{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EPEC5X6PBLTSMRDJ3PEK3UNFYL","short_pith_number":"pith:EPEC5X6P","schema_version":"1.0","canonical_sha256":"23c82edfcf0ae7264469dbc8add1a5c2de1f120944a041572cd69498d2e35403","source":{"kind":"arxiv","id":"2508.16992","version":1},"attestation_state":"computed","paper":{"title":"Online Learning for Approximately-Convex Functions with Long-term Adversarial Constraints","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Abhishek Sinha, Dhruv Sarkar, Samrat Mukhopadhyay","submitted_at":"2025-08-23T11:21:24Z","abstract_excerpt":"We study an online learning problem with long-term budget constraints in the adversarial setting. In this problem, at each round $t$, the learner selects an action from a convex decision set, after which the adversary reveals a cost function $f_t$ and a resource consumption function $g_t$. The cost and consumption functions are assumed to be $\\alpha$-approximately convex - a broad class that generalizes convexity and encompasses many common non-convex optimization problems, including DR-submodular maximization, Online Vertex Cover, and Regularized Phase Retrieval. The goal is to design an onli"},"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":"2508.16992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T11:21:24Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c089c7e2be77a16edf9dff9a88fda62363da06e19b01f11bfc185b4a5489431f","abstract_canon_sha256":"ad368861d6d623360836ce03907b7a372d4ac5e63a35cc5a84d2cb5f484fa562"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:07.827936Z","signature_b64":"Kr3R+r81brKqrd9ta20h52SYiOuiJP4iLQbun8QxrHQQ2gUYjbRvzrSfovOx7MNeEYKHXr3+OQn74yJjYqaKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23c82edfcf0ae7264469dbc8add1a5c2de1f120944a041572cd69498d2e35403","last_reissued_at":"2026-07-05T11:58:07.827424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:07.827424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning for Approximately-Convex Functions with Long-term Adversarial Constraints","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Abhishek Sinha, Dhruv Sarkar, Samrat Mukhopadhyay","submitted_at":"2025-08-23T11:21:24Z","abstract_excerpt":"We study an online learning problem with long-term budget constraints in the adversarial setting. In this problem, at each round $t$, the learner selects an action from a convex decision set, after which the adversary reveals a cost function $f_t$ and a resource consumption function $g_t$. The cost and consumption functions are assumed to be $\\alpha$-approximately convex - a broad class that generalizes convexity and encompasses many common non-convex optimization problems, including DR-submodular maximization, Online Vertex Cover, and Regularized Phase Retrieval. The goal is to design an onli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16992","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/2508.16992/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":"2508.16992","created_at":"2026-07-05T11:58:07.827472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16992v1","created_at":"2026-07-05T11:58:07.827472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16992","created_at":"2026-07-05T11:58:07.827472+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPEC5X6PBLTS","created_at":"2026-07-05T11:58:07.827472+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPEC5X6PBLTSMRDJ","created_at":"2026-07-05T11:58:07.827472+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPEC5X6P","created_at":"2026-07-05T11:58:07.827472+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/EPEC5X6PBLTSMRDJ3PEK3UNFYL","json":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL.json","graph_json":"https://pith.science/api/pith-number/EPEC5X6PBLTSMRDJ3PEK3UNFYL/graph.json","events_json":"https://pith.science/api/pith-number/EPEC5X6PBLTSMRDJ3PEK3UNFYL/events.json","paper":"https://pith.science/paper/EPEC5X6P"},"agent_actions":{"view_html":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL","download_json":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL.json","view_paper":"https://pith.science/paper/EPEC5X6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16992&json=true","fetch_graph":"https://pith.science/api/pith-number/EPEC5X6PBLTSMRDJ3PEK3UNFYL/graph.json","fetch_events":"https://pith.science/api/pith-number/EPEC5X6PBLTSMRDJ3PEK3UNFYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL/action/storage_attestation","attest_author":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL/action/author_attestation","sign_citation":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL/action/citation_signature","submit_replication":"https://pith.science/pith/EPEC5X6PBLTSMRDJ3PEK3UNFYL/action/replication_record"}},"created_at":"2026-07-05T11:58:07.827472+00:00","updated_at":"2026-07-05T11:58:07.827472+00:00"}