{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4U7MRUCINC4NPZFPLFFIDPMWYV","short_pith_number":"pith:4U7MRUCI","schema_version":"1.0","canonical_sha256":"e53ec8d04868b8d7e4af594a81bd96c57100777bf102c9830bd3c6f2ff5b65ed","source":{"kind":"arxiv","id":"2502.01971","version":1},"attestation_state":"computed","paper":{"title":"Bottom-Up Reputation Promotes Cooperation with Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Tianyu Ren, Xiao-Jun Zeng, Xuan Yao, Yang Li","submitted_at":"2025-02-04T03:28:51Z","abstract_excerpt":"Reputation serves as a powerful mechanism for promoting cooperation in multi-agent systems, as agents are more inclined to cooperate with those of good social standing. While existing multi-agent reinforcement learning methods typically rely on predefined social norms to assign reputations, the question of how a population reaches a consensus on judgement when agents hold private, independent views remains unresolved. In this paper, we propose a novel bottom-up reputation learning method, Learning with Reputation Reward (LR2), designed to promote cooperative behaviour through rewards shaping b"},"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":"2502.01971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-02-04T03:28:51Z","cross_cats_sorted":[],"title_canon_sha256":"aae99f07004fc6033fe65d73dd438d0e3f10ba44d9311c5af0ccb29094749c99","abstract_canon_sha256":"f3f7485ed3e56cd8e0549251fdf13f251b59c151e7a96fe5b0d84117cfce02c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:21.789069Z","signature_b64":"QyiKpbsSibgZP/lvBHRrXBKYR8qY9lKaJvyZvcKPm/xBjVNDPHoh9Vu+ggPb6pSy2EUzYbhsrE3/NyDguPG+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e53ec8d04868b8d7e4af594a81bd96c57100777bf102c9830bd3c6f2ff5b65ed","last_reissued_at":"2026-07-05T10:09:21.788656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:21.788656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bottom-Up Reputation Promotes Cooperation with Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Tianyu Ren, Xiao-Jun Zeng, Xuan Yao, Yang Li","submitted_at":"2025-02-04T03:28:51Z","abstract_excerpt":"Reputation serves as a powerful mechanism for promoting cooperation in multi-agent systems, as agents are more inclined to cooperate with those of good social standing. While existing multi-agent reinforcement learning methods typically rely on predefined social norms to assign reputations, the question of how a population reaches a consensus on judgement when agents hold private, independent views remains unresolved. In this paper, we propose a novel bottom-up reputation learning method, Learning with Reputation Reward (LR2), designed to promote cooperative behaviour through rewards shaping b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01971","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/2502.01971/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":"2502.01971","created_at":"2026-07-05T10:09:21.788712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01971v1","created_at":"2026-07-05T10:09:21.788712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01971","created_at":"2026-07-05T10:09:21.788712+00:00"},{"alias_kind":"pith_short_12","alias_value":"4U7MRUCINC4N","created_at":"2026-07-05T10:09:21.788712+00:00"},{"alias_kind":"pith_short_16","alias_value":"4U7MRUCINC4NPZFP","created_at":"2026-07-05T10:09:21.788712+00:00"},{"alias_kind":"pith_short_8","alias_value":"4U7MRUCI","created_at":"2026-07-05T10:09:21.788712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08323","citing_title":"The Reciprocity Gradient","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08103","citing_title":"Reinforcement learning with reputation-based adaptive exploration promotes the evolution of cooperation","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV","json":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV.json","graph_json":"https://pith.science/api/pith-number/4U7MRUCINC4NPZFPLFFIDPMWYV/graph.json","events_json":"https://pith.science/api/pith-number/4U7MRUCINC4NPZFPLFFIDPMWYV/events.json","paper":"https://pith.science/paper/4U7MRUCI"},"agent_actions":{"view_html":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV","download_json":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV.json","view_paper":"https://pith.science/paper/4U7MRUCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01971&json=true","fetch_graph":"https://pith.science/api/pith-number/4U7MRUCINC4NPZFPLFFIDPMWYV/graph.json","fetch_events":"https://pith.science/api/pith-number/4U7MRUCINC4NPZFPLFFIDPMWYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV/action/storage_attestation","attest_author":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV/action/author_attestation","sign_citation":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV/action/citation_signature","submit_replication":"https://pith.science/pith/4U7MRUCINC4NPZFPLFFIDPMWYV/action/replication_record"}},"created_at":"2026-07-05T10:09:21.788712+00:00","updated_at":"2026-07-05T10:09:21.788712+00:00"}