{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LXE7JI4WNRKER4EWHYTOWIPUOK","short_pith_number":"pith:LXE7JI4W","schema_version":"1.0","canonical_sha256":"5dc9f4a3966c5448f0963e26eb21f472894bf27666d708a913167badc33ceef3","source":{"kind":"arxiv","id":"2312.04819","version":2},"attestation_state":"computed","paper":{"title":"Attention-Guided Contrastive Role Representations for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chunlin Chen, Hongyu Ding, Huaxiong Li, Zhi Wang, Zican Hu, Zongzhang Zhang","submitted_at":"2023-12-08T03:40:38Z","abstract_excerpt":"Real-world multi-agent tasks usually involve dynamic team composition with the emergence of roles, which should also be a key to efficient cooperation in multi-agent reinforcement learning (MARL). Drawing inspiration from the correlation between roles and agent's behavior patterns, we propose a novel framework of **A**ttention-guided **CO**ntrastive **R**ole representation learning for **M**ARL (**ACORM**) to promote behavior heterogeneity, knowledge transfer, and skillful coordination across agents. First, we introduce mutual information maximization to formalize role representation learning,"},"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":"2312.04819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-12-08T03:40:38Z","cross_cats_sorted":[],"title_canon_sha256":"9d5ebf8bd3dce6495b58ea03b7be5b9ff5444e7ae2c23af33b2f0fd1f66902c2","abstract_canon_sha256":"afa64025724adf90c5769f3cf0237ff49bc6afa512279ed75fbb538672b00673"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:36.413571Z","signature_b64":"B/Cr4CTMaGKzBA1oJaCVvGhdwGezWz8lCjoqMIKalBz6Y9iX0gESNGJN3tpemsKBUVD4gUcKDk/JrUoQSp5MAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dc9f4a3966c5448f0963e26eb21f472894bf27666d708a913167badc33ceef3","last_reissued_at":"2026-07-05T07:51:36.413085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:36.413085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-Guided Contrastive Role Representations for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chunlin Chen, Hongyu Ding, Huaxiong Li, Zhi Wang, Zican Hu, Zongzhang Zhang","submitted_at":"2023-12-08T03:40:38Z","abstract_excerpt":"Real-world multi-agent tasks usually involve dynamic team composition with the emergence of roles, which should also be a key to efficient cooperation in multi-agent reinforcement learning (MARL). Drawing inspiration from the correlation between roles and agent's behavior patterns, we propose a novel framework of **A**ttention-guided **CO**ntrastive **R**ole representation learning for **M**ARL (**ACORM**) to promote behavior heterogeneity, knowledge transfer, and skillful coordination across agents. First, we introduce mutual information maximization to formalize role representation learning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04819","kind":"arxiv","version":2},"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/2312.04819/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":"2312.04819","created_at":"2026-07-05T07:51:36.413142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04819v2","created_at":"2026-07-05T07:51:36.413142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04819","created_at":"2026-07-05T07:51:36.413142+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXE7JI4WNRKE","created_at":"2026-07-05T07:51:36.413142+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXE7JI4WNRKER4EW","created_at":"2026-07-05T07:51:36.413142+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXE7JI4W","created_at":"2026-07-05T07:51:36.413142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00345","citing_title":"CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK","json":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK.json","graph_json":"https://pith.science/api/pith-number/LXE7JI4WNRKER4EWHYTOWIPUOK/graph.json","events_json":"https://pith.science/api/pith-number/LXE7JI4WNRKER4EWHYTOWIPUOK/events.json","paper":"https://pith.science/paper/LXE7JI4W"},"agent_actions":{"view_html":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK","download_json":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK.json","view_paper":"https://pith.science/paper/LXE7JI4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04819&json=true","fetch_graph":"https://pith.science/api/pith-number/LXE7JI4WNRKER4EWHYTOWIPUOK/graph.json","fetch_events":"https://pith.science/api/pith-number/LXE7JI4WNRKER4EWHYTOWIPUOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK/action/storage_attestation","attest_author":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK/action/author_attestation","sign_citation":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK/action/citation_signature","submit_replication":"https://pith.science/pith/LXE7JI4WNRKER4EWHYTOWIPUOK/action/replication_record"}},"created_at":"2026-07-05T07:51:36.413142+00:00","updated_at":"2026-07-05T07:51:36.413142+00:00"}