{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TVWQAFHC3PXPAHHPBFCI6PRVCZ","short_pith_number":"pith:TVWQAFHC","schema_version":"1.0","canonical_sha256":"9d6d0014e2dbeef01cef09448f3e3516774f4b862e185fffea05c07848547157","source":{"kind":"arxiv","id":"1811.01715","version":1},"attestation_state":"computed","paper":{"title":"Multi-armed Bandits with Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Longbo Huang, Siwei Wang","submitted_at":"2018-11-05T14:24:46Z","abstract_excerpt":"We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for $T$ steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receives a stochastic reward associated with the arm. In order to incentivize players to explore other arms, the controller provides a proper payment compensation to players. The objective of the controller is to maximize the total reward collected by players while minimizing the compe"},"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":"1811.01715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T14:24:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ebc458eeb3d5c841bcb49d96b2992e0b669436319c0fe09aa7d6ea27b4a055d0","abstract_canon_sha256":"7a86676a90a036938d0dd55c4df66887d8a1fdd2d1c9f45028015efdf64f96ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:33.487182Z","signature_b64":"W+ZJ4KJ0xjzsmDESkD9phRsltUlvKidSm25sw6ryGBHjw5yT0f2BjCIfmz0lUOBmWAT2h+rhcPc9bugza159DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d6d0014e2dbeef01cef09448f3e3516774f4b862e185fffea05c07848547157","last_reissued_at":"2026-05-18T00:01:33.486691Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:33.486691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-armed Bandits with Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Longbo Huang, Siwei Wang","submitted_at":"2018-11-05T14:24:46Z","abstract_excerpt":"We propose and study the known-compensation multi-arm bandit (KCMAB) problem, where a system controller offers a set of arms to many short-term players for $T$ steps. In each step, one short-term player arrives to the system. Upon arrival, the player aims to select an arm with the current best average reward and receives a stochastic reward associated with the arm. In order to incentivize players to explore other arms, the controller provides a proper payment compensation to players. The objective of the controller is to maximize the total reward collected by players while minimizing the compe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01715","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":""},"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":"1811.01715","created_at":"2026-05-18T00:01:33.486778+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01715v1","created_at":"2026-05-18T00:01:33.486778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01715","created_at":"2026-05-18T00:01:33.486778+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVWQAFHC3PXP","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVWQAFHC3PXPAHHP","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVWQAFHC","created_at":"2026-05-18T12:32:56.356000+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/TVWQAFHC3PXPAHHPBFCI6PRVCZ","json":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ.json","graph_json":"https://pith.science/api/pith-number/TVWQAFHC3PXPAHHPBFCI6PRVCZ/graph.json","events_json":"https://pith.science/api/pith-number/TVWQAFHC3PXPAHHPBFCI6PRVCZ/events.json","paper":"https://pith.science/paper/TVWQAFHC"},"agent_actions":{"view_html":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ","download_json":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ.json","view_paper":"https://pith.science/paper/TVWQAFHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01715&json=true","fetch_graph":"https://pith.science/api/pith-number/TVWQAFHC3PXPAHHPBFCI6PRVCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TVWQAFHC3PXPAHHPBFCI6PRVCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/action/storage_attestation","attest_author":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/action/author_attestation","sign_citation":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/action/citation_signature","submit_replication":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/action/replication_record"}},"created_at":"2026-05-18T00:01:33.486778+00:00","updated_at":"2026-05-18T00:01:33.486778+00:00"}