{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:DC57CW5MEFRLKRXDKR4UNBVX6M","short_pith_number":"pith:DC57CW5M","canonical_record":{"source":{"id":"1206.3582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/publicdomain/","primary_cat":"math.OC","submitted_at":"2012-06-14T07:07:58Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"68d8521d0b87af810fac9cf1b1ae142c31be2b3c26bebcb8f49211827e58d7cd","abstract_canon_sha256":"fe3f28205836cd49bc6d85731bcb8a5e76eb2a5afce5f7c86558924730446993"},"schema_version":"1.0"},"canonical_sha256":"18bbf15bac2162b546e354794686b7f32f13d18663a66c8a68c9f1013f7baeb2","source":{"kind":"arxiv","id":"1206.3582","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.3582","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1206.3582v1","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3582","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"DC57CW5MEFRL","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"DC57CW5MEFRLKRXD","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"DC57CW5M","created_at":"2026-05-18T12:27:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:DC57CW5MEFRLKRXDKR4UNBVX6M","target":"record","payload":{"canonical_record":{"source":{"id":"1206.3582","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/publicdomain/","primary_cat":"math.OC","submitted_at":"2012-06-14T07:07:58Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"68d8521d0b87af810fac9cf1b1ae142c31be2b3c26bebcb8f49211827e58d7cd","abstract_canon_sha256":"fe3f28205836cd49bc6d85731bcb8a5e76eb2a5afce5f7c86558924730446993"},"schema_version":"1.0"},"canonical_sha256":"18bbf15bac2162b546e354794686b7f32f13d18663a66c8a68c9f1013f7baeb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:56.910774Z","signature_b64":"d7hJOLiUij3pLH3TxHo5kCAm/4ldSyvXD3QA4HxpqqXw++oODt0YapMCjCyGI4GQYOlGnSXxfK36nDdDbla0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18bbf15bac2162b546e354794686b7f32f13d18663a66c8a68c9f1013f7baeb2","last_reissued_at":"2026-05-18T00:57:56.910207Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:56.910207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.3582","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":"2026-05-18T00:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iP7T9Ci/0DqqJhcvmzukDhZv3/Qo9Y5PTJBL5/3hiag3jgX1X7L1xpWujFPtFaHZ8HZu/dJN89/XAOfvjrwYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:42:25.894003Z"},"content_sha256":"dc3477b3e488c001864a10608a61cf11903ba6fdecb41f5d49f31b05a6702e4a","schema_version":"1.0","event_id":"sha256:dc3477b3e488c001864a10608a61cf11903ba6fdecb41f5d49f31b05a6702e4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:DC57CW5MEFRLKRXDKR4UNBVX6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decentralized Learning for Multi-player Multi-armed Bandits","license":"http://creativecommons.org/licenses/publicdomain/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"math.OC","authors_text":"Dileep Kalathil, Naumaan Nayyar, Rahul Jain","submitted_at":"2012-06-14T07:07:58Z","abstract_excerpt":"We consider the problem of distributed online learning with multiple players in multi-armed bandits (MAB) models. Each player can pick among multiple arms. When a player picks an arm, it gets a reward. We consider both i.i.d. reward model and Markovian reward model. In the i.i.d. model each arm is modelled as an i.i.d. process with an unknown distribution with an unknown mean. In the Markovian model, each arm is modelled as a finite, irreducible, aperiodic and reversible Markov chain with an unknown probability transition matrix and stationary distribution. The arms give different rewards