{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TVWQAFHC3PXPAHHPBFCI6PRVCZ","short_pith_number":"pith:TVWQAFHC","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"},"canonical_sha256":"9d6d0014e2dbeef01cef09448f3e3516774f4b862e185fffea05c07848547157","source":{"kind":"arxiv","id":"1811.01715","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01715","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01715v1","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01715","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"TVWQAFHC3PXP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TVWQAFHC3PXPAHHP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TVWQAFHC","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TVWQAFHC3PXPAHHPBFCI6PRVCZ","target":"record","payload":{"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"},"canonical_sha256":"9d6d0014e2dbeef01cef09448f3e3516774f4b862e185fffea05c07848547157","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"},"source_kind":"arxiv","source_id":"1811.01715","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kz0bdjtUvWhRCKt3P0jcTYuVyKGdEz7uuKD8Urd1wtmVVbr2PqjHphv5+QhMQsEaHLFwzZMW/nDIvnPvriZQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:43:33.627286Z"},"content_sha256":"79f896f7fc96b67fadeeb13fe5788accd0a87effbac67e2d01542d9d8623e1a0","schema_version":"1.0","event_id":"sha256:79f896f7fc96b67fadeeb13fe5788accd0a87effbac67e2d01542d9d8623e1a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TVWQAFHC3PXPAHHPBFCI6PRVCZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:01:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NtCCT6flmLMjphBA1YBDyMTU6spuVlKkEXbTePn/8SbWwoVjLUlGdCJ2hoAMSbJRKIwSXnX43nXAqciHpk0eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:43:33.627791Z"},"content_sha256":"0a255927badcdbe5e40b5d7794d2bfd40e5b2b151ddce58aaf16c00e9f81446e","schema_version":"1.0","event_id":"sha256:0a255927badcdbe5e40b5d7794d2bfd40e5b2b151ddce58aaf16c00e9f81446e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/bundle.json","state_url":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T14:43:33Z","links":{"resolver":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ","bundle":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/bundle.json","state":"https://pith.science/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVWQAFHC3PXPAHHPBFCI6PRVCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TVWQAFHC3PXPAHHPBFCI6PRVCZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7a86676a90a036938d0dd55c4df66887d8a1fdd2d1c9f45028015efdf64f96ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T14:24:46Z","title_canon_sha256":"ebc458eeb3d5c841bcb49d96b2992e0b669436319c0fe09aa7d6ea27b4a055d0"},"schema_version":"1.0","source":{"id":"1811.01715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01715","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01715v1","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01715","created_at":"2026-05-18T00:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"TVWQAFHC3PXP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TVWQAFHC3PXPAHHP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TVWQAFHC","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:0a255927badcdbe5e40b5d7794d2bfd40e5b2b151ddce58aaf16c00e9f81446e","target":"graph","created_at":"2026-05-18T00:01:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Longbo Huang, Siwei Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T14:24:46Z","title":"Multi-armed Bandits with Compensation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01715","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:79f896f7fc96b67fadeeb13fe5788accd0a87effbac67e2d01542d9d8623e1a0","target":"record","created_at":"2026-05-18T00:01:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7a86676a90a036938d0dd55c4df66887d8a1fdd2d1c9f45028015efdf64f96ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T14:24:46Z","title_canon_sha256":"ebc458eeb3d5c841bcb49d96b2992e0b669436319c0fe09aa7d6ea27b4a055d0"},"schema_version":"1.0","source":{"id":"1811.01715","kind":"arxiv","version":1}},"canonical_sha256":"9d6d0014e2dbeef01cef09448f3e3516774f4b862e185fffea05c07848547157","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d6d0014e2dbeef01cef09448f3e3516774f4b862e185fffea05c07848547157","first_computed_at":"2026-05-18T00:01:33.486691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:33.486691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W+ZJ4KJ0xjzsmDESkD9phRsltUlvKidSm25sw6ryGBHjw5yT0f2BjCIfmz0lUOBmWAT2h+rhcPc9bugza159DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:33.487182Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79f896f7fc96b67fadeeb13fe5788accd0a87effbac67e2d01542d9d8623e1a0","sha256:0a255927badcdbe5e40b5d7794d2bfd40e5b2b151ddce58aaf16c00e9f81446e"],"state_sha256":"eff18b7f03323bc1a87c0f8c3c2d07a3b119be229309fac9f243d8269ee090fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/TR2dyXOhy5WnAIEonxdoYkDPHh7kfl5vz5ujOq+eJXcW5Q+L8GTfxAOJtUhlpMBsDmd7F8g4YNWHgUi27mvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T14:43:33.629927Z","bundle_sha256":"57809d5c00397f34f6e6a44bdce760aaaa60668ecd97cab84fa5caf2c558237e"}}