{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MRWDBHDJY5AK5Q3UYZ762BFDFT","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":"47fc8ce9ba8fbb008b3e3e20412424f904ea783dcf7ea2dcf2401aa0262261d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-06-05T03:27:08Z","title_canon_sha256":"f3cd9f3b203afa55937004e9e1c98569d4470e1ea7b9e6fdb97a40c6c85f1f9b"},"schema_version":"1.0","source":{"id":"2106.07551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07551","created_at":"2026-07-05T02:49:06Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07551v1","created_at":"2026-07-05T02:49:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07551","created_at":"2026-07-05T02:49:06Z"},{"alias_kind":"pith_short_12","alias_value":"MRWDBHDJY5AK","created_at":"2026-07-05T02:49:06Z"},{"alias_kind":"pith_short_16","alias_value":"MRWDBHDJY5AK5Q3U","created_at":"2026-07-05T02:49:06Z"},{"alias_kind":"pith_short_8","alias_value":"MRWDBHDJ","created_at":"2026-07-05T02:49:06Z"}],"graph_snapshots":[{"event_id":"sha256:af17196faee1a15ec13113d1230213ca993ecef784e57158ee913a1439363d6c","target":"graph","created_at":"2026-07-05T02:49:06Z","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/2106.07551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms, which produces a self-generated sequence of tasks arising from the coupled population dynamics. By leveraging auto-curricula to induce a population of distinct emergent strategies, PB-MARL has achieved impressive success in tackling multi-agent tasks. Despite remarkable prior arts of distributed RL frameworks, PB-MARL poses new challenges for parallelizing the training frameworks due to the additional complexity of multiple nested workloads between s","authors_text":"Hanjing Wang, Jun Wang, Ming Zhou, Muning Wen, Runzhe Wu, Weinan Zhang, Yaodong Yang, Ying Wen, Ziyu Wan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-06-05T03:27:08Z","title":"MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07551","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":"sha256:5781a60435bc3f1a29562c423560985357c39745f24ea4676b7c2fcaf41bfc50","target":"record","created_at":"2026-07-05T02:49:06Z","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":"47fc8ce9ba8fbb008b3e3e20412424f904ea783dcf7ea2dcf2401aa0262261d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2021-06-05T03:27:08Z","title_canon_sha256":"f3cd9f3b203afa55937004e9e1c98569d4470e1ea7b9e6fdb97a40c6c85f1f9b"},"schema_version":"1.0","source":{"id":"2106.07551","kind":"arxiv","version":1}},"canonical_sha256":"646c309c69c740aec374c67fed04a32cc3b3ef4622b8c9f744e3930fc65cbd88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"646c309c69c740aec374c67fed04a32cc3b3ef4622b8c9f744e3930fc65cbd88","first_computed_at":"2026-07-05T02:49:06.141190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:06.141190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BevuoBlA0Hk7xmhZpQDbBqamWdrKQ8wjXCIJnPD73kyLcf/hPIRqnWMzv58+dum/KVLvFUDdEpAbSWdZ228cDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:06.141578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5781a60435bc3f1a29562c423560985357c39745f24ea4676b7c2fcaf41bfc50","sha256:af17196faee1a15ec13113d1230213ca993ecef784e57158ee913a1439363d6c"],"state_sha256":"37e34e430ca554e8d3a0550c81e2bedc045b57d3d38a51f7845b42724609335c"}