{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HV5ADZX43PEIUKFWRKLQDEEOBC","short_pith_number":"pith:HV5ADZX4","schema_version":"1.0","canonical_sha256":"3d7a01e6fcdbc88a28b68a9701908e088e33fce0e291fb4ebde3549609ccba35","source":{"kind":"arxiv","id":"2012.09720","version":3},"attestation_state":"computed","paper":{"title":"Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas","submitted_at":"2020-12-17T16:43:11Z","abstract_excerpt":"We study the problem of PAC learning halfspaces with Massart noise. Given labeled samples $(x, y)$ from a distribution $D$ on $\\mathbb{R}^{d} \\times \\{ \\pm 1\\}$ such that the marginal $D_x$ on the examples is arbitrary and the label $y$ of example $x$ is generated from the target halfspace corrupted by a Massart adversary with flipping probability $\\eta(x) \\leq \\eta \\leq 1/2$, the goal is to compute a hypothesis with small misclassification error. The best known $\\mathrm{poly}(d, 1/\\epsilon)$-time algorithms for this problem achieve error of $\\eta+\\epsilon$, which can be far from the optimal b"},"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":"2012.09720","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-17T16:43:11Z","cross_cats_sorted":["cs.CC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"cf9945ee53cb89ab4a6ef466696c66c50395272202a19927e3ac30f513a4b199","abstract_canon_sha256":"feb2b58df81f5e2b008a9f5685c503a5f39cb76a901e1f954d7b09f777ba7f42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:46.891760Z","signature_b64":"zt9SkBmaowHo7zS8QNrLkg0qb9yp3csC0QWQa5u4MfX/J0VLbMiyaeQ0YBFoHq7ZbxKGbLRO+ZgDAFIK1yJpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7a01e6fcdbc88a28b68a9701908e088e33fce0e291fb4ebde3549609ccba35","last_reissued_at":"2026-07-05T03:29:46.891360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:46.891360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Ilias Diakonikolas","submitted_at":"2020-12-17T16:43:11Z","abstract_excerpt":"We study the problem of PAC learning halfspaces with Massart noise. Given labeled samples $(x, y)$ from a distribution $D$ on $\\mathbb{R}^{d} \\times \\{ \\pm 1\\}$ such that the marginal $D_x$ on the examples is arbitrary and the label $y$ of example $x$ is generated from the target halfspace corrupted by a Massart adversary with flipping probability $\\eta(x) \\leq \\eta \\leq 1/2$, the goal is to compute a hypothesis with small misclassification error. The best known $\\mathrm{poly}(d, 1/\\epsilon)$-time algorithms for this problem achieve error of $\\eta+\\epsilon$, which can be far from the optimal b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09720","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/2012.09720/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":"2012.09720","created_at":"2026-07-05T03:29:46.891417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.09720v3","created_at":"2026-07-05T03:29:46.891417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09720","created_at":"2026-07-05T03:29:46.891417+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV5ADZX43PEI","created_at":"2026-07-05T03:29:46.891417+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV5ADZX43PEIUKFW","created_at":"2026-07-05T03:29:46.891417+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV5ADZX4","created_at":"2026-07-05T03:29:46.891417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09851","citing_title":"Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC","json":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC.json","graph_json":"https://pith.science/api/pith-number/HV5ADZX43PEIUKFWRKLQDEEOBC/graph.json","events_json":"https://pith.science/api/pith-number/HV5ADZX43PEIUKFWRKLQDEEOBC/events.json","paper":"https://pith.science/paper/HV5ADZX4"},"agent_actions":{"view_html":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC","download_json":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC.json","view_paper":"https://pith.science/paper/HV5ADZX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.09720&json=true","fetch_graph":"https://pith.science/api/pith-number/HV5ADZX43PEIUKFWRKLQDEEOBC/graph.json","fetch_events":"https://pith.science/api/pith-number/HV5ADZX43PEIUKFWRKLQDEEOBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC/action/storage_attestation","attest_author":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC/action/author_attestation","sign_citation":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC/action/citation_signature","submit_replication":"https://pith.science/pith/HV5ADZX43PEIUKFWRKLQDEEOBC/action/replication_record"}},"created_at":"2026-07-05T03:29:46.891417+00:00","updated_at":"2026-07-05T03:29:46.891417+00:00"}