{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HW7YJKGCZJJURLMIBJZLYXXEMY","short_pith_number":"pith:HW7YJKGC","schema_version":"1.0","canonical_sha256":"3dbf84a8c2ca5348ad880a72bc5ee4660357c6482efff1b57eaa23772f03ac52","source":{"kind":"arxiv","id":"2302.06512","version":1},"attestation_state":"computed","paper":{"title":"Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas, Lisheng Ren","submitted_at":"2023-02-13T16:46:23Z","abstract_excerpt":"We study the task of agnostically learning halfspaces under the Gaussian distribution. Specifically, given labeled examples $(\\mathbf{x},y)$ from an unknown distribution on $\\mathbb{R}^n \\times \\{ \\pm 1\\}$, 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. We prove a near-optimal computational hardness result for this task, under the widely believed sub-exponential time hardness of the Learning with"},"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":"2302.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T16:46:23Z","cross_cats_sorted":["cs.CC","cs.DS"],"title_canon_sha256":"bf4ae6e75be6c9a38ba8f1ba5c963f32cc813b8d0560686921ffbb5fa4f851f4","abstract_canon_sha256":"6a6df085454b9ec408710e9979149070d6d440ef9e62101ace34c7c9ed1390d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:11.817583Z","signature_b64":"xQnfjj++W6Q/33FjPTp3wcve3ktEiYSHta0HIWlQgOMgH9iEUtdBALpr/DPm/xNLI1bFXXSJR+a1V5bCPZcVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dbf84a8c2ca5348ad880a72bc5ee4660357c6482efff1b57eaa23772f03ac52","last_reissued_at":"2026-07-05T05:41:11.817177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:11.817177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.DS"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas, Lisheng Ren","submitted_at":"2023-02-13T16:46:23Z","abstract_excerpt":"We study the task of agnostically learning halfspaces under the Gaussian distribution. Specifically, given labeled examples $(\\mathbf{x},y)$ from an unknown distribution on $\\mathbb{R}^n \\times \\{ \\pm 1\\}$, 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. We prove a near-optimal computational hardness result for this task, under the widely believed sub-exponential time hardness of the Learning with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06512","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/2302.06512/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":"2302.06512","created_at":"2026-07-05T05:41:11.817234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06512v1","created_at":"2026-07-05T05:41:11.817234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06512","created_at":"2026-07-05T05:41:11.817234+00:00"},{"alias_kind":"pith_short_12","alias_value":"HW7YJKGCZJJU","created_at":"2026-07-05T05:41:11.817234+00:00"},{"alias_kind":"pith_short_16","alias_value":"HW7YJKGCZJJURLMI","created_at":"2026-07-05T05:41:11.817234+00:00"},{"alias_kind":"pith_short_8","alias_value":"HW7YJKGC","created_at":"2026-07-05T05:41:11.817234+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/HW7YJKGCZJJURLMIBJZLYXXEMY","json":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY.json","graph_json":"https://pith.science/api/pith-number/HW7YJKGCZJJURLMIBJZLYXXEMY/graph.json","events_json":"https://pith.science/api/pith-number/HW7YJKGCZJJURLMIBJZLYXXEMY/events.json","paper":"https://pith.science/paper/HW7YJKGC"},"agent_actions":{"view_html":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY","download_json":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY.json","view_paper":"https://pith.science/paper/HW7YJKGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06512&json=true","fetch_graph":"https://pith.science/api/pith-number/HW7YJKGCZJJURLMIBJZLYXXEMY/graph.json","fetch_events":"https://pith.science/api/pith-number/HW7YJKGCZJJURLMIBJZLYXXEMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY/action/storage_attestation","attest_author":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY/action/author_attestation","sign_citation":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY/action/citation_signature","submit_replication":"https://pith.science/pith/HW7YJKGCZJJURLMIBJZLYXXEMY/action/replication_record"}},"created_at":"2026-07-05T05:41:11.817234+00:00","updated_at":"2026-07-05T05:41:11.817234+00:00"}