{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GIGYYSZVTM577FTA3HWEVREMIX","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":"d573dc621bfadd52dac524e31e2da5c4c533b4074decfe91d3ad26dd32bb09eb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-04-08T03:45:48Z","title_canon_sha256":"e6e47ddd04df1b35dea32146600a6e5df75917db8de8d5dfb69633a9ed8189d4"},"schema_version":"1.0","source":{"id":"2004.03793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.03793","created_at":"2026-07-05T00:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"2004.03793v1","created_at":"2026-07-05T00:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.03793","created_at":"2026-07-05T00:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"GIGYYSZVTM57","created_at":"2026-07-05T00:53:56Z"},{"alias_kind":"pith_short_16","alias_value":"GIGYYSZVTM577FTA","created_at":"2026-07-05T00:53:56Z"},{"alias_kind":"pith_short_8","alias_value":"GIGYYSZV","created_at":"2026-07-05T00:53:56Z"}],"graph_snapshots":[{"event_id":"sha256:a4b04a1e9971ad60f01e13a03fb69d39be7604edf38adeb9169fc65ecda4a317","target":"graph","created_at":"2026-07-05T00:53:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.03793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Naomi Ehrich Leonard, Udari Madhushani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-04-08T03:45:48Z","title":"A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.03793","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":"sha256:0d3c13a770a5ca0fe3fad1c7a77e88725eb4dd23aae48b23fe1f036ce2c58c73","target":"record","created_at":"2026-07-05T00:53:56Z","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":"d573dc621bfadd52dac524e31e2da5c4c533b4074decfe91d3ad26dd32bb09eb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-04-08T03:45:48Z","title_canon_sha256":"e6e47ddd04df1b35dea32146600a6e5df75917db8de8d5dfb69633a9ed8189d4"},"schema_version":"1.0","source":{"id":"2004.03793","kind":"arxiv","version":1}},"canonical_sha256":"320d8c4b359b3bff9660d9ec4ac48c45ed8614f3485b040c680ec9ed6e830e29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"320d8c4b359b3bff9660d9ec4ac48c45ed8614f3485b040c680ec9ed6e830e29","first_computed_at":"2026-07-05T00:53:56.208043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:56.208043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cUx+veCHl8ZeEWjuu/fL2aixa2eWAPziZm6/MFWXRBngM5xBaKj9NW/pXIqc63f1tJ6OjH+DBrKQkaJsSATOCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:56.208415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.03793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d3c13a770a5ca0fe3fad1c7a77e88725eb4dd23aae48b23fe1f036ce2c58c73","sha256:a4b04a1e9971ad60f01e13a03fb69d39be7604edf38adeb9169fc65ecda4a317"],"state_sha256":"5e55cb36ad49930b807113a5c856d4449f78e965a361045a35eee88577acabab"}