{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q2N36Q7D7LVDTSJ6ZV2GD2FOKG","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":"e044de356264dba7a0e4421046567ea5f5e3dd110a34eefcb4482d9523fafd33","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T09:18:30Z","title_canon_sha256":"573c6ce4b159f029914c3dc71a46e4cdb2c5dc62570b447fb5879beeb9ad04f8"},"schema_version":"1.0","source":{"id":"2412.15700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15700","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15700v2","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15700","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"Q2N36Q7D7LVD","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"Q2N36Q7D7LVDTSJ6","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"Q2N36Q7D","created_at":"2026-07-05T09:55:15Z"}],"graph_snapshots":[{"event_id":"sha256:2e4abf6e868c10621cc712d379b25a2b298b0eccd1293f5c6a2a3c4188d95b9c","target":"graph","created_at":"2026-07-05T09:55:15Z","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/2412.15700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration in cooperative multi-agent reinforcement learning (MARL) remains challenging for value-based agents due to the absence of an explicit policy. Existing approaches include individual exploration based on uncertainty towards the system and collective exploration through behavioral diversity among agents. However, the introduction of additional structures often leads to reduced training efficiency and infeasible integration of these methods. In this paper, we propose Adaptive exploration via Identity Recognition~(AIR), which consists of two adversarial components: a classifier that rec","authors_text":"Guangchong Zhou, Guoliang Fan, Zeren Zhang","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T09:18:30Z","title":"AIR: Unifying Individual and Collective Exploration in Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15700","kind":"arxiv","version":2},"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:df1c9a19567aba61a83b5398d5ed03bfbf1d0564db7c0b5a946a6e1313e100ae","target":"record","created_at":"2026-07-05T09:55:15Z","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":"e044de356264dba7a0e4421046567ea5f5e3dd110a34eefcb4482d9523fafd33","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-20T09:18:30Z","title_canon_sha256":"573c6ce4b159f029914c3dc71a46e4cdb2c5dc62570b447fb5879beeb9ad04f8"},"schema_version":"1.0","source":{"id":"2412.15700","kind":"arxiv","version":2}},"canonical_sha256":"869bbf43e3faea39c93ecd7461e8ae51ab166edd8b03257161ecf7eb9ea7b4a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"869bbf43e3faea39c93ecd7461e8ae51ab166edd8b03257161ecf7eb9ea7b4a1","first_computed_at":"2026-07-05T09:55:15.292241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:15.292241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mcRD+UoqKHUMqi09tiPeUqkrDfIXdd453VDrcRgh/fN01+Jc9uEflaXIPExPUOV+QmO8kcPnDcolHHiJru5sDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:15.292699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df1c9a19567aba61a83b5398d5ed03bfbf1d0564db7c0b5a946a6e1313e100ae","sha256:2e4abf6e868c10621cc712d379b25a2b298b0eccd1293f5c6a2a3c4188d95b9c"],"state_sha256":"70747f0b8acba94c7516184d5ae06f55eb0f59948e963d4fd9484eef136a08d5"}