{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O5Z2HKDOAOMUCD6HKRKD4D6XX4","short_pith_number":"pith:O5Z2HKDO","canonical_record":{"source":{"id":"2210.06516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-10-12T18:18:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"33a37699f17254a74515b8a7fb5fcb84abe586a9d8ada6974da18110df5c60aa","abstract_canon_sha256":"8aac0fb8c24131eb0467dfb96dbf72a814e66d45d4c84977eac5d42445adc947"},"schema_version":"1.0"},"canonical_sha256":"7773a3a86e0399410fc754543e0fd7bf3dd5ca17408105fd9f2002df89bc902d","source":{"kind":"arxiv","id":"2210.06516","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06516","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06516v2","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06516","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"O5Z2HKDOAOMU","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"O5Z2HKDOAOMUCD6H","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"O5Z2HKDO","created_at":"2026-07-05T06:16:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O5Z2HKDOAOMUCD6HKRKD4D6XX4","target":"record","payload":{"canonical_record":{"source":{"id":"2210.06516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-10-12T18:18:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"33a37699f17254a74515b8a7fb5fcb84abe586a9d8ada6974da18110df5c60aa","abstract_canon_sha256":"8aac0fb8c24131eb0467dfb96dbf72a814e66d45d4c84977eac5d42445adc947"},"schema_version":"1.0"},"canonical_sha256":"7773a3a86e0399410fc754543e0fd7bf3dd5ca17408105fd9f2002df89bc902d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:00.702648Z","signature_b64":"ENCLdm5IlfhWf2eIYn3CKIv1eqk0Lu6Pg/yRl54vqSaFCYof/XFzhJ48oWMvGPa9WleaV0JhntxKBqJCbp/eBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7773a3a86e0399410fc754543e0fd7bf3dd5ca17408105fd9f2002df89bc902d","last_reissued_at":"2026-07-05T06:16:00.702194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:00.702194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.06516","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":"2026-07-05T06:16:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZKUra4+pZzxZCTaMdLoJ4lQGyPwYUia22NokmhVYpng3XnRwH14XRSE0h6CA1INGpvItttp7f4IVTyo4RbC+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:52:27.180274Z"},"content_sha256":"84487c580eb8673bf0bb0ac783c5ad92539595b1d90a0ef0c6333fa86eabf8c3","schema_version":"1.0","event_id":"sha256:84487c580eb8673bf0bb0ac783c5ad92539595b1d90a0ef0c6333fa86eabf8c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O5Z2HKDOAOMUCD6HKRKD4D6XX4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Himanshu Jahagirdar, Lingjuan Lyu, Ming Jin, Minzhou Pan, Ruoxi Jia, Yi Zeng","submitted_at":"2022-10-12T18:18:21Z","abstract_excerpt":"Given the volume of data needed to train modern machine learning models, external suppliers are increasingly used. However, incorporating external data poses data poisoning risks, wherein attackers manipulate their data to degrade model utility or integrity. Most poisoning defenses presume access to a set of clean data (or base set). While this assumption has been taken for granted, given the fast-growing research on stealthy poisoning attacks, a question arises: can defenders really identify a clean subset within a contaminated dataset to support defenses?\n  This paper starts by examining the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06516","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/2210.06516/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":"2026-07-05T06:16:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPdNdEWZLqVFyu3fiu7wDWM4s3I9N42LvotMFM4IZaJ8c3ThADZJvadYX+IaE1IlFtenCghWB+u6df/nNoOnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:52:27.181137Z"},"content_sha256":"366dd5f9ecdffc5851068bddfb8df1630132f85eaee8ce281f32016cb5e8deb6","schema_version":"1.0","event_id":"sha256:366dd5f9ecdffc5851068bddfb8df1630132f85eaee8ce281f32016cb5e8deb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4/bundle.json","state_url":"https://pith.science/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4/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":"2026-08-19T17:52:27Z","links":{"resolver":"https://pith.science/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4","bundle":"https://pith.science/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4/bundle.json","state":"https://pith.science/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5Z2HKDOAOMUCD6HKRKD4D6XX4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O5Z2HKDOAOMUCD6HKRKD4D6XX4","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":"8aac0fb8c24131eb0467dfb96dbf72a814e66d45d4c84977eac5d42445adc947","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-10-12T18:18:21Z","title_canon_sha256":"33a37699f17254a74515b8a7fb5fcb84abe586a9d8ada6974da18110df5c60aa"},"schema_version":"1.0","source":{"id":"2210.06516","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06516","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06516v2","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06516","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"O5Z2HKDOAOMU","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"O5Z2HKDOAOMUCD6H","created_at":"2026-07-05T06:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"O5Z2HKDO","created_at":"2026-07-05T06:16:00Z"}],"graph_snapshots":[{"event_id":"sha256:366dd5f9ecdffc5851068bddfb8df1630132f85eaee8ce281f32016cb5e8deb6","target":"graph","created_at":"2026-07-05T06:16:00Z","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/2210.06516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given the volume of data needed to train modern machine learning models, external suppliers are increasingly used. However, incorporating external data poses data poisoning risks, wherein attackers manipulate their data to degrade model utility or integrity. Most poisoning defenses presume access to a set of clean data (or base set). While this assumption has been taken for granted, given the fast-growing research on stealthy poisoning attacks, a question arises: can defenders really identify a clean subset within a contaminated dataset to support defenses?\n  This paper starts by examining the","authors_text":"Himanshu Jahagirdar, Lingjuan Lyu, Ming Jin, Minzhou Pan, Ruoxi Jia, Yi Zeng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-10-12T18:18:21Z","title":"How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06516","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":"sha256:84487c580eb8673bf0bb0ac783c5ad92539595b1d90a0ef0c6333fa86eabf8c3","target":"record","created_at":"2026-07-05T06:16:00Z","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":"8aac0fb8c24131eb0467dfb96dbf72a814e66d45d4c84977eac5d42445adc947","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2022-10-12T18:18:21Z","title_canon_sha256":"33a37699f17254a74515b8a7fb5fcb84abe586a9d8ada6974da18110df5c60aa"},"schema_version":"1.0","source":{"id":"2210.06516","kind":"arxiv","version":2}},"canonical_sha256":"7773a3a86e0399410fc754543e0fd7bf3dd5ca17408105fd9f2002df89bc902d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7773a3a86e0399410fc754543e0fd7bf3dd5ca17408105fd9f2002df89bc902d","first_computed_at":"2026-07-05T06:16:00.702194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:00.702194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ENCLdm5IlfhWf2eIYn3CKIv1eqk0Lu6Pg/yRl54vqSaFCYof/XFzhJ48oWMvGPa9WleaV0JhntxKBqJCbp/eBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:00.702648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06516","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84487c580eb8673bf0bb0ac783c5ad92539595b1d90a0ef0c6333fa86eabf8c3","sha256:366dd5f9ecdffc5851068bddfb8df1630132f85eaee8ce281f32016cb5e8deb6"],"state_sha256":"8c3be69197f0ef8ed3b185112fec2bb0c327b4a3eb27206aac06f1f638f45d9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O94odeyljTxhAwc//UZy/iP7vauWGLv5argbJE6iLwmtNJadZQLNldIp7OEdi9wS9VwmS/DUpgXJMGnWyS7MDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:52:27.187364Z","bundle_sha256":"d2b15e5f36d9a955e111d9c9727eed9948eed27da4eddee344d25ebd3050f1f0"}}