{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQTZHDISXQ3GSBANEJFFUN43C3","short_pith_number":"pith:CQTZHDIS","schema_version":"1.0","canonical_sha256":"1427938d12bc3669040d224a5a379b16c712fa366c09518f52b67ab879786c9c","source":{"kind":"arxiv","id":"2601.18115","version":2},"attestation_state":"computed","paper":{"title":"Robust Learning of a Group DRO Neuron","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Guyang Cao, Jelena Diakonikolas, Shuyao Li, Sushrut Karmalkar","submitted_at":"2026-01-26T04:00:53Z","abstract_excerpt":"We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional shifts, for a broad family of covariate distributions. Our goal is to identify a ''best-fit'' neuron parameterized by $\\mathbf{w}_*$ that performs well under the most challenging reweighting of the groups. Specifically, we address a Group Distributionally Robust Optimization problem: given sample access to $K$ distinct distributions $\\mathcal p_{[1]},\\dots,\\mathcal p_{[K]}$, we seek to approximate $\\mathbf{w}_*$ that minimizes the worst-case objec"},"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":"2601.18115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T04:00:53Z","cross_cats_sorted":["cs.DS","math.OC"],"title_canon_sha256":"6d1ad4ef03bfa8f5b702c74f9a5af97017c6c7d303848a71467e96a5d53f0526","abstract_canon_sha256":"e8e4cf29942576a8eb7cdf63908ae16022b9265c1be89a1eb6731932d277bee4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:13.443449Z","signature_b64":"k8m5IB3q2Pycc+vadupcnjcVPsDTo0u/Pew8GmKN+NoLMSujMCyoIx78g5dNnX1v94HbSaW2RxYO83kuisDhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1427938d12bc3669040d224a5a379b16c712fa366c09518f52b67ab879786c9c","last_reissued_at":"2026-06-02T02:04:13.442955Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:13.442955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Learning of a Group DRO Neuron","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Guyang Cao, Jelena Diakonikolas, Shuyao Li, Sushrut Karmalkar","submitted_at":"2026-01-26T04:00:53Z","abstract_excerpt":"We study the problem of learning a single neuron under standard squared loss in the presence of arbitrary label noise and group-level distributional shifts, for a broad family of covariate distributions. Our goal is to identify a ''best-fit'' neuron parameterized by $\\mathbf{w}_*$ that performs well under the most challenging reweighting of the groups. Specifically, we address a Group Distributionally Robust Optimization problem: given sample access to $K$ distinct distributions $\\mathcal p_{[1]},\\dots,\\mathcal p_{[K]}$, we seek to approximate $\\mathbf{w}_*$ that minimizes the worst-case objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18115","kind":"arxiv","version":2},"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/2601.18115/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":"2601.18115","created_at":"2026-06-02T02:04:13.443016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18115v2","created_at":"2026-06-02T02:04:13.443016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18115","created_at":"2026-06-02T02:04:13.443016+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQTZHDISXQ3G","created_at":"2026-06-02T02:04:13.443016+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQTZHDISXQ3GSBAN","created_at":"2026-06-02T02:04:13.443016+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQTZHDIS","created_at":"2026-06-02T02:04:13.443016+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/CQTZHDISXQ3GSBANEJFFUN43C3","json":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3.json","graph_json":"https://pith.science/api/pith-number/CQTZHDISXQ3GSBANEJFFUN43C3/graph.json","events_json":"https://pith.science/api/pith-number/CQTZHDISXQ3GSBANEJFFUN43C3/events.json","paper":"https://pith.science/paper/CQTZHDIS"},"agent_actions":{"view_html":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3","download_json":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3.json","view_paper":"https://pith.science/paper/CQTZHDIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18115&json=true","fetch_graph":"https://pith.science/api/pith-number/CQTZHDISXQ3GSBANEJFFUN43C3/graph.json","fetch_events":"https://pith.science/api/pith-number/CQTZHDISXQ3GSBANEJFFUN43C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3/action/storage_attestation","attest_author":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3/action/author_attestation","sign_citation":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3/action/citation_signature","submit_replication":"https://pith.science/pith/CQTZHDISXQ3GSBANEJFFUN43C3/action/replication_record"}},"created_at":"2026-06-02T02:04:13.443016+00:00","updated_at":"2026-06-02T02:04:13.443016+00:00"}