{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6ZYM5GO5TW4ZVEUNKM6RRNHY7C","short_pith_number":"pith:6ZYM5GO5","canonical_record":{"source":{"id":"1505.00553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-04T08:22:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec0d01c0b72815fd9cec56d1b6a253a89dca3296617a4a69e6f3a16d09ca40d2","abstract_canon_sha256":"98334bb702ed1376a7a566a58ea5a2a2e55adac4bf75047742c4aae89f0a9505"},"schema_version":"1.0"},"canonical_sha256":"f670ce99dd9db99a928d533d18b4f8f88667be42e27dc534dcdfbd9fe7ee2b08","source":{"kind":"arxiv","id":"1505.00553","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.00553","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"arxiv_version","alias_value":"1505.00553v2","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00553","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"pith_short_12","alias_value":"6ZYM5GO5TW4Z","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6ZYM5GO5TW4ZVEUN","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6ZYM5GO5","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6ZYM5GO5TW4ZVEUNKM6RRNHY7C","target":"record","payload":{"canonical_record":{"source":{"id":"1505.00553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-04T08:22:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec0d01c0b72815fd9cec56d1b6a253a89dca3296617a4a69e6f3a16d09ca40d2","abstract_canon_sha256":"98334bb702ed1376a7a566a58ea5a2a2e55adac4bf75047742c4aae89f0a9505"},"schema_version":"1.0"},"canonical_sha256":"f670ce99dd9db99a928d533d18b4f8f88667be42e27dc534dcdfbd9fe7ee2b08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:06.605584Z","signature_b64":"LmRRM0HwmxTbjh+eWyZm9wYXPADh0ZwWToKgRQBrbOSfjCRoCFVgpJF6SMYEmN3NliMAf5KvU2+0KtHkygHyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f670ce99dd9db99a928d533d18b4f8f88667be42e27dc534dcdfbd9fe7ee2b08","last_reissued_at":"2026-05-18T00:56:06.605161Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:06.605161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.00553","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":"2026-05-18T00:56:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wxsC6aqrn7Qpnvw0znUOYjYfB4FUZBL7I/JOqzOgnAg8m83G6pRaiKA8adFuYJGOLARtaiuNYzxvEgJ+h8J3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:20:30.030667Z"},"content_sha256":"663b08afe52f5b1f3efc16072fc12fd292ed0a7c07fc0208776782006a770218","schema_version":"1.0","event_id":"sha256:663b08afe52f5b1f3efc16072fc12fd292ed0a7c07fc0208776782006a770218"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6ZYM5GO5TW4ZVEUNKM6RRNHY7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dileep Kalathil, Naumaan Nayyar, Rahul Jain","submitted_at":"2015-05-04T08:22:04Z","abstract_excerpt":"We consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarmed bandit model, players can pick among many arms, and each play of an arm generates an i.i.d. reward from an unknown distribution. The objective is to design a policy that maximizes the expected reward over a time horizon for a single player setting and the sum of expected rewards for the multiplayer setting. In the multiplayer setting, arms may give different rewards to diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00553","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":""},"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":"2026-05-18T00:56:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CAFhsz2dU5FHMsM2sjUv/V1CiIuLsthTaGgekYj0WrL8UwcG8YOjulYzQ8iPpk2Mwvr4IgwHk9KMgFX9EAChCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:20:30.031516Z"},"content_sha256":"9c9f6a13b24be03c4d60c6cbe0bb75c53dd540b2b4929bc7dd0d340fc8213600","schema_version":"1.0","event_id":"sha256:9c9f6a13b24be03c4d60c6cbe0bb75c53dd540b2b4929bc7dd0d340fc8213600"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C/bundle.json","state_url":"https://pith.science/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C/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":"2026-05-31T13:20:30Z","links":{"resolver":"https://pith.science/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C","bundle":"https://pith.science/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C/bundle.json","state":"https://pith.science/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ZYM5GO5TW4ZVEUNKM6RRNHY7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6ZYM5GO5TW4ZVEUNKM6RRNHY7C","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":"98334bb702ed1376a7a566a58ea5a2a2e55adac4bf75047742c4aae89f0a9505","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-04T08:22:04Z","title_canon_sha256":"ec0d01c0b72815fd9cec56d1b6a253a89dca3296617a4a69e6f3a16d09ca40d2"},"schema_version":"1.0","source":{"id":"1505.00553","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.00553","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"arxiv_version","alias_value":"1505.00553v2","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00553","created_at":"2026-05-18T00:56:06Z"},{"alias_kind":"pith_short_12","alias_value":"6ZYM5GO5TW4Z","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6ZYM5GO5TW4ZVEUN","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6ZYM5GO5","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:9c9f6a13b24be03c4d60c6cbe0bb75c53dd540b2b4929bc7dd0d340fc8213600","target":"graph","created_at":"2026-05-18T00:56:06Z","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 consider the problem of learning in single-player and multiplayer multiarmed bandit models. Bandit problems are classes of online learning problems that capture exploration versus exploitation tradeoffs. In a multiarmed bandit model, players can pick among many arms, and each play of an arm generates an i.i.d. reward from an unknown distribution. The objective is to design a policy that maximizes the expected reward over a time horizon for a single player setting and the sum of expected rewards for the multiplayer setting. In the multiplayer setting, arms may give different rewards to diffe","authors_text":"Dileep Kalathil, Naumaan Nayyar, Rahul Jain","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-04T08:22:04Z","title":"On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00553","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":"sha256:663b08afe52f5b1f3efc16072fc12fd292ed0a7c07fc0208776782006a770218","target":"record","created_at":"2026-05-18T00:56:06Z","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":"98334bb702ed1376a7a566a58ea5a2a2e55adac4bf75047742c4aae89f0a9505","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-05-04T08:22:04Z","title_canon_sha256":"ec0d01c0b72815fd9cec56d1b6a253a89dca3296617a4a69e6f3a16d09ca40d2"},"schema_version":"1.0","source":{"id":"1505.00553","kind":"arxiv","version":2}},"canonical_sha256":"f670ce99dd9db99a928d533d18b4f8f88667be42e27dc534dcdfbd9fe7ee2b08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f670ce99dd9db99a928d533d18b4f8f88667be42e27dc534dcdfbd9fe7ee2b08","first_computed_at":"2026-05-18T00:56:06.605161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:56:06.605161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LmRRM0HwmxTbjh+eWyZm9wYXPADh0ZwWToKgRQBrbOSfjCRoCFVgpJF6SMYEmN3NliMAf5KvU2+0KtHkygHyDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:56:06.605584Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.00553","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:663b08afe52f5b1f3efc16072fc12fd292ed0a7c07fc0208776782006a770218","sha256:9c9f6a13b24be03c4d60c6cbe0bb75c53dd540b2b4929bc7dd0d340fc8213600"],"state_sha256":"80afa7e5e4f6e96c296f347fb7faca6495452f72ecf17ef11986f13adca2da8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXHzkA+agoJ2XfQqTa+tBo+71I8+2w4cKVngFwRgxfD7qDC+zM6N9riLUTSryAima4XBhj8RjRKzEWQL01m9DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T13:20:30.036698Z","bundle_sha256":"ad2a55abd86bbe3af0d7e4c2eb21040f0f00d176fb39d07670ef2b664a24e078"}}