{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6TJMW46I4E2IQMTKBSRF34SCMY","short_pith_number":"pith:6TJMW46I","schema_version":"1.0","canonical_sha256":"f4d2cb73c8e13488326a0ca25df242661e047feb7be11986b2a8878ae4695622","source":{"kind":"arxiv","id":"2606.04359","version":1},"attestation_state":"computed","paper":{"title":"Learning to cooperate with emergent reputation via multi-agent reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Dengji Zhao, Xinwei Song, Xue Feng, Yizhe Huang","submitted_at":"2026-06-03T02:20:02Z","abstract_excerpt":"Reputation, the aggregation of peer assessments diffused through social networks, is a pivotal mechanism for promoting cooperation in social dilemmas ubiquitous to distributed multi-agent systems comprising agents with limited perception and cognitive capabilities. Exploring efficient reputation systems, comprising reputation assessment rules and reputation-based policies, is a long-standing challenge. Previous work assumes predefined reputation assessment rules or models reputation as an intrinsic reward to learn policies, compromising the methods' ability for generalization and adaptation. T"},"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":"2606.04359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2026-06-03T02:20:02Z","cross_cats_sorted":[],"title_canon_sha256":"13fcc7e501847b3ac66e4ecc05c5a259839534d39f5232ab7e2b3e32d79d84e4","abstract_canon_sha256":"ab8832a92095573cae3632d1fa6958c2102de61056e89a37ceb6d465ca7c1920"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:04.880612Z","signature_b64":"M/fQAljm0KGnEH+DkAlBn181KuABY/3yBr0gOKf0MRom77Pr3FYwkv4q/bVkOx2QM3aTIEfrtBloKpgPo5NsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4d2cb73c8e13488326a0ca25df242661e047feb7be11986b2a8878ae4695622","last_reissued_at":"2026-06-04T01:09:04.879996Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:04.879996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to cooperate with emergent reputation via multi-agent reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Dengji Zhao, Xinwei Song, Xue Feng, Yizhe Huang","submitted_at":"2026-06-03T02:20:02Z","abstract_excerpt":"Reputation, the aggregation of peer assessments diffused through social networks, is a pivotal mechanism for promoting cooperation in social dilemmas ubiquitous to distributed multi-agent systems comprising agents with limited perception and cognitive capabilities. Exploring efficient reputation systems, comprising reputation assessment rules and reputation-based policies, is a long-standing challenge. Previous work assumes predefined reputation assessment rules or models reputation as an intrinsic reward to learn policies, compromising the methods' ability for generalization and adaptation. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04359","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/2606.04359/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":"2606.04359","created_at":"2026-06-04T01:09:04.880067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04359v1","created_at":"2026-06-04T01:09:04.880067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04359","created_at":"2026-06-04T01:09:04.880067+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TJMW46I4E2I","created_at":"2026-06-04T01:09:04.880067+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TJMW46I4E2IQMTK","created_at":"2026-06-04T01:09:04.880067+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TJMW46I","created_at":"2026-06-04T01:09:04.880067+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/6TJMW46I4E2IQMTKBSRF34SCMY","json":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY.json","graph_json":"https://pith.science/api/pith-number/6TJMW46I4E2IQMTKBSRF34SCMY/graph.json","events_json":"https://pith.science/api/pith-number/6TJMW46I4E2IQMTKBSRF34SCMY/events.json","paper":"https://pith.science/paper/6TJMW46I"},"agent_actions":{"view_html":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY","download_json":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY.json","view_paper":"https://pith.science/paper/6TJMW46I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04359&json=true","fetch_graph":"https://pith.science/api/pith-number/6TJMW46I4E2IQMTKBSRF34SCMY/graph.json","fetch_events":"https://pith.science/api/pith-number/6TJMW46I4E2IQMTKBSRF34SCMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY/action/storage_attestation","attest_author":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY/action/author_attestation","sign_citation":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY/action/citation_signature","submit_replication":"https://pith.science/pith/6TJMW46I4E2IQMTKBSRF34SCMY/action/replication_record"}},"created_at":"2026-06-04T01:09:04.880067+00:00","updated_at":"2026-06-04T01:09:04.880067+00:00"}