{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2QQEJ4B3NG4MQGJG3HB7M62PFU","short_pith_number":"pith:2QQEJ4B3","schema_version":"1.0","canonical_sha256":"d42044f03b69b8c81926d9c3f67b4f2d2f941f9060e5134a97a771eb58653d16","source":{"kind":"arxiv","id":"2504.15812","version":1},"attestation_state":"computed","paper":{"title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Jinhang Zuo, John C.S. Lui, Mohammad Hajiesmaili, Qirun Zeng, Xuchuang Wang, Xutong Liu","submitted_at":"2025-04-22T11:51:20Z","abstract_excerpt":"This paper investigates the fusion of absolute (reward) and relative (dueling) feedback in stochastic bandits, where both feedback types are gathered in each decision round. We derive a regret lower bound, demonstrating that an efficient algorithm may incur only the smaller among the reward and dueling-based regret for each individual arm. We propose two fusion approaches: (1) a simple elimination fusion algorithm that leverages both feedback types to explore all arms and unifies collected information by sharing a common candidate arm set, and (2) a decomposition fusion algorithm that selects "},"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":"2504.15812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T11:51:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37407cb749d524d6ff6614fd5cb8c1e840fceeb4b182f406971011803e73058b","abstract_canon_sha256":"710aa2d8a591c90e126c086a4eab6536a6a38e37633ca9188c0b19beee6df6cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:30.379827Z","signature_b64":"jNmbCrTs8gAN+1aMpleqh0F5ruHO0/MFGLJppdz3tOFdZYTDWgUHl0O2CaYbCZpaHjKl0RoI4ZBSkiSmLHtnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d42044f03b69b8c81926d9c3f67b4f2d2f941f9060e5134a97a771eb58653d16","last_reissued_at":"2026-07-05T10:52:30.379344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:30.379344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fusing Reward and Dueling Feedback in Stochastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Jinhang Zuo, John C.S. Lui, Mohammad Hajiesmaili, Qirun Zeng, Xuchuang Wang, Xutong Liu","submitted_at":"2025-04-22T11:51:20Z","abstract_excerpt":"This paper investigates the fusion of absolute (reward) and relative (dueling) feedback in stochastic bandits, where both feedback types are gathered in each decision round. We derive a regret lower bound, demonstrating that an efficient algorithm may incur only the smaller among the reward and dueling-based regret for each individual arm. We propose two fusion approaches: (1) a simple elimination fusion algorithm that leverages both feedback types to explore all arms and unifies collected information by sharing a common candidate arm set, and (2) a decomposition fusion algorithm that selects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15812","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/2504.15812/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":"2504.15812","created_at":"2026-07-05T10:52:30.379408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15812v1","created_at":"2026-07-05T10:52:30.379408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15812","created_at":"2026-07-05T10:52:30.379408+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QQEJ4B3NG4M","created_at":"2026-07-05T10:52:30.379408+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QQEJ4B3NG4MQGJG","created_at":"2026-07-05T10:52:30.379408+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QQEJ4B3","created_at":"2026-07-05T10:52:30.379408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05745","citing_title":"Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU","json":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU.json","graph_json":"https://pith.science/api/pith-number/2QQEJ4B3NG4MQGJG3HB7M62PFU/graph.json","events_json":"https://pith.science/api/pith-number/2QQEJ4B3NG4MQGJG3HB7M62PFU/events.json","paper":"https://pith.science/paper/2QQEJ4B3"},"agent_actions":{"view_html":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU","download_json":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU.json","view_paper":"https://pith.science/paper/2QQEJ4B3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15812&json=true","fetch_graph":"https://pith.science/api/pith-number/2QQEJ4B3NG4MQGJG3HB7M62PFU/graph.json","fetch_events":"https://pith.science/api/pith-number/2QQEJ4B3NG4MQGJG3HB7M62PFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU/action/storage_attestation","attest_author":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU/action/author_attestation","sign_citation":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU/action/citation_signature","submit_replication":"https://pith.science/pith/2QQEJ4B3NG4MQGJG3HB7M62PFU/action/replication_record"}},"created_at":"2026-07-05T10:52:30.379408+00:00","updated_at":"2026-07-05T10:52:30.379408+00:00"}