{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LOKGO3PB7VY5KW6O4R7CUC5DDV","short_pith_number":"pith:LOKGO3PB","schema_version":"1.0","canonical_sha256":"5b94676de1fd71d55bcee47e2a0ba31d6d859818a5735d87ca4fd1565ba049b0","source":{"kind":"arxiv","id":"2506.15856","version":1},"attestation_state":"computed","paper":{"title":"Learning to Coordinate Under Threshold Rewards: A Cooperative Multi-Agent Bandit Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Michael Ledford, William Regli","submitted_at":"2025-06-18T20:04:43Z","abstract_excerpt":"Cooperative multi-agent systems often face tasks that require coordinated actions under uncertainty. While multi-armed bandit (MAB) problems provide a powerful framework for decentralized learning, most prior work assumes individually attainable rewards. We address the challenging setting where rewards are threshold-activated: an arm yields a payoff only when a minimum number of agents pull it simultaneously, with this threshold unknown in advance. Complicating matters further, some arms are decoys - requiring coordination to activate but yielding no reward - introducing a new challenge of was"},"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":"2506.15856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-06-18T20:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"af5ac5887f32176c61bcf36bcbbd9376d9cf079d5130bfe4ac314fa83f5632c5","abstract_canon_sha256":"7825ac0bc594ce28dc4f06a6aa69f86be53b5e07e73ad949753dfcec1dfe9baa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:53.625335Z","signature_b64":"Dt6NOL5MB7abh0Q4YpW6P5yUq8v+k5MGtdKNEjFAfBmJSHxvH2EPBVHCdR3bRzMxcaPnurNM47l/PkAqedm2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b94676de1fd71d55bcee47e2a0ba31d6d859818a5735d87ca4fd1565ba049b0","last_reissued_at":"2026-07-05T11:23:53.624701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:53.624701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Coordinate Under Threshold Rewards: A Cooperative Multi-Agent Bandit Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Michael Ledford, William Regli","submitted_at":"2025-06-18T20:04:43Z","abstract_excerpt":"Cooperative multi-agent systems often face tasks that require coordinated actions under uncertainty. While multi-armed bandit (MAB) problems provide a powerful framework for decentralized learning, most prior work assumes individually attainable rewards. We address the challenging setting where rewards are threshold-activated: an arm yields a payoff only when a minimum number of agents pull it simultaneously, with this threshold unknown in advance. Complicating matters further, some arms are decoys - requiring coordination to activate but yielding no reward - introducing a new challenge of was"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15856","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/2506.15856/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":"2506.15856","created_at":"2026-07-05T11:23:53.624786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15856v1","created_at":"2026-07-05T11:23:53.624786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15856","created_at":"2026-07-05T11:23:53.624786+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOKGO3PB7VY5","created_at":"2026-07-05T11:23:53.624786+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOKGO3PB7VY5KW6O","created_at":"2026-07-05T11:23:53.624786+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOKGO3PB","created_at":"2026-07-05T11:23:53.624786+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/LOKGO3PB7VY5KW6O4R7CUC5DDV","json":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV.json","graph_json":"https://pith.science/api/pith-number/LOKGO3PB7VY5KW6O4R7CUC5DDV/graph.json","events_json":"https://pith.science/api/pith-number/LOKGO3PB7VY5KW6O4R7CUC5DDV/events.json","paper":"https://pith.science/paper/LOKGO3PB"},"agent_actions":{"view_html":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV","download_json":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV.json","view_paper":"https://pith.science/paper/LOKGO3PB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15856&json=true","fetch_graph":"https://pith.science/api/pith-number/LOKGO3PB7VY5KW6O4R7CUC5DDV/graph.json","fetch_events":"https://pith.science/api/pith-number/LOKGO3PB7VY5KW6O4R7CUC5DDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV/action/storage_attestation","attest_author":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV/action/author_attestation","sign_citation":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV/action/citation_signature","submit_replication":"https://pith.science/pith/LOKGO3PB7VY5KW6O4R7CUC5DDV/action/replication_record"}},"created_at":"2026-07-05T11:23:53.624786+00:00","updated_at":"2026-07-05T11:23:53.624786+00:00"}