{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HXAF55S4FCUYLHEH6STBQMSAFT","short_pith_number":"pith:HXAF55S4","schema_version":"1.0","canonical_sha256":"3dc05ef65c28a9859c87f4a61832402cdc6af1640c59b6b03fcce1897f828180","source":{"kind":"arxiv","id":"2507.20143","version":1},"attestation_state":"computed","paper":{"title":"Concept Learning for Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunlin Chen, Yuanyang Zhu, Zhonghan Ge","submitted_at":"2025-07-27T06:22:24Z","abstract_excerpt":"Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via concept bottleneck models, which promote trustworthiness by conditioning credit assignment on an intermediate level of human-like cooperation concepts. To address this problem, we propose a novel value-based method, named Concepts learni"},"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":"2507.20143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-27T06:22:24Z","cross_cats_sorted":[],"title_canon_sha256":"449a8e8cec3ea1aff4924d36a77747662dc4f4f53e1de9b51439a1495a60f3e4","abstract_canon_sha256":"ec5d1358cca40aa56735b684c383542ac6dc8196ffdc091f48fc3c4316c628dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:14.000473Z","signature_b64":"6KAMhkJrBCKS//0oWy6l9Dfggwoq0dBoaGWSGSwU8lT2vWAEMc12q+fF/TPWiWu2nAR9r1nNqkamVESr1iM8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dc05ef65c28a9859c87f4a61832402cdc6af1640c59b6b03fcce1897f828180","last_reissued_at":"2026-07-05T11:44:14.000101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:14.000101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept Learning for Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunlin Chen, Yuanyang Zhu, Zhonghan Ge","submitted_at":"2025-07-27T06:22:24Z","abstract_excerpt":"Despite substantial progress in applying neural networks (NN) to multi-agent reinforcement learning (MARL) areas, they still largely suffer from a lack of transparency and interoperability. However, its implicit cooperative mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via concept bottleneck models, which promote trustworthiness by conditioning credit assignment on an intermediate level of human-like cooperation concepts. To address this problem, we propose a novel value-based method, named Concepts learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20143","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/2507.20143/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":"2507.20143","created_at":"2026-07-05T11:44:14.000160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20143v1","created_at":"2026-07-05T11:44:14.000160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20143","created_at":"2026-07-05T11:44:14.000160+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXAF55S4FCUY","created_at":"2026-07-05T11:44:14.000160+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXAF55S4FCUYLHEH","created_at":"2026-07-05T11:44:14.000160+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXAF55S4","created_at":"2026-07-05T11:44:14.000160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT","json":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT.json","graph_json":"https://pith.science/api/pith-number/HXAF55S4FCUYLHEH6STBQMSAFT/graph.json","events_json":"https://pith.science/api/pith-number/HXAF55S4FCUYLHEH6STBQMSAFT/events.json","paper":"https://pith.science/paper/HXAF55S4"},"agent_actions":{"view_html":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT","download_json":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT.json","view_paper":"https://pith.science/paper/HXAF55S4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20143&json=true","fetch_graph":"https://pith.science/api/pith-number/HXAF55S4FCUYLHEH6STBQMSAFT/graph.json","fetch_events":"https://pith.science/api/pith-number/HXAF55S4FCUYLHEH6STBQMSAFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT/action/storage_attestation","attest_author":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT/action/author_attestation","sign_citation":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT/action/citation_signature","submit_replication":"https://pith.science/pith/HXAF55S4FCUYLHEH6STBQMSAFT/action/replication_record"}},"created_at":"2026-07-05T11:44:14.000160+00:00","updated_at":"2026-07-05T11:44:14.000160+00:00"}