to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.3582","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":"2026-05-18T00:57:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0z55ZTp/iLmG9Rh564v556J3951aMWY+udNlyA1FcVm6W3ZGYX6LLnHNcuzo/NLsAqZYQfUVukHTuXgFwD0NBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:42:25.894704Z"},"content_sha256":"6aac1e7cc4f55dfc31f1c82590c51a524bc631deaa565bcd1853d6f8e4bddd70","schema_version":"1.0","event_id":"sha256:6aac1e7cc4f55dfc31f1c82590c51a524bc631deaa565bcd1853d6f8e4bddd70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/bundle.json","state_url":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/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":"2026-05-25T23:42:25Z","links":{"resolver":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M","bundle":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/bundle.json","state":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:DC57CW5MEFRLKRXDKR4UNBVX6M","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":"fe3f28205836cd49bc6d85731bcb8a5e76eb2a5afce5f7c86558924730446993","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://creativecommons.org/licenses/publicdomain/","primary_cat":"math.OC","submitted_at":"2012-06-14T07:07:58Z","title_canon_sha256":"68d8521d0b87af810fac9cf1b1ae142c31be2b3c26bebcb8f49211827e58d7cd"},"schema_version":"1.0","source":{"id":"1206.3582","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.3582","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"arxiv_version","alias_value":"1206.3582v1","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3582","created_at":"2026-05-18T00:57:56Z"},{"alias_kind":"pith_short_12","alias_value":"DC57CW5MEFRL","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_16","alias_value":"DC57CW5MEFRLKRXD","created_at":"2026-05-18T12:27:01Z"},{"alias_kind":"pith_short_8","alias_value":"DC57CW5M","created_at":"2026-05-18T12:27:01Z"}],"graph_snapshots":[{"event_id":"sha256:6aac1e7cc4f55dfc31f1c82590c51a524bc631deaa565bcd1853d6f8e4bddd70","target":"graph","created_at":"2026-05-18T00:57:56Z","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 distributed online learning with multiple players in multi-armed bandits (MAB) models. Each player can pick among multiple arms. When a player picks an arm, it gets a reward. We consider both i.i.d. reward model and Markovian reward model. In the i.i.d. model each arm is modelled as an i.i.d. process with an unknown distribution with an unknown mean. In the Markovian model, each arm is modelled as a finite, irreducible, aperiodic and reversible Markov chain with an unknown probability transition matrix and stationary distribution. The arms give different rewards to d","authors_text":"Dileep Kalathil, Naumaan Nayyar, Rahul Jain","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/publicdomain/","primary_cat":"math.OC","submitted_at":"2012-06-14T07:07:58Z","title":"Decentralized Learning for Multi-player Multi-armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.3582","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:dc3477b3e488c001864a10608a61cf11903ba6fdecb41f5d49f31b05a6702e4a","target":"record","created_at":"2026-05-18T00:57:56Z","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":"fe3f28205836cd49bc6d85731bcb8a5e76eb2a5afce5f7c86558924730446993","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://creativecommons.org/licenses/publicdomain/","primary_cat":"math.OC","submitted_at":"2012-06-14T07:07:58Z","title_canon_sha256":"68d8521d0b87af810fac9cf1b1ae142c31be2b3c26bebcb8f49211827e58d7cd"},"schema_version":"1.0","source":{"id":"1206.3582","kind":"arxiv","version":1}},"canonical_sha256":"18bbf15bac2162b546e354794686b7f32f13d18663a66c8a68c9f1013f7baeb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18bbf15bac2162b546e354794686b7f32f13d18663a66c8a68c9f1013f7baeb2","first_computed_at":"2026-05-18T00:57:56.910207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:57:56.910207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d7hJOLiUij3pLH3TxHo5kCAm/4ldSyvXD3QA4HxpqqXw++oODt0YapMCjCyGI4GQYOlGnSXxfK36nDdDbla0DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:57:56.910774Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.3582","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc3477b3e488c001864a10608a61cf11903ba6fdecb41f5d49f31b05a6702e4a","sha256:6aac1e7cc4f55dfc31f1c82590c51a524bc631deaa565bcd1853d6f8e4bddd70"],"state_sha256":"0f01ab00e5f9920156e58486b08f88979201b3bf93a05da9f02101c9a2691aba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"taLheR+iRrFx9VTL5KdSA4Q9eynTc08eIpt+eNFofcUIcuKcMyTMzCxha1gLvu1yM2pjniYhP1zS9QRDUFk+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:42:25.899048Z","bundle_sha256":"bdbd3de4500a2d4de2b8a9d79094d8f3967cc33e6310d47dd68c800477bd852d"}}