{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H6Z74G3REVTOLIHIHQP7CP246T","short_pith_number":"pith:H6Z74G3R","schema_version":"1.0","canonical_sha256":"3fb3fe1b712566e5a0e83c1ff13f5cf4d93817f20fc4e262e098dae52229c851","source":{"kind":"arxiv","id":"2202.05453","version":1},"attestation_state":"computed","paper":{"title":"Robust estimation algorithms don't need to know the corruption level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Orlitsky, Ayush Jain, Vaishakh Ravindrakumar","submitted_at":"2022-02-11T05:18:28Z","abstract_excerpt":"Real data are rarely pure. Hence the past half-century has seen great interest in robust estimation algorithms that perform well even when part of the data is corrupt. However, their vast majority approach optimal accuracy only when given a tight upper bound on the fraction of corrupt data. Such bounds are not available in practice, resulting in weak guarantees and often poor performance. This brief note abstracts the complex and pervasive robustness problem into a simple geometric puzzle. It then applies the puzzle's solution to derive a universal meta technique that converts any robust estim"},"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":"2202.05453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-11T05:18:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a9a78ab612e5876d276bd69eed311da4b4fd94114dd37221089a31152ae8126e","abstract_canon_sha256":"d5f1d44dbf0e496aa8a08e5629623c594c070fc0cc041b53932a238f40f64258"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:08.353919Z","signature_b64":"pU3rNQKkkkQ/2q7PCUGQQalpwic4vm6L9kfQxxjeBVxITKeqXlCa9s7ymuCrNzYTsu+h3x0H1yUjK2bpQEADCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fb3fe1b712566e5a0e83c1ff13f5cf4d93817f20fc4e262e098dae52229c851","last_reissued_at":"2026-07-05T03:56:08.353449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:08.353449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust estimation algorithms don't need to know the corruption level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Orlitsky, Ayush Jain, Vaishakh Ravindrakumar","submitted_at":"2022-02-11T05:18:28Z","abstract_excerpt":"Real data are rarely pure. Hence the past half-century has seen great interest in robust estimation algorithms that perform well even when part of the data is corrupt. However, their vast majority approach optimal accuracy only when given a tight upper bound on the fraction of corrupt data. Such bounds are not available in practice, resulting in weak guarantees and often poor performance. This brief note abstracts the complex and pervasive robustness problem into a simple geometric puzzle. It then applies the puzzle's solution to derive a universal meta technique that converts any robust estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.05453","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/2202.05453/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":"2202.05453","created_at":"2026-07-05T03:56:08.353508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.05453v1","created_at":"2026-07-05T03:56:08.353508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.05453","created_at":"2026-07-05T03:56:08.353508+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6Z74G3REVTO","created_at":"2026-07-05T03:56:08.353508+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6Z74G3REVTOLIHI","created_at":"2026-07-05T03:56:08.353508+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6Z74G3R","created_at":"2026-07-05T03:56:08.353508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09737","citing_title":"Online change point detection under heavy-tailedness and contamination","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T","json":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T.json","graph_json":"https://pith.science/api/pith-number/H6Z74G3REVTOLIHIHQP7CP246T/graph.json","events_json":"https://pith.science/api/pith-number/H6Z74G3REVTOLIHIHQP7CP246T/events.json","paper":"https://pith.science/paper/H6Z74G3R"},"agent_actions":{"view_html":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T","download_json":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T.json","view_paper":"https://pith.science/paper/H6Z74G3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.05453&json=true","fetch_graph":"https://pith.science/api/pith-number/H6Z74G3REVTOLIHIHQP7CP246T/graph.json","fetch_events":"https://pith.science/api/pith-number/H6Z74G3REVTOLIHIHQP7CP246T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T/action/storage_attestation","attest_author":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T/action/author_attestation","sign_citation":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T/action/citation_signature","submit_replication":"https://pith.science/pith/H6Z74G3REVTOLIHIHQP7CP246T/action/replication_record"}},"created_at":"2026-07-05T03:56:08.353508+00:00","updated_at":"2026-07-05T03:56:08.353508+00:00"}