{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WFXGBP5QE5B6JFGHLBOFPD44YO","short_pith_number":"pith:WFXGBP5Q","schema_version":"1.0","canonical_sha256":"b16e60bfb02743e494c7585c578f9cc39e648f67f72b76e32ed7cc5fee8fa9bb","source":{"kind":"arxiv","id":"2410.13548","version":2},"attestation_state":"computed","paper":{"title":"Adaptive and oblivious statistical adversaries are equivalent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","cs.DS"],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Guy Blanc","submitted_at":"2024-10-17T13:42:56Z","abstract_excerpt":"We resolve a fundamental question about the ability to perform a statistical task, such as learning, when an adversary corrupts the sample. Such adversaries are specified by the types of corruption they can make and their level of knowledge about the sample. The latter distinguishes between sample-adaptive adversaries which know the contents of the sample when choosing the corruption, and sample-oblivious adversaries, which do not. We prove that for all types of corruptions, sample-adaptive and sample-oblivious adversaries are \\emph{equivalent} up to polynomial factors in the sample size. This"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.13548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T13:42:56Z","cross_cats_sorted":["cs.CC","cs.DS"],"title_canon_sha256":"6b2f7468d0d4392153c74cdc19df4cff643e286252c06a6a95169f07229e0997","abstract_canon_sha256":"577e5eb3e347a7873b822c3220f7636a53840fe5d194e7e3c936640225573cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:55.199913Z","signature_b64":"SuWQtw+7+AtvciCP29P5TfM1gjL4B2TOZQJt1oKAKHhIeUklla/3T0dwwJjq0uo75HPl8QvBZ97W15VjJ5dMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b16e60bfb02743e494c7585c578f9cc39e648f67f72b76e32ed7cc5fee8fa9bb","last_reissued_at":"2026-07-05T12:01:55.199373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:55.199373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive and oblivious statistical adversaries are equivalent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","cs.DS"],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Guy Blanc","submitted_at":"2024-10-17T13:42:56Z","abstract_excerpt":"We resolve a fundamental question about the ability to perform a statistical task, such as learning, when an adversary corrupts the sample. Such adversaries are specified by the types of corruption they can make and their level of knowledge about the sample. The latter distinguishes between sample-adaptive adversaries which know the contents of the sample when choosing the corruption, and sample-oblivious adversaries, which do not. We prove that for all types of corruptions, sample-adaptive and sample-oblivious adversaries are \\emph{equivalent} up to polynomial factors in the sample size. This"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13548","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/2410.13548/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.13548","created_at":"2026-07-05T12:01:55.199444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13548v2","created_at":"2026-07-05T12:01:55.199444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13548","created_at":"2026-07-05T12:01:55.199444+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFXGBP5QE5B6","created_at":"2026-07-05T12:01:55.199444+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFXGBP5QE5B6JFGH","created_at":"2026-07-05T12:01:55.199444+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFXGBP5Q","created_at":"2026-07-05T12:01:55.199444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05137","citing_title":"On the Learnability of Distribution Classes with Adaptive Adversaries","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO","json":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO.json","graph_json":"https://pith.science/api/pith-number/WFXGBP5QE5B6JFGHLBOFPD44YO/graph.json","events_json":"https://pith.science/api/pith-number/WFXGBP5QE5B6JFGHLBOFPD44YO/events.json","paper":"https://pith.science/paper/WFXGBP5Q"},"agent_actions":{"view_html":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO","download_json":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO.json","view_paper":"https://pith.science/paper/WFXGBP5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13548&json=true","fetch_graph":"https://pith.science/api/pith-number/WFXGBP5QE5B6JFGHLBOFPD44YO/graph.json","fetch_events":"https://pith.science/api/pith-number/WFXGBP5QE5B6JFGHLBOFPD44YO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO/action/storage_attestation","attest_author":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO/action/author_attestation","sign_citation":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO/action/citation_signature","submit_replication":"https://pith.science/pith/WFXGBP5QE5B6JFGHLBOFPD44YO/action/replication_record"}},"created_at":"2026-07-05T12:01:55.199444+00:00","updated_at":"2026-07-05T12:01:55.199444+00:00"}