{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2A223536TTPLKLTQDMYUQIWYFL","short_pith_number":"pith:2A223536","schema_version":"1.0","canonical_sha256":"d035adf77e9cdeb52e701b314822d82ad5480f990e5a48775baeb636ff1bea24","source":{"kind":"arxiv","id":"2109.03818","version":1},"attestation_state":"computed","paper":{"title":"Online Learning for Cooperative Multi-Player Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mehdi Jafarnia-Jahromi, Rahul Jain, William Chang","submitted_at":"2021-09-07T18:18:58Z","abstract_excerpt":"We introduce a framework for decentralized online learning for multi-armed bandits (MAB) with multiple cooperative players. The reward obtained by the players in each round depends on the actions taken by all the players. It's a team setting, and the objective is common. Information asymmetry is what makes the problem interesting and challenging. We consider three types of information asymmetry: action information asymmetry when the actions of the players can't be observed but the rewards received are common; reward information asymmetry when the actions of the other players are observable but"},"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":"2109.03818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-07T18:18:58Z","cross_cats_sorted":[],"title_canon_sha256":"79a3b7f08502e7b387cf3355ffee668b63faadbe2046b7e379a454dc13806a19","abstract_canon_sha256":"83fe86489e6adf387fd70d800f6c97204f981780e17ed98beeee42be179d3f75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:51.669004Z","signature_b64":"kzhb0KYnifZ+BZ0gVMVDTbix7HrfgzNPup7mdqVbI+P7By4S7Y2A3ULcFQWngA5wwImeR6C6UqmvkjmpQzV0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d035adf77e9cdeb52e701b314822d82ad5480f990e5a48775baeb636ff1bea24","last_reissued_at":"2026-07-05T03:12:51.668542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:51.668542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning for Cooperative Multi-Player Multi-Armed Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mehdi Jafarnia-Jahromi, Rahul Jain, William Chang","submitted_at":"2021-09-07T18:18:58Z","abstract_excerpt":"We introduce a framework for decentralized online learning for multi-armed bandits (MAB) with multiple cooperative players. The reward obtained by the players in each round depends on the actions taken by all the players. It's a team setting, and the objective is common. Information asymmetry is what makes the problem interesting and challenging. We consider three types of information asymmetry: action information asymmetry when the actions of the players can't be observed but the rewards received are common; reward information asymmetry when the actions of the other players are observable but"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03818","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.03818/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.03818","created_at":"2026-07-05T03:12:51.668603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03818v1","created_at":"2026-07-05T03:12:51.668603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03818","created_at":"2026-07-05T03:12:51.668603+00:00"},{"alias_kind":"pith_short_12","alias_value":"2A223536TTPL","created_at":"2026-07-05T03:12:51.668603+00:00"},{"alias_kind":"pith_short_16","alias_value":"2A223536TTPLKLTQ","created_at":"2026-07-05T03:12:51.668603+00:00"},{"alias_kind":"pith_short_8","alias_value":"2A223536","created_at":"2026-07-05T03:12:51.668603+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/2A223536TTPLKLTQDMYUQIWYFL","json":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL.json","graph_json":"https://pith.science/api/pith-number/2A223536TTPLKLTQDMYUQIWYFL/graph.json","events_json":"https://pith.science/api/pith-number/2A223536TTPLKLTQDMYUQIWYFL/events.json","paper":"https://pith.science/paper/2A223536"},"agent_actions":{"view_html":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL","download_json":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL.json","view_paper":"https://pith.science/paper/2A223536","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03818&json=true","fetch_graph":"https://pith.science/api/pith-number/2A223536TTPLKLTQDMYUQIWYFL/graph.json","fetch_events":"https://pith.science/api/pith-number/2A223536TTPLKLTQDMYUQIWYFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL/action/storage_attestation","attest_author":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL/action/author_attestation","sign_citation":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL/action/citation_signature","submit_replication":"https://pith.science/pith/2A223536TTPLKLTQDMYUQIWYFL/action/replication_record"}},"created_at":"2026-07-05T03:12:51.668603+00:00","updated_at":"2026-07-05T03:12:51.668603+00:00"}