{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3GIY2XGOSCJVO7MUU3UGCHJZUA","short_pith_number":"pith:3GIY2XGO","schema_version":"1.0","canonical_sha256":"d9918d5cce9093577d94a6e8611d39a00b2dfb4a3ee5559a31e45b109bcec46c","source":{"kind":"arxiv","id":"2506.12781","version":1},"attestation_state":"computed","paper":{"title":"Unconstrained Robust Online Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ashok Cutkosky, Jiujia Zhang","submitted_at":"2025-06-15T09:21:15Z","abstract_excerpt":"This paper addresses online learning with ``corrupted'' feedback. Our learner is provided with potentially corrupted gradients $\\tilde g_t$ instead of the ``true'' gradients $g_t$. We make no assumptions about how the corruptions arise: they could be the result of outliers, mislabeled data, or even malicious interference. We focus on the difficult ``unconstrained'' setting in which our algorithm must maintain low regret with respect to any comparison point $u \\in \\mathbb{R}^d$. The unconstrained setting is significantly more challenging as existing algorithms suffer extremely high regret even "},"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":"2506.12781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T09:21:15Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"f63b0e47dc249d15bc300d406e50f4a86470440c676bfc7ffb1b6ae396e6be14","abstract_canon_sha256":"cedb1fa99df18a7b40258354ef30020b8f1490711ebac09149d1c6c74e0311aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:59.877544Z","signature_b64":"J34icXlgFHa9U37Mv1FQOrS2Wm4QfSMrsoJNQTeGa4SjkBYU9mj7wKawQFRGHTnTzn0oq0IdzaOltG6Hhj2hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9918d5cce9093577d94a6e8611d39a00b2dfb4a3ee5559a31e45b109bcec46c","last_reissued_at":"2026-07-05T11:21:59.877090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:59.877090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unconstrained Robust Online Convex Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ashok Cutkosky, Jiujia Zhang","submitted_at":"2025-06-15T09:21:15Z","abstract_excerpt":"This paper addresses online learning with ``corrupted'' feedback. Our learner is provided with potentially corrupted gradients $\\tilde g_t$ instead of the ``true'' gradients $g_t$. We make no assumptions about how the corruptions arise: they could be the result of outliers, mislabeled data, or even malicious interference. We focus on the difficult ``unconstrained'' setting in which our algorithm must maintain low regret with respect to any comparison point $u \\in \\mathbb{R}^d$. The unconstrained setting is significantly more challenging as existing algorithms suffer extremely high regret even "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12781","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/2506.12781/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":"2506.12781","created_at":"2026-07-05T11:21:59.877146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12781v1","created_at":"2026-07-05T11:21:59.877146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12781","created_at":"2026-07-05T11:21:59.877146+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GIY2XGOSCJV","created_at":"2026-07-05T11:21:59.877146+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GIY2XGOSCJVO7MU","created_at":"2026-07-05T11:21:59.877146+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GIY2XGO","created_at":"2026-07-05T11:21:59.877146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20515","citing_title":"Online Conformal Prediction with Corrupted Feedback","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA","json":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA.json","graph_json":"https://pith.science/api/pith-number/3GIY2XGOSCJVO7MUU3UGCHJZUA/graph.json","events_json":"https://pith.science/api/pith-number/3GIY2XGOSCJVO7MUU3UGCHJZUA/events.json","paper":"https://pith.science/paper/3GIY2XGO"},"agent_actions":{"view_html":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA","download_json":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA.json","view_paper":"https://pith.science/paper/3GIY2XGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12781&json=true","fetch_graph":"https://pith.science/api/pith-number/3GIY2XGOSCJVO7MUU3UGCHJZUA/graph.json","fetch_events":"https://pith.science/api/pith-number/3GIY2XGOSCJVO7MUU3UGCHJZUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA/action/storage_attestation","attest_author":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA/action/author_attestation","sign_citation":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA/action/citation_signature","submit_replication":"https://pith.science/pith/3GIY2XGOSCJVO7MUU3UGCHJZUA/action/replication_record"}},"created_at":"2026-07-05T11:21:59.877146+00:00","updated_at":"2026-07-05T11:21:59.877146+00:00"}