{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FVY2LVLNEYEVNU4OJDO3IKS43G","short_pith_number":"pith:FVY2LVLN","schema_version":"1.0","canonical_sha256":"2d71a5d56d260956d38e48ddb42a5cd9aaf06cde6cb3d284a7af6571f65e2ca4","source":{"kind":"arxiv","id":"2006.16200","version":1},"attestation_state":"computed","paper":{"title":"Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas, Nikos Zarifis","submitted_at":"2020-06-29T17:10:10Z","abstract_excerpt":"We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. In the former problem, given labeled examples $(\\mathbf{x}, y)$ from an unknown distribution on $\\mathbb{R}^d \\times \\{ \\pm 1\\}$, whose marginal distribution on $\\mathbf{x}$ is the standard Gaussian and the labels $y$ can be arbitrary, the goal is to output a hypothesis with 0-1 loss $\\mathrm{OPT}+\\epsilon$, where $\\mathrm{OPT}$ is the 0-1 loss of the best-fitting halfspace. In the latter problem, given labeled examples $(\\mathbf{x}, y)$ from an unknown distribution on $\\mathbb{R}^d \\times"},"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":"2006.16200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:10:10Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"67b0f8f3bf62198b2a91e8144fdb387c5cf1296057ca9aeddb308532613b89f8","abstract_canon_sha256":"3e43515ab78fce2a0e99094e4d76a16b8a05fb3b2ac82384bbbd33e37e840fff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:13.334901Z","signature_b64":"Au9ZvQZcJVVbFC16WWD0VME+biJYGcawAe8YlqAoq+HB95Hz1iZeFn0/VE6I3Efa0RX/vOGDqhY9NWbCeAVyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d71a5d56d260956d38e48ddb42a5cd9aaf06cde6cb3d284a7af6571f65e2ca4","last_reissued_at":"2026-07-05T01:14:13.334492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:13.334492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas, Nikos Zarifis","submitted_at":"2020-06-29T17:10:10Z","abstract_excerpt":"We study the fundamental problems of agnostically learning halfspaces and ReLUs under Gaussian marginals. In the former problem, given labeled examples $(\\mathbf{x}, y)$ from an unknown distribution on $\\mathbb{R}^d \\times \\{ \\pm 1\\}$, whose marginal distribution on $\\mathbf{x}$ is the standard Gaussian and the labels $y$ can be arbitrary, the goal is to output a hypothesis with 0-1 loss $\\mathrm{OPT}+\\epsilon$, where $\\mathrm{OPT}$ is the 0-1 loss of the best-fitting halfspace. In the latter problem, given labeled examples $(\\mathbf{x}, y)$ from an unknown distribution on $\\mathbb{R}^d \\times"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16200","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/2006.16200/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":"2006.16200","created_at":"2026-07-05T01:14:13.334552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16200v1","created_at":"2026-07-05T01:14:13.334552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16200","created_at":"2026-07-05T01:14:13.334552+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVY2LVLNEYEV","created_at":"2026-07-05T01:14:13.334552+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVY2LVLNEYEVNU4O","created_at":"2026-07-05T01:14:13.334552+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVY2LVLN","created_at":"2026-07-05T01:14:13.334552+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/FVY2LVLNEYEVNU4OJDO3IKS43G","json":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G.json","graph_json":"https://pith.science/api/pith-number/FVY2LVLNEYEVNU4OJDO3IKS43G/graph.json","events_json":"https://pith.science/api/pith-number/FVY2LVLNEYEVNU4OJDO3IKS43G/events.json","paper":"https://pith.science/paper/FVY2LVLN"},"agent_actions":{"view_html":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G","download_json":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G.json","view_paper":"https://pith.science/paper/FVY2LVLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16200&json=true","fetch_graph":"https://pith.science/api/pith-number/FVY2LVLNEYEVNU4OJDO3IKS43G/graph.json","fetch_events":"https://pith.science/api/pith-number/FVY2LVLNEYEVNU4OJDO3IKS43G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G/action/storage_attestation","attest_author":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G/action/author_attestation","sign_citation":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G/action/citation_signature","submit_replication":"https://pith.science/pith/FVY2LVLNEYEVNU4OJDO3IKS43G/action/replication_record"}},"created_at":"2026-07-05T01:14:13.334552+00:00","updated_at":"2026-07-05T01:14:13.334552+00:00"}