{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:DC57CW5MEFRLKRXDKR4UNBVX6M","short_pith_number":"pith:DC57CW5M","schema_version":"1.0","canonical_sha256":"18bbf15bac2162b546e354794686b7f32f13d18663a66c8a68c9f1013f7baeb2","source":{"kind":"arxiv","id":"1206.3582","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1206.3582","created_at":"2026-05-18T00:57:56.910297+00:00"},{"alias_kind":"arxiv_version","alias_value":"1206.3582v1","created_at":"2026-05-18T00:57:56.910297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.3582","created_at":"2026-05-18T00:57:56.910297+00:00"},{"alias_kind":"pith_short_12","alias_value":"DC57CW5MEFRL","created_at":"2026-05-18T12:27:01.376967+00:00"},{"alias_kind":"pith_short_16","alias_value":"DC57CW5MEFRLKRXD","created_at":"2026-05-18T12:27:01.376967+00:00"},{"alias_kind":"pith_short_8","alias_value":"DC57CW5M","created_at":"2026-05-18T12:27:01.376967+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/DC57CW5MEFRLKRXDKR4UNBVX6M","json":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M.json","graph_json":"https://pith.science/api/pith-number/DC57CW5MEFRLKRXDKR4UNBVX6M/graph.json","events_json":"https://pith.science/api/pith-number/DC57CW5MEFRLKRXDKR4UNBVX6M/events.json","paper":"https://pith.science/paper/DC57CW5M"},"agent_actions":{"view_html":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M","download_json":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M.json","view_paper":"https://pith.science/paper/DC57CW5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1206.3582&json=true","fetch_graph":"https://pith.science/api/pith-number/DC57CW5MEFRLKRXDKR4UNBVX6M/graph.json","fetch_events":"https://pith.science/api/pith-number/DC57CW5MEFRLKRXDKR4UNBVX6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/action/storage_attestation","attest_author":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/action/author_attestation","sign_citation":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/action/citation_signature","submit_replication":"https://pith.science/pith/DC57CW5MEFRLKRXDKR4UNBVX6M/action/replication_record"}},"created_at":"2026-05-18T00:57:56.910297+00:00","updated_at":"2026-05-18T00:57:56.910297+00:00"}