb23915801da1da97","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T21:49:21Z","title_canon_sha256":"bb92a2c4da98f9bdd61c9875c4b674b54cb2c7a3497f8c38338fd7774212288e"},"schema_version":"1.0","source":{"id":"2201.06640","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.06640","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"arxiv_version","alias_value":"2201.06640v3","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06640","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"pith_short_12","alias_value":"UMEVFO3ZQCEG","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"pith_short_16","alias_value":"UMEVFO3ZQCEGFLVA","created_at":"2026-07-05T05:44:37Z"},{"alias_kind":"pith_short_8","alias_value":"UMEVFO3Z","created_at":"2026-07-05T05:44:37Z"}],"graph_snapshots":[{"event_id":"sha256:8b5d322dbad6f723ccbca8bad010ce0aff280336971adc6107ddb3b48bb79faa","target":"graph","created_at":"2026-07-05T05:44:37Z","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/2201.06640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of affected training data from a learned model. Achieving this task exactly is computationally expensive; consequently, recent works have proposed inexact unlearning algorithms to solve this approximately as well as evaluation methods to test the effectiveness of these algorithms.\n  In this work, we first outline some necessary criteria for evaluation methods and sh","authors_text":"Amartya Sanyal, Ameya Prabhu, Philip Torr, Ponnurangam Kumaraguru, Ser-Nam Lim, Shashwat Goel","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T21:49:21Z","title":"Towards Adversarial Evaluations for Inexact Machine Unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06640","kind":"arxiv","version":3},"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":"sha256:607ae3f3f38c306943fbe69f36f445fe313073260ac38d668491d214f770c515","target":"record","created_at":"2026-07-05T05:44:37Z","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":"9ecf8c40a0688418022baac9130513b7cb10383d88106f2bb23915801da1da97","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-17T21:49:21Z","title_canon_sha256":"bb92a2c4da98f9bdd61c9875c4b674b54cb2c7a3497f8c38338fd7774212288e"},"schema_version":"1.0","source":{"id":"2201.06640","kind":"arxiv","version":3}},"canonical_sha256":"a30952bb79808862aea058fb002d80ff3d377f73a4c586a4b39042c62bf6e52c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a30952bb79808862aea058fb002d80ff3d377f73a4c586a4b39042c62bf6e52c","first_computed_at":"2026-07-05T05:44:37.278733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:37.278733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6aVtJNqXLVx2vtCtADZFhVnWO0/azTptde/eR94O/0cMjjSDktPxiR39sZF1cT9uI+P3eItmoOp3OLlzktaoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:37.279238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.06640","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:607ae3f3f38c306943fbe69f36f445fe313073260ac38d668491d214f770c515","sha256:8b5d322dbad6f723ccbca8bad010ce0aff280336971adc6107ddb3b48bb79faa"],"state_sha256":"1fe6346e86aeec2ee448c78cfc6418bee6bf290b53977dde2130f42fc083e12f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvLHG+s7tHmognN3085GxgkO6ZKAcK1lOqCXyhwKU07MSbAs0gQ7SH5zmvOLo1HLLKFctqcIrPSukpNL8TWbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:01:12.910018Z","bundle_sha256":"ac513dc1b6506fbfc9348160b723f30fa7c541095d350a9f0ca0045acbe3818b"}}