{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AKUB4K2ZUMQXQKMIW7WHZF3VR4","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":"de2f4fc03b6689c437677b8d34726465baa3f01064564659786fb3625a68dba4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T09:38:41Z","title_canon_sha256":"a8e131a886012903601f47bc9c1bb37068bb6b206e4b722d63f87443867e4453"},"schema_version":"1.0","source":{"id":"2608.08604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08604","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08604v1","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08604","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"AKUB4K2ZUMQX","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"AKUB4K2ZUMQXQKMI","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"AKUB4K2Z","created_at":"2026-08-11T01:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:394f02e866cb8b3903c18aae86a1f2f4babadf6356968961f3f5cf27be77e48e","target":"graph","created_at":"2026-08-11T01:23:08Z","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/2608.08604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions. Designing such rewards is challenging, especially in systems with heterogeneous agents, where a single scalar objective may fail to capture diverse behaviors. In this paper, we introduce Multi-AGent Preference-Integrated lEarning (MAGPIE), which addresses these challenges through agent-specific preference modeling. Each agent is evaluated by a dedicated expert through preference signals, eliminating the need for global evaluat","authors_text":"Ni Mu, Qing-Shan Jia, Yao Luan, Yiqin Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T09:38:41Z","title":"Multi-Agent Reinforcement Learning via Agent-Specific Preference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08604","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":"sha256:3d8a7fc2c4a7b0a353d3aedfb0001e4a0a1e868d09d686a5d1df654620bb191b","target":"record","created_at":"2026-08-11T01:23:08Z","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":"de2f4fc03b6689c437677b8d34726465baa3f01064564659786fb3625a68dba4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T09:38:41Z","title_canon_sha256":"a8e131a886012903601f47bc9c1bb37068bb6b206e4b722d63f87443867e4453"},"schema_version":"1.0","source":{"id":"2608.08604","kind":"arxiv","version":1}},"canonical_sha256":"02a81e2b59a321782988b7ec7c97758f1d1f6d24e3faca50f64a9f84188d5231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02a81e2b59a321782988b7ec7c97758f1d1f6d24e3faca50f64a9f84188d5231","first_computed_at":"2026-08-11T01:23:08.094052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:23:08.094052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V0pwcSOwOCo6eYhegcwg5HjsE15+E/nrnjGbiRRQNv+EqsKl5QgFRfq3DJSzAtSHhgPvm2l1qgf07QnMN2M5Ag==","signature_status":"signed_v1","signed_at":"2026-08-11T01:23:08.096510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d8a7fc2c4a7b0a353d3aedfb0001e4a0a1e868d09d686a5d1df654620bb191b","sha256:394f02e866cb8b3903c18aae86a1f2f4babadf6356968961f3f5cf27be77e48e"],"state_sha256":"39381fb670bbfcf8fca764880b9eab7187ab96caaafd96ff5a0f38f42d635eeb"}