{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L4MQ45EWX5DGVIAQSNAXTAW327","short_pith_number":"pith:L4MQ45EW","schema_version":"1.0","canonical_sha256":"5f190e7496bf466aa01093417982dbd7e629bf5ea8b2f334c68d5e81d7bd5b00","source":{"kind":"arxiv","id":"2304.12653","version":4},"attestation_state":"computed","paper":{"title":"Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanjun Liu, Min Yang, Ziyuan Zhou","submitted_at":"2023-04-25T08:38:32Z","abstract_excerpt":"Traditional multi-agent reinforcement learning algorithms are difficultly applied in a large-scale multi-agent environment. The introduction of mean field theory has enhanced the scalability of multi-agent reinforcement learning in recent years. This paper considers partially observable multi-agent reinforcement learning (MARL), where each agent can only observe other agents within a fixed range. This partial observability affects the agent's ability to assess the quality of the actions of surrounding agents. This paper focuses on developing a method to capture more effective information from "},"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":"2304.12653","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-25T08:38:32Z","cross_cats_sorted":[],"title_canon_sha256":"d784881bffc068e56a76f904d015fa89dcb10c1cc8af7d5b6d3910533e0afbe5","abstract_canon_sha256":"7100c02772613ad918902d167840790b46ea7fd1d3d36fa1f77b6a334894c7dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:27.968338Z","signature_b64":"5DmNKVIFVIYtXTewjoN+JIbtysz39rArvtgNDGhhJ/eas8XLCDKK2UkyZmaeGgYesQkPd2+1P1EkruFHFCy7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f190e7496bf466aa01093417982dbd7e629bf5ea8b2f334c68d5e81d7bd5b00","last_reissued_at":"2026-07-05T09:04:27.967872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:27.967872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanjun Liu, Min Yang, Ziyuan Zhou","submitted_at":"2023-04-25T08:38:32Z","abstract_excerpt":"Traditional multi-agent reinforcement learning algorithms are difficultly applied in a large-scale multi-agent environment. The introduction of mean field theory has enhanced the scalability of multi-agent reinforcement learning in recent years. This paper considers partially observable multi-agent reinforcement learning (MARL), where each agent can only observe other agents within a fixed range. This partial observability affects the agent's ability to assess the quality of the actions of surrounding agents. This paper focuses on developing a method to capture more effective information from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12653","kind":"arxiv","version":4},"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/2304.12653/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":"2304.12653","created_at":"2026-07-05T09:04:27.967928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12653v4","created_at":"2026-07-05T09:04:27.967928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12653","created_at":"2026-07-05T09:04:27.967928+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4MQ45EWX5DG","created_at":"2026-07-05T09:04:27.967928+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4MQ45EWX5DGVIAQ","created_at":"2026-07-05T09:04:27.967928+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4MQ45EW","created_at":"2026-07-05T09:04:27.967928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14131","citing_title":"An Improved Multi-Agent Algorithm for Cooperative and Competitive Environments by Identifying and Encouraging Cooperation among Agents","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327","json":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327.json","graph_json":"https://pith.science/api/pith-number/L4MQ45EWX5DGVIAQSNAXTAW327/graph.json","events_json":"https://pith.science/api/pith-number/L4MQ45EWX5DGVIAQSNAXTAW327/events.json","paper":"https://pith.science/paper/L4MQ45EW"},"agent_actions":{"view_html":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327","download_json":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327.json","view_paper":"https://pith.science/paper/L4MQ45EW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12653&json=true","fetch_graph":"https://pith.science/api/pith-number/L4MQ45EWX5DGVIAQSNAXTAW327/graph.json","fetch_events":"https://pith.science/api/pith-number/L4MQ45EWX5DGVIAQSNAXTAW327/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327/action/storage_attestation","attest_author":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327/action/author_attestation","sign_citation":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327/action/citation_signature","submit_replication":"https://pith.science/pith/L4MQ45EWX5DGVIAQSNAXTAW327/action/replication_record"}},"created_at":"2026-07-05T09:04:27.967928+00:00","updated_at":"2026-07-05T09:04:27.967928+00:00"}