{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q2P7S2Z4PVOEOXXKL7PHGG2LAZ","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":"280d06a94d4d83ece8a175b340a5b0679735f7b0d29e1299b125d330df70f22c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-01-02T14:06:52Z","title_canon_sha256":"48d48b811385034f2a4ee38da01289f4f7f964cc3f9fb3361bed2017d9c38e16"},"schema_version":"1.0","source":{"id":"2501.01266","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01266","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01266v1","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01266","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"Q2P7S2Z4PVOE","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"Q2P7S2Z4PVOEOXXK","created_at":"2026-07-05T09:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"Q2P7S2Z4","created_at":"2026-07-05T09:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:ee39f56610df4d5afdf962026aba573bcbd002c22f57483dcd7fa8788e43a611","target":"graph","created_at":"2026-07-05T09:56:17Z","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/2501.01266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While exploration in single-agent reinforcement learning has been studied extensively in recent years, considerably less work has focused on its counterpart in multi-agent reinforcement learning. To address this issue, this work proposes a peer-incentivized reward function inspired by previous research on intrinsic curiosity and influence-based rewards. The \\textit{PIMAEX} reward, short for Peer-Incentivized Multi-Agent Exploration, aims to improve exploration in the multi-agent setting by encouraging agents to exert influence over each other to increase the likelihood of encountering novel st","authors_text":"Claudia Linnhoff-Popien, Gerhard Stenzel, Johannes Tochtermann, Julian Sch\\\"onberger, Michael K\\\"olle, Philipp Altmann","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-01-02T14:06:52Z","title":"PIMAEX: Multi-Agent Exploration through Peer Incentivization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01266","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:e1ee21f99bc85f63226fe0e2e315607e8bb39b6e990a062fbf9e85f2d29bb33f","target":"record","created_at":"2026-07-05T09:56:17Z","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":"280d06a94d4d83ece8a175b340a5b0679735f7b0d29e1299b125d330df70f22c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-01-02T14:06:52Z","title_canon_sha256":"48d48b811385034f2a4ee38da01289f4f7f964cc3f9fb3361bed2017d9c38e16"},"schema_version":"1.0","source":{"id":"2501.01266","kind":"arxiv","version":1}},"canonical_sha256":"869ff96b3c7d5c475eea5fde731b4b0649d574ac7b2c25b0073c8bf39d4d3b27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"869ff96b3c7d5c475eea5fde731b4b0649d574ac7b2c25b0073c8bf39d4d3b27","first_computed_at":"2026-07-05T09:56:17.147515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:17.147515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IqEoY09klSeXu7zzcy8jUf6QFxgJVrGh5ys4tTSzDaHHRc6U5mL/O5HeIOxztZ96mU1AykI9pSJbzsvj1ossBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:17.147973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01266","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1ee21f99bc85f63226fe0e2e315607e8bb39b6e990a062fbf9e85f2d29bb33f","sha256:ee39f56610df4d5afdf962026aba573bcbd002c22f57483dcd7fa8788e43a611"],"state_sha256":"1158c782b929e2f53667ed23c7711058c9183b6f2386392f3488816bb104c0b7"}