{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QHCDCYQR343ZL6HTSK7QM5INXA","short_pith_number":"pith:QHCDCYQR","canonical_record":{"source":{"id":"2305.10091","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-17T09:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"4d243e14b894522b39da98f961768142bf6a3ee4a3df23dce653151ff57d40ac","abstract_canon_sha256":"15ede375fc000ef4b878da6d0fbf54d37961e07151f5c2b4cf7638135ad70c52"},"schema_version":"1.0"},"canonical_sha256":"81c4316211df3795f8f392bf06750db83d4d4c540913d58d8f359cca6ee71541","source":{"kind":"arxiv","id":"2305.10091","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10091","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10091v1","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10091","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_12","alias_value":"QHCDCYQR343Z","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_16","alias_value":"QHCDCYQR343ZL6HT","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_8","alias_value":"QHCDCYQR","created_at":"2026-07-05T08:28:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QHCDCYQR343ZL6HTSK7QM5INXA","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10091","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-17T09:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"4d243e14b894522b39da98f961768142bf6a3ee4a3df23dce653151ff57d40ac","abstract_canon_sha256":"15ede375fc000ef4b878da6d0fbf54d37961e07151f5c2b4cf7638135ad70c52"},"schema_version":"1.0"},"canonical_sha256":"81c4316211df3795f8f392bf06750db83d4d4c540913d58d8f359cca6ee71541","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:00.847479Z","signature_b64":"vcUouOWVm0hkWRgYknDa6Id0NPK7MCR+dv6Zmd7WSPsfW//It4zw3psCdj1cHDvpw25bhutTRgBgi83AE6qdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81c4316211df3795f8f392bf06750db83d4d4c540913d58d8f359cca6ee71541","last_reissued_at":"2026-07-05T08:28:00.847041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:00.847041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10091","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6c0/A/WxCqDx4Kn8kOdi2+2w92aR8JphrIZJCB7E/z0RV+F3tQ+Kmzqn+n68yD0Qc5XSnQjMXzlLdts4HpIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:36:25.275493Z"},"content_sha256":"37e771f0983d4cf933eea07f92e30b813ff476ebec01b6b30902cfecb7cc4706","schema_version":"1.0","event_id":"sha256:37e771f0983d4cf933eea07f92e30b813ff476ebec01b6b30902cfecb7cc4706"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QHCDCYQR343ZL6HTSK7QM5INXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanjun Liu, Ying Tang, Ziyuan Zhou","submitted_at":"2023-05-17T09:53:13Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI) technique. However, current studies and applications need to address its scalability, non-stationarity, and trustworthiness. This paper aims to review methods and applications and point out research trends and visionary prospects for the next decade. First, this paper summarizes the basic methods and application scenarios of MARL. Second, this paper outlines the corresponding research methods and their limitations on safety, robustness, generalization, and ethical constraints that need to be addressed in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10091","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/2305.10091/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"36jJmqWaXIK/4GLmns+an+Mk0lyHcex6/3zHcTL6QA4I9jfrPprSsB787uAn1uc3K2EpsCgue60Bheckp3kyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:36:25.276390Z"},"content_sha256":"13e07fc912d35ab24bd935b1f73b32bb6c17b61e3c3f1e2a184737e23b792b04","schema_version":"1.0","event_id":"sha256:13e07fc912d35ab24bd935b1f73b32bb6c17b61e3c3f1e2a184737e23b792b04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QHCDCYQR343ZL6HTSK7QM5INXA/bundle.json","state_url":"https://pith.science/pith/QHCDCYQR343ZL6HTSK7QM5INXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QHCDCYQR343ZL6HTSK7QM5INXA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T13:36:25Z","links":{"resolver":"https://pith.science/pith/QHCDCYQR343ZL6HTSK7QM5INXA","bundle":"https://pith.science/pith/QHCDCYQR343ZL6HTSK7QM5INXA/bundle.json","state":"https://pith.science/pith/QHCDCYQR343ZL6HTSK7QM5INXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QHCDCYQR343ZL6HTSK7QM5INXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QHCDCYQR343ZL6HTSK7QM5INXA","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":"15ede375fc000ef4b878da6d0fbf54d37961e07151f5c2b4cf7638135ad70c52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-17T09:53:13Z","title_canon_sha256":"4d243e14b894522b39da98f961768142bf6a3ee4a3df23dce653151ff57d40ac"},"schema_version":"1.0","source":{"id":"2305.10091","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10091","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10091v1","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10091","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_12","alias_value":"QHCDCYQR343Z","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_16","alias_value":"QHCDCYQR343ZL6HT","created_at":"2026-07-05T08:28:00Z"},{"alias_kind":"pith_short_8","alias_value":"QHCDCYQR","created_at":"2026-07-05T08:28:00Z"}],"graph_snapshots":[{"event_id":"sha256:13e07fc912d35ab24bd935b1f73b32bb6c17b61e3c3f1e2a184737e23b792b04","target":"graph","created_at":"2026-07-05T08:28:00Z","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/2305.10091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI) technique. However, current studies and applications need to address its scalability, non-stationarity, and trustworthiness. This paper aims to review methods and applications and point out research trends and visionary prospects for the next decade. First, this paper summarizes the basic methods and application scenarios of MARL. Second, this paper outlines the corresponding research methods and their limitations on safety, robustness, generalization, and ethical constraints that need to be addressed in th","authors_text":"Guanjun Liu, Ying Tang, Ziyuan Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-17T09:53:13Z","title":"Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10091","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":"sha256:37e771f0983d4cf933eea07f92e30b813ff476ebec01b6b30902cfecb7cc4706","target":"record","created_at":"2026-07-05T08:28:00Z","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":"15ede375fc000ef4b878da6d0fbf54d37961e07151f5c2b4cf7638135ad70c52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-17T09:53:13Z","title_canon_sha256":"4d243e14b894522b39da98f961768142bf6a3ee4a3df23dce653151ff57d40ac"},"schema_version":"1.0","source":{"id":"2305.10091","kind":"arxiv","version":1}},"canonical_sha256":"81c4316211df3795f8f392bf06750db83d4d4c540913d58d8f359cca6ee71541","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81c4316211df3795f8f392bf06750db83d4d4c540913d58d8f359cca6ee71541","first_computed_at":"2026-07-05T08:28:00.847041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:00.847041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vcUouOWVm0hkWRgYknDa6Id0NPK7MCR+dv6Zmd7WSPsfW//It4zw3psCdj1cHDvpw25bhutTRgBgi83AE6qdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:00.847479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10091","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37e771f0983d4cf933eea07f92e30b813ff476ebec01b6b30902cfecb7cc4706","sha256:13e07fc912d35ab24bd935b1f73b32bb6c17b61e3c3f1e2a184737e23b792b04"],"state_sha256":"80383dc7adb1e83ba0ff96e8ab5a5acec0d01ecfc39a517d236aae01763dd512"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Spt+NapF6c2P4vBZZ67PTGts94CczBbl+MmxbC8CPJVFK04DaZCOyArwt/XnA66T3RgDp8QduEWl74EsL/CcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:36:25.283521Z","bundle_sha256":"4a18e03fc6025527d47a0f8308a2ca7d3a8738c9a5b87eb31fc8de4fcfae373e"}}