{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HIXOM7G66YP42O6FINWYKZ5TKM","short_pith_number":"pith:HIXOM7G6","schema_version":"1.0","canonical_sha256":"3a2ee67cdef61fcd3bc5436d8567b3531e883603093e9b1707bf5256fe663682","source":{"kind":"arxiv","id":"2411.06697","version":1},"attestation_state":"computed","paper":{"title":"Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilias Diakonikolas, Jelena Diakonikolas, Shuyao Li, Sushrut Karmalkar","submitted_at":"2024-11-11T03:43:52Z","abstract_excerpt":"We study the problem of learning a single neuron with respect to the $L_2^2$-loss in the presence of adversarial distribution shifts, where the labels can be arbitrary, and the goal is to find a ``best-fit'' function. More precisely, given training samples from a reference distribution $\\mathcal{p}_0$, the goal is to approximate the vector $\\mathbf{w}^*$ which minimizes the squared loss with respect to the worst-case distribution that is close in $\\chi^2$-divergence to $\\mathcal{p}_{0}$. We design a computationally efficient algorithm that recovers a vector $ \\hat{\\mathbf{w}}$ satisfying $\\mat"},"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":"2411.06697","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-11T03:43:52Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"ae33ada405f5bbfa2f232af17a7f20c2058638016ce0cabbe85633b05c093bb4","abstract_canon_sha256":"b2d9a1853face2a1c3a4010f9aaf289ae145673d4ac7186d434f7863cc52f471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:50.225550Z","signature_b64":"1Lneu+kmczrwcK+apFBEfLxr9E0tMggIzlTOSMSCWfPoWlGf/8cAMFD6+pKHhWL6T2TUDuloCyYa+mhzranoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a2ee67cdef61fcd3bc5436d8567b3531e883603093e9b1707bf5256fe663682","last_reissued_at":"2026-07-05T09:33:50.225154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:50.225154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ilias Diakonikolas, Jelena Diakonikolas, Shuyao Li, Sushrut Karmalkar","submitted_at":"2024-11-11T03:43:52Z","abstract_excerpt":"We study the problem of learning a single neuron with respect to the $L_2^2$-loss in the presence of adversarial distribution shifts, where the labels can be arbitrary, and the goal is to find a ``best-fit'' function. More precisely, given training samples from a reference distribution $\\mathcal{p}_0$, the goal is to approximate the vector $\\mathbf{w}^*$ which minimizes the squared loss with respect to the worst-case distribution that is close in $\\chi^2$-divergence to $\\mathcal{p}_{0}$. We design a computationally efficient algorithm that recovers a vector $ \\hat{\\mathbf{w}}$ satisfying $\\mat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06697","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/2411.06697/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":"2411.06697","created_at":"2026-07-05T09:33:50.225212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06697v1","created_at":"2026-07-05T09:33:50.225212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06697","created_at":"2026-07-05T09:33:50.225212+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIXOM7G66YP4","created_at":"2026-07-05T09:33:50.225212+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIXOM7G66YP42O6F","created_at":"2026-07-05T09:33:50.225212+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIXOM7G6","created_at":"2026-07-05T09:33:50.225212+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/HIXOM7G66YP42O6FINWYKZ5TKM","json":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM.json","graph_json":"https://pith.science/api/pith-number/HIXOM7G66YP42O6FINWYKZ5TKM/graph.json","events_json":"https://pith.science/api/pith-number/HIXOM7G66YP42O6FINWYKZ5TKM/events.json","paper":"https://pith.science/paper/HIXOM7G6"},"agent_actions":{"view_html":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM","download_json":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM.json","view_paper":"https://pith.science/paper/HIXOM7G6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06697&json=true","fetch_graph":"https://pith.science/api/pith-number/HIXOM7G66YP42O6FINWYKZ5TKM/graph.json","fetch_events":"https://pith.science/api/pith-number/HIXOM7G66YP42O6FINWYKZ5TKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM/action/storage_attestation","attest_author":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM/action/author_attestation","sign_citation":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM/action/citation_signature","submit_replication":"https://pith.science/pith/HIXOM7G66YP42O6FINWYKZ5TKM/action/replication_record"}},"created_at":"2026-07-05T09:33:50.225212+00:00","updated_at":"2026-07-05T09:33:50.225212+00:00"}