{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HRVXPR5GUQQQXCKJTBEHHIBPQC","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":"62865a94b63b52ec6663fefb34fa9aab086921d3179fece6a81e80e6edd3d56a","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T08:43:42Z","title_canon_sha256":"8d99887f9f349cc0bdb0df032db0efbf6c572ceb4c1e65b6e06f0d42e0417767"},"schema_version":"1.0","source":{"id":"2505.18595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18595","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18595v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18595","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"HRVXPR5GUQQQ","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"HRVXPR5GUQQQXCKJ","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"HRVXPR5G","created_at":"2026-07-05T11:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:33f5839e7b9345ef70ee69423d7e35a692c171ac348b334af619c4bd41a9f803","target":"graph","created_at":"2026-07-05T11:09:16Z","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/2505.18595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study offline imitation learning (IL) in cooperative multi-agent settings, where demonstrations have unlabeled mixed quality - containing both expert and suboptimal trajectories. Our proposed solution is structured in two stages: trajectory labeling and multi-agent imitation learning, designed jointly to enable effective learning from heterogeneous, unlabeled data. In the first stage, we combine advances in large language models and preference-based reinforcement learning to construct a progressive labeling pipeline that distinguishes expert-quality trajectories. In the second stage, we int","authors_text":"Hong Thanh Nguyen, The Viet Bui, Tien Mai","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T08:43:42Z","title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18595","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:bf645f37fa86c6b33005475bcbeca0951f3b363608dcfdf261c85a5350a57f95","target":"record","created_at":"2026-07-05T11:09:16Z","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":"62865a94b63b52ec6663fefb34fa9aab086921d3179fece6a81e80e6edd3d56a","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T08:43:42Z","title_canon_sha256":"8d99887f9f349cc0bdb0df032db0efbf6c572ceb4c1e65b6e06f0d42e0417767"},"schema_version":"1.0","source":{"id":"2505.18595","kind":"arxiv","version":1}},"canonical_sha256":"3c6b77c7a6a4210b8949984873a02f80a49c1eb9cc52b11e5f2808577338511d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c6b77c7a6a4210b8949984873a02f80a49c1eb9cc52b11e5f2808577338511d","first_computed_at":"2026-07-05T11:09:16.272652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:16.272652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CDoumdSXqK2qLAuACfp2R73ua+mv1B+QUKFDWht6hSEuySR+yHfBG+jm5m6fElFZNLu5PL/WD8Qz/D4WBpTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:16.273103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf645f37fa86c6b33005475bcbeca0951f3b363608dcfdf261c85a5350a57f95","sha256:33f5839e7b9345ef70ee69423d7e35a692c171ac348b334af619c4bd41a9f803"],"state_sha256":"8a48397e4579baf3c1066feaad6d4f69abbdf3ed605388ade4ccc3a86638330a"}