{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VUL7WOY7UVR6FMS763J2ODF3UH","short_pith_number":"pith:VUL7WOY7","schema_version":"1.0","canonical_sha256":"ad17fb3b1fa563e2b25ff6d3a70cbba1e2b5cb1ff93d03a05ca7e96b34d1ff34","source":{"kind":"arxiv","id":"1803.03241","version":3},"attestation_state":"computed","paper":{"title":"Efficient Algorithms for Outlier-Robust Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Pravesh K. Kothari, Raghu Meka","submitted_at":"2018-03-08T18:30:31Z","abstract_excerpt":"We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels.\n  Given a sufficiently large (polynomial-size) training set drawn i.i.d. from distribution D and subsequently corrupted on some fraction of points, our algorithm outputs a linear function whose squared error is close to the squared error of the best-fitting linear function with respect to D, assuming that the marginal distribution of D over the input space is \\emph{certifiably hypercontractive}. This natural property is satisfied by many w"},"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":"1803.03241","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-08T18:30:31Z","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"title_canon_sha256":"f6511f1b8af1894101803c2f56c247c8aa2dd8b130bb1f427e32b38ffbc8ad52","abstract_canon_sha256":"0c971d827bb64c6a1c15c8a5b165999a30a85e71d5b395ce088f359fededac7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:47.912778Z","signature_b64":"xSIDg+OKCj14qqj2w/e9BZ7viSYBZ/waCMhGoGZlITTUFv0GJIt9muxUxxy0kvRaSD+JsGFZ6zWftlWyjZmBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad17fb3b1fa563e2b25ff6d3a70cbba1e2b5cb1ff93d03a05ca7e96b34d1ff34","last_reissued_at":"2026-07-05T01:07:47.912336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:47.912336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Algorithms for Outlier-Robust Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Klivans, Pravesh K. Kothari, Raghu Meka","submitted_at":"2018-03-08T18:30:31Z","abstract_excerpt":"We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels.\n  Given a sufficiently large (polynomial-size) training set drawn i.i.d. from distribution D and subsequently corrupted on some fraction of points, our algorithm outputs a linear function whose squared error is close to the squared error of the best-fitting linear function with respect to D, assuming that the marginal distribution of D over the input space is \\emph{certifiably hypercontractive}. This natural property is satisfied by many w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03241","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1803.03241/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":"1803.03241","created_at":"2026-07-05T01:07:47.912396+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03241v3","created_at":"2026-07-05T01:07:47.912396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03241","created_at":"2026-07-05T01:07:47.912396+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUL7WOY7UVR6","created_at":"2026-07-05T01:07:47.912396+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUL7WOY7UVR6FMS7","created_at":"2026-07-05T01:07:47.912396+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUL7WOY7","created_at":"2026-07-05T01:07:47.912396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00265","citing_title":"Outlier-Robust Training of Machine Learning Models","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH","json":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH.json","graph_json":"https://pith.science/api/pith-number/VUL7WOY7UVR6FMS763J2ODF3UH/graph.json","events_json":"https://pith.science/api/pith-number/VUL7WOY7UVR6FMS763J2ODF3UH/events.json","paper":"https://pith.science/paper/VUL7WOY7"},"agent_actions":{"view_html":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH","download_json":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH.json","view_paper":"https://pith.science/paper/VUL7WOY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03241&json=true","fetch_graph":"https://pith.science/api/pith-number/VUL7WOY7UVR6FMS763J2ODF3UH/graph.json","fetch_events":"https://pith.science/api/pith-number/VUL7WOY7UVR6FMS763J2ODF3UH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH/action/storage_attestation","attest_author":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH/action/author_attestation","sign_citation":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH/action/citation_signature","submit_replication":"https://pith.science/pith/VUL7WOY7UVR6FMS763J2ODF3UH/action/replication_record"}},"created_at":"2026-07-05T01:07:47.912396+00:00","updated_at":"2026-07-05T01:07:47.912396+00:00"}