{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UL3EMV6UOQIZBXRWY74CCUECVI","short_pith_number":"pith:UL3EMV6U","schema_version":"1.0","canonical_sha256":"a2f64657d4741190de36c7f8215082aa3d8e3ab6d9161778539dc9d89e0a3a4e","source":{"kind":"arxiv","id":"1703.04940","version":3},"attestation_state":"computed","paper":{"title":"Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Jacob Steinhardt, Moses Charikar","submitted_at":"2017-03-15T05:43:48Z","abstract_excerpt":"We introduce a criterion, resilience, which allows properties of a dataset (such as its mean or best low rank approximation) to be robustly computed, even in the presence of a large fraction of arbitrary additional data. Resilience is a weaker condition than most other properties considered so far in the literature, and yet enables robust estimation in a broader variety of settings. We provide new information-theoretic results on robust distribution learning, robust estimation of stochastic block models, and robust mean estimation under bounded $k$th moments. We also provide new algorithmic re"},"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":"1703.04940","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-15T05:43:48Z","cross_cats_sorted":["cs.AI","cs.CC","cs.CR","stat.ML"],"title_canon_sha256":"325d3245a17fad333cf75436cc23f587b302f12cfef8ef2d9a7cf5f75b416101","abstract_canon_sha256":"c696dbdcbff1ccfc0b0362c4ebebb755277a4d2668682111b3f7c4a50b06846f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:39.275984Z","signature_b64":"5Bx9f0gyxnZkRmwSSYTgqAw91R9+Je2Hb630nWXpL1jQs1fF85GyuG4gjbqvvxXmy5N2JTn1jCeVFHaBQAbADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f64657d4741190de36c7f8215082aa3d8e3ab6d9161778539dc9d89e0a3a4e","last_reissued_at":"2026-05-18T00:29:39.275556Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:39.275556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gregory Valiant, Jacob Steinhardt, Moses Charikar","submitted_at":"2017-03-15T05:43:48Z","abstract_excerpt":"We introduce a criterion, resilience, which allows properties of a dataset (such as its mean or best low rank approximation) to be robustly computed, even in the presence of a large fraction of arbitrary additional data. Resilience is a weaker condition than most other properties considered so far in the literature, and yet enables robust estimation in a broader variety of settings. We provide new information-theoretic results on robust distribution learning, robust estimation of stochastic block models, and robust mean estimation under bounded $k$th moments. We also provide new algorithmic re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.04940","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":""},"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":"1703.04940","created_at":"2026-05-18T00:29:39.275621+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.04940v3","created_at":"2026-05-18T00:29:39.275621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.04940","created_at":"2026-05-18T00:29:39.275621+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL3EMV6UOQIZ","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL3EMV6UOQIZBXRW","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL3EMV6U","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.00927","citing_title":"A Unified Approach to Robust Mean Estimation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23318","citing_title":"Generalized Rank Regression","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18042","citing_title":"On efficient robust regression with subquadratic samples","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI","json":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI.json","graph_json":"https://pith.science/api/pith-number/UL3EMV6UOQIZBXRWY74CCUECVI/graph.json","events_json":"https://pith.science/api/pith-number/UL3EMV6UOQIZBXRWY74CCUECVI/events.json","paper":"https://pith.science/paper/UL3EMV6U"},"agent_actions":{"view_html":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI","download_json":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI.json","view_paper":"https://pith.science/paper/UL3EMV6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.04940&json=true","fetch_graph":"https://pith.science/api/pith-number/UL3EMV6UOQIZBXRWY74CCUECVI/graph.json","fetch_events":"https://pith.science/api/pith-number/UL3EMV6UOQIZBXRWY74CCUECVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI/action/storage_attestation","attest_author":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI/action/author_attestation","sign_citation":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI/action/citation_signature","submit_replication":"https://pith.science/pith/UL3EMV6UOQIZBXRWY74CCUECVI/action/replication_record"}},"created_at":"2026-05-18T00:29:39.275621+00:00","updated_at":"2026-05-18T00:29:39.275621+00:00"}