{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3CRT7A2J2KTXTYCPBERADYSNVU","short_pith_number":"pith:3CRT7A2J","canonical_record":{"source":{"id":"2504.13610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-18T10:31:44Z","cross_cats_sorted":[],"title_canon_sha256":"b5b49abec402ff766cf074ff666c56cfc4e081579918b51e0e08dea660e9628e","abstract_canon_sha256":"fd1d46532bf4c23368373827b6ac078cb1573f4989a75ad5b107d857b244942c"},"schema_version":"1.0"},"canonical_sha256":"d8a33f8349d2a779e04f092201e24dad3a5086c5bab94350b8e09a933f76f58f","source":{"kind":"arxiv","id":"2504.13610","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13610","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13610v1","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13610","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"3CRT7A2J2KTX","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"3CRT7A2J2KTXTYCP","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"3CRT7A2J","created_at":"2026-07-05T10:50:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3CRT7A2J2KTXTYCPBERADYSNVU","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-18T10:31:44Z","cross_cats_sorted":[],"title_canon_sha256":"b5b49abec402ff766cf074ff666c56cfc4e081579918b51e0e08dea660e9628e","abstract_canon_sha256":"fd1d46532bf4c23368373827b6ac078cb1573f4989a75ad5b107d857b244942c"},"schema_version":"1.0"},"canonical_sha256":"d8a33f8349d2a779e04f092201e24dad3a5086c5bab94350b8e09a933f76f58f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:59.120542Z","signature_b64":"p07yzi2jB4FkkxdeqJU7JXW5Q9rnI+BhO0DOG12+Z+etFZqEQnQ1uIb5cXSDFiITDFZk0brGLjQ8SXqFQQXXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a33f8349d2a779e04f092201e24dad3a5086c5bab94350b8e09a933f76f58f","last_reissued_at":"2026-07-05T10:50:59.120058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:59.120058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13610","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":"2026-07-05T10:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n44Lf1pVk+LxjOTxWIIV8FRKb14FS4dOmi/OWjipww2Z+n3W0t4KUmiuGtgO8sdlHcAwBln0jFmc7KURcxGPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:42.213630Z"},"content_sha256":"7091bc58dee80f13267bdadd301443092418b54d8213f797d839ca4543f01104","schema_version":"1.0","event_id":"sha256:7091bc58dee80f13267bdadd301443092418b54d8213f797d839ca4543f01104"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3CRT7A2J2KTXTYCPBERADYSNVU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fairness and Robustness in Machine Unlearning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Khoa Tran, Simon S. Woo","submitted_at":"2025-04-18T10:31:44Z","abstract_excerpt":"Machine unlearning poses the challenge of ``how to eliminate the influence of specific data from a pretrained model'' in regard to privacy concerns. While prior research on approximated unlearning has demonstrated accuracy and efficiency in time complexity, we claim that it falls short of achieving exact unlearning, and we are the first to focus on fairness and robustness in machine unlearning algorithms. Our study presents fairness Conjectures for a well-trained model, based on the variance-bias trade-off characteristic, and considers their relevance to robustness. Our Conjectures are support"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13610","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/2504.13610/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":"2026-07-05T10:50:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oTQUPHb/wc4MO+G3asNh9dhTRCAtdDFoBqF3kkoWDcnH9YjetG8ucLPsfBQfjg517xzJu+0QcBy9Luh23bI0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:57:42.214137Z"},"content_sha256":"b7bc4aa36c62e216646c20a16f46e019b85514dd175658cc4eb1db6f39c142d7","schema_version":"1.0","event_id":"sha256:b7bc4aa36c62e216646c20a16f46e019b85514dd175658cc4eb1db6f39c142d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CRT7A2J2KTXTYCPBERADYSNVU/bundle.json","state_url":"https://pith.science/pith/3CRT7A2J2KTXTYCPBERADYSNVU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CRT7A2J2KTXTYCPBERADYSNVU/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":"2026-08-08T16:57:42Z","links":{"resolver":"https://pith.science/pith/3CRT7A2J2KTXTYCPBERADYSNVU","bundle":"https://pith.science/pith/3CRT7A2J2KTXTYCPBERADYSNVU/bundle.json","state":"https://pith.science/pith/3CRT7A2J2KTXTYCPBERADYSNVU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CRT7A2J2KTXTYCPBERADYSNVU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3CRT7A2J2KTXTYCPBERADYSNVU","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":"fd1d46532bf4c23368373827b6ac078cb1573f4989a75ad5b107d857b244942c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-18T10:31:44Z","title_canon_sha256":"b5b49abec402ff766cf074ff666c56cfc4e081579918b51e0e08dea660e9628e"},"schema_version":"1.0","source":{"id":"2504.13610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13610","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13610v1","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13610","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_12","alias_value":"3CRT7A2J2KTX","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_16","alias_value":"3CRT7A2J2KTXTYCP","created_at":"2026-07-05T10:50:59Z"},{"alias_kind":"pith_short_8","alias_value":"3CRT7A2J","created_at":"2026-07-05T10:50:59Z"}],"graph_snapshots":[{"event_id":"sha256:b7bc4aa36c62e216646c20a16f46e019b85514dd175658cc4eb1db6f39c142d7","target":"graph","created_at":"2026-07-05T10:50:59Z","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/2504.13610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine unlearning poses the challenge of ``how to eliminate the influence of specific data from a pretrained model'' in regard to privacy concerns. While prior research on approximated unlearning has demonstrated accuracy and efficiency in time complexity, we claim that it falls short of achieving exact unlearning, and we are the first to focus on fairness and robustness in machine unlearning algorithms. Our study presents fairness Conjectures for a well-trained model, based on the variance-bias trade-off characteristic, and considers their relevance to robustness. Our Conjectures are support","authors_text":"Khoa Tran, Simon S. Woo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-18T10:31:44Z","title":"Fairness and Robustness in Machine Unlearning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13610","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":"sha256:7091bc58dee80f13267bdadd301443092418b54d8213f797d839ca4543f01104","target":"record","created_at":"2026-07-05T10:50:59Z","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":"fd1d46532bf4c23368373827b6ac078cb1573f4989a75ad5b107d857b244942c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-18T10:31:44Z","title_canon_sha256":"b5b49abec402ff766cf074ff666c56cfc4e081579918b51e0e08dea660e9628e"},"schema_version":"1.0","source":{"id":"2504.13610","kind":"arxiv","version":1}},"canonical_sha256":"d8a33f8349d2a779e04f092201e24dad3a5086c5bab94350b8e09a933f76f58f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8a33f8349d2a779e04f092201e24dad3a5086c5bab94350b8e09a933f76f58f","first_computed_at":"2026-07-05T10:50:59.120058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:59.120058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p07yzi2jB4FkkxdeqJU7JXW5Q9rnI+BhO0DOG12+Z+etFZqEQnQ1uIb5cXSDFiITDFZk0brGLjQ8SXqFQQXXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:59.120542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7091bc58dee80f13267bdadd301443092418b54d8213f797d839ca4543f01104","sha256:b7bc4aa36c62e216646c20a16f46e019b85514dd175658cc4eb1db6f39c142d7"],"state_sha256":"2c01a14257b7dadef69bdb4d36f2d9bcbf11d24ac417f82c6e2dbfc02421b1c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/trU2bXmhlVQvSqUsTkzgvc+ZWHIdmwPKI3B9bS0wWExczq5YB6mRNheOLbbZERIZeOgYlw5EMVNr9OYfgd8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:57:42.217905Z","bundle_sha256":"79aadd29be309aeaa15fe4c2663de85b6cdf6829c573e699cfd5a914c77b151b"}}