{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YAU3725BCSYVG6KWA726RMZHIP","short_pith_number":"pith:YAU3725B","schema_version":"1.0","canonical_sha256":"c029bfeba114b153795607f5e8b32743f968d9ae9915779eca5ca5e4e85258ee","source":{"kind":"arxiv","id":"2208.04957","version":3},"attestation_state":"computed","paper":{"title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.NE","authors_text":"Chao Qian, Cong Guan, Haobo Fu, Ke Xue, Lei Yuan, Qiang Fu, Yang Yu, Yutong Wang","submitted_at":"2022-08-09T16:16:28Z","abstract_excerpt":"Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some studies have made progress in ZSC by exposing the agents to diverse partners during the training process. They usually involve self-play when training the partners, implicitly assuming that the tasks are homogeneous. However, many real-world tasks are heterogeneous, and hence previous methods may be inefficient. In this paper, we study the heterogeneous ZSC problem for the first time and propose a general method based o"},"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":"2208.04957","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-08-09T16:16:28Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"2e10f455630777cb50525dc0b63ed8fc0cfc19a8e0d9d6382998252b1239448c","abstract_canon_sha256":"ef821d07582950a82e5bdea97afe11d335ae7d4d16a913a5627d9a302c4d2ba0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:30.451501Z","signature_b64":"wAyardtU73pzCGzj6/nWMPD93xfuWw0VcmMoCz3oyqPdYNf0hnI+ww24/k5jpYFFReIZ0OLahaluJ5fPvc1BCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c029bfeba114b153795607f5e8b32743f968d9ae9915779eca5ca5e4e85258ee","last_reissued_at":"2026-07-05T09:55:30.451001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:30.451001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.NE","authors_text":"Chao Qian, Cong Guan, Haobo Fu, Ke Xue, Lei Yuan, Qiang Fu, Yang Yu, Yutong Wang","submitted_at":"2022-08-09T16:16:28Z","abstract_excerpt":"Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some studies have made progress in ZSC by exposing the agents to diverse partners during the training process. They usually involve self-play when training the partners, implicitly assuming that the tasks are homogeneous. However, many real-world tasks are heterogeneous, and hence previous methods may be inefficient. In this paper, we study the heterogeneous ZSC problem for the first time and propose a general method based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04957","kind":"arxiv","version":3},"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/2208.04957/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":"2208.04957","created_at":"2026-07-05T09:55:30.451058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.04957v3","created_at":"2026-07-05T09:55:30.451058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04957","created_at":"2026-07-05T09:55:30.451058+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAU3725BCSYV","created_at":"2026-07-05T09:55:30.451058+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAU3725BCSYVG6KW","created_at":"2026-07-05T09:55:30.451058+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAU3725B","created_at":"2026-07-05T09:55:30.451058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16718","citing_title":"Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP","json":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP.json","graph_json":"https://pith.science/api/pith-number/YAU3725BCSYVG6KWA726RMZHIP/graph.json","events_json":"https://pith.science/api/pith-number/YAU3725BCSYVG6KWA726RMZHIP/events.json","paper":"https://pith.science/paper/YAU3725B"},"agent_actions":{"view_html":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP","download_json":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP.json","view_paper":"https://pith.science/paper/YAU3725B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.04957&json=true","fetch_graph":"https://pith.science/api/pith-number/YAU3725BCSYVG6KWA726RMZHIP/graph.json","fetch_events":"https://pith.science/api/pith-number/YAU3725BCSYVG6KWA726RMZHIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP/action/storage_attestation","attest_author":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP/action/author_attestation","sign_citation":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP/action/citation_signature","submit_replication":"https://pith.science/pith/YAU3725BCSYVG6KWA726RMZHIP/action/replication_record"}},"created_at":"2026-07-05T09:55:30.451058+00:00","updated_at":"2026-07-05T09:55:30.451058+00:00"}