{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:Q2CAILP5BWHHGICEYQUFL4ZO2I","short_pith_number":"pith:Q2CAILP5","canonical_record":{"source":{"id":"2111.03290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-05T06:50:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca762def59fcd2ea95723fe93f7f40edcf40a9af8844db6def55af264e36b2d2","abstract_canon_sha256":"3cad17e53a9366abc5859e70026f9c145db65387d8ed7233c8a6de945ddc8d35"},"schema_version":"1.0"},"canonical_sha256":"8684042dfd0d8e732044c42855f32ed22a457891c9d70bc5b77aae8ae3bebfee","source":{"kind":"arxiv","id":"2111.03290","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03290","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03290v2","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03290","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"Q2CAILP5BWHH","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"Q2CAILP5BWHHGICE","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"Q2CAILP5","created_at":"2026-07-05T04:02:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:Q2CAILP5BWHHGICEYQUFL4ZO2I","target":"record","payload":{"canonical_record":{"source":{"id":"2111.03290","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-05T06:50:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca762def59fcd2ea95723fe93f7f40edcf40a9af8844db6def55af264e36b2d2","abstract_canon_sha256":"3cad17e53a9366abc5859e70026f9c145db65387d8ed7233c8a6de945ddc8d35"},"schema_version":"1.0"},"canonical_sha256":"8684042dfd0d8e732044c42855f32ed22a457891c9d70bc5b77aae8ae3bebfee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:20.632248Z","signature_b64":"hKRB23AKefjqk0ZOLabKj7ux0Yc2cJh4L0Yip16IhFhnv54xwUMmc+Fg0RxIHZ/dQyVdcEAn5Pax38Q/cwKgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8684042dfd0d8e732044c42855f32ed22a457891c9d70bc5b77aae8ae3bebfee","last_reissued_at":"2026-07-05T04:02:20.631814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:20.631814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.03290","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSF6cnFNP9EEPntHoFMsOqBY/zjXI1y0xF4K9SvXWB26G8mQw50yy56Z/CnEqRHXkOoNv0uqUFJVmSNy9Md5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:16:14.486202Z"},"content_sha256":"8404d7e4761f423a50d4ac1b9ce8a2a1f5fc0728a9f82c7a1e5e5b5d2d70cbd1","schema_version":"1.0","event_id":"sha256:8404d7e4761f423a50d4ac1b9ce8a2a1f5fc0728a9f82c7a1e5e5b5d2d70cbd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:Q2CAILP5BWHHGICEYQUFL4ZO2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maillard Sampling: Boltzmann Exploration Done Optimally","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jie Bian, Kwang-Sung Jun","submitted_at":"2021-11-05T06:50:22Z","abstract_excerpt":"The PhD thesis of Maillard (2013) presents a rather obscure algorithm for the $K$-armed bandit problem. This less-known algorithm, which we call Maillard sampling (MS), computes the probability of choosing each arm in a \\textit{closed form}, which is not true for Thompson sampling, a widely-adopted bandit algorithm in the industry. This means that the bandit-logged data from running MS can be readily used for counterfactual evaluation, unlike Thompson sampling. Motivated by such merit, we revisit MS and perform an improved analysis to show that it achieves both the asymptotical optimality and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03290","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/2111.03290/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7QReGruqTdsHshCbbBFY2R2MxT9zTiV3gvOeJSLdGMHDAh4UwjYaXKnJJgoGnfyJE7Nd/lqyGbAWHH0wms7wDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:16:14.486816Z"},"content_sha256":"af10b1a09a0284b81f4c6c35f57551747f2a470ad0aca28996b727ab2f0f517d","schema_version":"1.0","event_id":"sha256:af10b1a09a0284b81f4c6c35f57551747f2a470ad0aca28996b727ab2f0f517d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I/bundle.json","state_url":"https://pith.science/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I/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":"2026-08-07T16:16:14Z","links":{"resolver":"https://pith.science/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I","bundle":"https://pith.science/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I/bundle.json","state":"https://pith.science/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q2CAILP5BWHHGICEYQUFL4ZO2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Q2CAILP5BWHHGICEYQUFL4ZO2I","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":"3cad17e53a9366abc5859e70026f9c145db65387d8ed7233c8a6de945ddc8d35","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-05T06:50:22Z","title_canon_sha256":"ca762def59fcd2ea95723fe93f7f40edcf40a9af8844db6def55af264e36b2d2"},"schema_version":"1.0","source":{"id":"2111.03290","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.03290","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2111.03290v2","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.03290","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"Q2CAILP5BWHH","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"Q2CAILP5BWHHGICE","created_at":"2026-07-05T04:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"Q2CAILP5","created_at":"2026-07-05T04:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:af10b1a09a0284b81f4c6c35f57551747f2a470ad0aca28996b727ab2f0f517d","target":"graph","created_at":"2026-07-05T04:02:20Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2111.03290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The PhD thesis of Maillard (2013) presents a rather obscure algorithm for the $K$-armed bandit problem. This less-known algorithm, which we call Maillard sampling (MS), computes the probability of choosing each arm in a \\textit{closed form}, which is not true for Thompson sampling, a widely-adopted bandit algorithm in the industry. This means that the bandit-logged data from running MS can be readily used for counterfactual evaluation, unlike Thompson sampling. Motivated by such merit, we revisit MS and perform an improved analysis to show that it achieves both the asymptotical optimality and ","authors_text":"Jie Bian, Kwang-Sung Jun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-05T06:50:22Z","title":"Maillard Sampling: Boltzmann Exploration Done Optimally"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.03290","kind":"arxiv","version":2},"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":"sha256:8404d7e4761f423a50d4ac1b9ce8a2a1f5fc0728a9f82c7a1e5e5b5d2d70cbd1","target":"record","created_at":"2026-07-05T04:02:20Z","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":"3cad17e53a9366abc5859e70026f9c145db65387d8ed7233c8a6de945ddc8d35","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-05T06:50:22Z","title_canon_sha256":"ca762def59fcd2ea95723fe93f7f40edcf40a9af8844db6def55af264e36b2d2"},"schema_version":"1.0","source":{"id":"2111.03290","kind":"arxiv","version":2}},"canonical_sha256":"8684042dfd0d8e732044c42855f32ed22a457891c9d70bc5b77aae8ae3bebfee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8684042dfd0d8e732044c42855f32ed22a457891c9d70bc5b77aae8ae3bebfee","first_computed_at":"2026-07-05T04:02:20.631814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:20.631814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hKRB23AKefjqk0ZOLabKj7ux0Yc2cJh4L0Yip16IhFhnv54xwUMmc+Fg0RxIHZ/dQyVdcEAn5Pax38Q/cwKgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:20.632248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.03290","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8404d7e4761f423a50d4ac1b9ce8a2a1f5fc0728a9f82c7a1e5e5b5d2d70cbd1","sha256:af10b1a09a0284b81f4c6c35f57551747f2a470ad0aca28996b727ab2f0f517d"],"state_sha256":"cdeb7aacaa4a7b8bb86da000503b2c426eb97ba43622c76ab60eeb4b17c2203c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2UdX83aSLprsKhjgl1kfoDkUxEve9O6fSimfwU/yTNYjlaPwhfEkHZawfzkP+8S+QPLqL1qTandpT7vuHIe9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:16:14.491696Z","bundle_sha256":"d9cddb68364d8f52fcc1da43871428c1b82591aaee02367f654027b6d8bda9bd"}}