{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DXZ452ZVIPOFQJYYLZ77GCKJGG","short_pith_number":"pith:DXZ452ZV","schema_version":"1.0","canonical_sha256":"1df3ceeb3543dc5827185e7ff3094931a9ef3011e3152b2449f3a95defd82181","source":{"kind":"arxiv","id":"2502.12528","version":2},"attestation_state":"computed","paper":{"title":"Contextual Linear Bandits with Delay as Payoff","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haipeng Luo, Mengxiao Zhang, Yingfei Wang","submitted_at":"2025-02-18T04:32:51Z","abstract_excerpt":"A recent work by Schlisselberg et al. (2024) studies a delay-as-payoff model for stochastic multi-armed bandits, where the payoff (either loss or reward) is delayed for a period that is proportional to the payoff itself. While this captures many real-world applications, the simple multi-armed bandit setting limits the practicality of their results. In this paper, we address this limitation by studying the delay-as-payoff model for contextual linear bandits. Specifically, we start from the case with a fixed action set and propose an efficient algorithm whose regret overhead compared to the stan"},"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":"2502.12528","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T04:32:51Z","cross_cats_sorted":[],"title_canon_sha256":"27f100b4508f097caa50caaa2d0cdd82ee27136a98de757cc911604d986aad8a","abstract_canon_sha256":"ed3f6252ac77a726356f6bf4c65ea6b45a7ecd5aeb3d10e90757804f7c73e7b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:18.083537Z","signature_b64":"WHLQQmsI++R1bSThUAxFu98yni5ZA6IPFSnDJsv5XPMH9Yy8j02Az3TrufbRR1BA3qE3Wd4xxF21upRFHvOQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1df3ceeb3543dc5827185e7ff3094931a9ef3011e3152b2449f3a95defd82181","last_reissued_at":"2026-07-05T10:17:18.083037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:18.083037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Linear Bandits with Delay as Payoff","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haipeng Luo, Mengxiao Zhang, Yingfei Wang","submitted_at":"2025-02-18T04:32:51Z","abstract_excerpt":"A recent work by Schlisselberg et al. (2024) studies a delay-as-payoff model for stochastic multi-armed bandits, where the payoff (either loss or reward) is delayed for a period that is proportional to the payoff itself. While this captures many real-world applications, the simple multi-armed bandit setting limits the practicality of their results. In this paper, we address this limitation by studying the delay-as-payoff model for contextual linear bandits. Specifically, we start from the case with a fixed action set and propose an efficient algorithm whose regret overhead compared to the stan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12528","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/2502.12528/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":"2502.12528","created_at":"2026-07-05T10:17:18.083107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12528v2","created_at":"2026-07-05T10:17:18.083107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12528","created_at":"2026-07-05T10:17:18.083107+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXZ452ZVIPOF","created_at":"2026-07-05T10:17:18.083107+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXZ452ZVIPOFQJYY","created_at":"2026-07-05T10:17:18.083107+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXZ452ZV","created_at":"2026-07-05T10:17:18.083107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20296","citing_title":"Online Survival Analysis: A Bandit Approach under Cox PH Model","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG","json":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG.json","graph_json":"https://pith.science/api/pith-number/DXZ452ZVIPOFQJYYLZ77GCKJGG/graph.json","events_json":"https://pith.science/api/pith-number/DXZ452ZVIPOFQJYYLZ77GCKJGG/events.json","paper":"https://pith.science/paper/DXZ452ZV"},"agent_actions":{"view_html":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG","download_json":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG.json","view_paper":"https://pith.science/paper/DXZ452ZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12528&json=true","fetch_graph":"https://pith.science/api/pith-number/DXZ452ZVIPOFQJYYLZ77GCKJGG/graph.json","fetch_events":"https://pith.science/api/pith-number/DXZ452ZVIPOFQJYYLZ77GCKJGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG/action/storage_attestation","attest_author":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG/action/author_attestation","sign_citation":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG/action/citation_signature","submit_replication":"https://pith.science/pith/DXZ452ZVIPOFQJYYLZ77GCKJGG/action/replication_record"}},"created_at":"2026-07-05T10:17:18.083107+00:00","updated_at":"2026-07-05T10:17:18.083107+00:00"}