{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GIGYYSZVTM577FTA3HWEVREMIX","short_pith_number":"pith:GIGYYSZV","schema_version":"1.0","canonical_sha256":"320d8c4b359b3bff9660d9ec4ac48c45ed8614f3485b040c680ec9ed6e830e29","source":{"kind":"arxiv","id":"2004.03793","version":1},"attestation_state":"computed","paper":{"title":"A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Naomi Ehrich Leonard, Udari Madhushani","submitted_at":"2020-04-08T03:45:48Z","abstract_excerpt":"We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors under a linear observation cost. Neighbors are defined by a network graph that encodes the inherent observation constraints of the system. We define a cost associated with observations such that at every instance an agent makes an observation it receives a constant observation regret. We design a sampling algorithm and an observation protocol for each agent to maximize its own expected cumulative reward through minimizing expected cumulative samp"},"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":"2004.03793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-04-08T03:45:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6e47ddd04df1b35dea32146600a6e5df75917db8de8d5dfb69633a9ed8189d4","abstract_canon_sha256":"d573dc621bfadd52dac524e31e2da5c4c533b4074decfe91d3ad26dd32bb09eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:56.208415Z","signature_b64":"cUx+veCHl8ZeEWjuu/fL2aixa2eWAPziZm6/MFWXRBngM5xBaKj9NW/pXIqc63f1tJ6OjH+DBrKQkaJsSATOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320d8c4b359b3bff9660d9ec4ac48c45ed8614f3485b040c680ec9ed6e830e29","last_reissued_at":"2026-07-05T00:53:56.208043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:56.208043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Naomi Ehrich Leonard, Udari Madhushani","submitted_at":"2020-04-08T03:45:48Z","abstract_excerpt":"We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors under a linear observation cost. Neighbors are defined by a network graph that encodes the inherent observation constraints of the system. We define a cost associated with observations such that at every instance an agent makes an observation it receives a constant observation regret. We design a sampling algorithm and an observation protocol for each agent to maximize its own expected cumulative reward through minimizing expected cumulative samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03793","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/2004.03793/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":"2004.03793","created_at":"2026-07-05T00:53:56.208099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.03793v1","created_at":"2026-07-05T00:53:56.208099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03793","created_at":"2026-07-05T00:53:56.208099+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIGYYSZVTM57","created_at":"2026-07-05T00:53:56.208099+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIGYYSZVTM577FTA","created_at":"2026-07-05T00:53:56.208099+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIGYYSZV","created_at":"2026-07-05T00:53:56.208099+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/GIGYYSZVTM577FTA3HWEVREMIX","json":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX.json","graph_json":"https://pith.science/api/pith-number/GIGYYSZVTM577FTA3HWEVREMIX/graph.json","events_json":"https://pith.science/api/pith-number/GIGYYSZVTM577FTA3HWEVREMIX/events.json","paper":"https://pith.science/paper/GIGYYSZV"},"agent_actions":{"view_html":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX","download_json":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX.json","view_paper":"https://pith.science/paper/GIGYYSZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.03793&json=true","fetch_graph":"https://pith.science/api/pith-number/GIGYYSZVTM577FTA3HWEVREMIX/graph.json","fetch_events":"https://pith.science/api/pith-number/GIGYYSZVTM577FTA3HWEVREMIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX/action/storage_attestation","attest_author":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX/action/author_attestation","sign_citation":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX/action/citation_signature","submit_replication":"https://pith.science/pith/GIGYYSZVTM577FTA3HWEVREMIX/action/replication_record"}},"created_at":"2026-07-05T00:53:56.208099+00:00","updated_at":"2026-07-05T00:53:56.208099+00:00"}