{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4GQ2WYK7PH7IIVQL7ZVGV6DAQA","short_pith_number":"pith:4GQ2WYK7","schema_version":"1.0","canonical_sha256":"e1a1ab615f79fe84560bfe6a6af860800ad0922232b19dcefc58505e3a822d08","source":{"kind":"arxiv","id":"1506.04257","version":1},"attestation_state":"computed","paper":{"title":"Contamination Estimation via Convex Relaxations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","math.OC"],"primary_cat":"cs.IT","authors_text":"Matthew L. Malloy, Paul Barford, Scott Alfeld","submitted_at":"2015-06-13T11:51:52Z","abstract_excerpt":"Identifying anomalies and contamination in datasets is important in a wide variety of settings. In this paper, we describe a new technique for estimating contamination in large, discrete valued datasets. Our approach considers the normal condition of the data to be specified by a model consisting of a set of distributions. Our key contribution is in our approach to contamination estimation. Specifically, we develop a technique that identifies the minimum number of data points that must be discarded (i.e., the level of contamination) from an empirical data set in order to match the model to wit"},"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":"1506.04257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2015-06-13T11:51:52Z","cross_cats_sorted":["cs.LG","math.IT","math.OC"],"title_canon_sha256":"023265be0fbd20a5b3e8bf54bd74850787f692c1a02414695e3714882c41b22a","abstract_canon_sha256":"ba22329ddd396a4d7e5b8c6096b533125aa6107ea6bfdf8d49c0e35a3a684ed8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:49:55.116619Z","signature_b64":"kz+BXw7WCmsykSg/I3xN3qyqm8P4Hq04ErCs2n9UX1LWLjYLtG0KFZ4a/hNq+ixBY49SEtpjnmcQOCTDBWBlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1a1ab615f79fe84560bfe6a6af860800ad0922232b19dcefc58505e3a822d08","last_reissued_at":"2026-05-18T01:49:55.116117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:49:55.116117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contamination Estimation via Convex Relaxations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.IT","math.OC"],"primary_cat":"cs.IT","authors_text":"Matthew L. Malloy, Paul Barford, Scott Alfeld","submitted_at":"2015-06-13T11:51:52Z","abstract_excerpt":"Identifying anomalies and contamination in datasets is important in a wide variety of settings. In this paper, we describe a new technique for estimating contamination in large, discrete valued datasets. Our approach considers the normal condition of the data to be specified by a model consisting of a set of distributions. Our key contribution is in our approach to contamination estimation. Specifically, we develop a technique that identifies the minimum number of data points that must be discarded (i.e., the level of contamination) from an empirical data set in order to match the model to wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.04257","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":""},"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":"1506.04257","created_at":"2026-05-18T01:49:55.116191+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.04257v1","created_at":"2026-05-18T01:49:55.116191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.04257","created_at":"2026-05-18T01:49:55.116191+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GQ2WYK7PH7I","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GQ2WYK7PH7IIVQL","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GQ2WYK7","created_at":"2026-05-18T12:29:05.191682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA","json":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA.json","graph_json":"https://pith.science/api/pith-number/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/graph.json","events_json":"https://pith.science/api/pith-number/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/events.json","paper":"https://pith.science/paper/4GQ2WYK7"},"agent_actions":{"view_html":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA","download_json":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA.json","view_paper":"https://pith.science/paper/4GQ2WYK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.04257&json=true","fetch_graph":"https://pith.science/api/pith-number/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/graph.json","fetch_events":"https://pith.science/api/pith-number/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/action/storage_attestation","attest_author":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/action/author_attestation","sign_citation":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/action/citation_signature","submit_replication":"https://pith.science/pith/4GQ2WYK7PH7IIVQL7ZVGV6DAQA/action/replication_record"}},"created_at":"2026-05-18T01:49:55.116191+00:00","updated_at":"2026-05-18T01:49:55.116191+00:00"}