{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HRVXPR5GUQQQXCKJTBEHHIBPQC","short_pith_number":"pith:HRVXPR5G","schema_version":"1.0","canonical_sha256":"3c6b77c7a6a4210b8949984873a02f80a49c1eb9cc52b11e5f2808577338511d","source":{"kind":"arxiv","id":"2505.18595","version":1},"attestation_state":"computed","paper":{"title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Hong Thanh Nguyen, The Viet Bui, Tien Mai","submitted_at":"2025-05-24T08:43:42Z","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"},"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":"2505.18595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T08:43:42Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8d99887f9f349cc0bdb0df032db0efbf6c572ceb4c1e65b6e06f0d42e0417767","abstract_canon_sha256":"62865a94b63b52ec6663fefb34fa9aab086921d3179fece6a81e80e6edd3d56a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:16.273103Z","signature_b64":"/CDoumdSXqK2qLAuACfp2R73ua+mv1B+QUKFDWht6hSEuySR+yHfBG+jm5m6fElFZNLu5PL/WD8Qz/D4WBpTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6b77c7a6a4210b8949984873a02f80a49c1eb9cc52b11e5f2808577338511d","last_reissued_at":"2026-07-05T11:09:16.272652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:16.272652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MisoDICE: Multi-Agent Imitation from Unlabeled Mixed-Quality Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Hong Thanh Nguyen, The Viet Bui, Tien Mai","submitted_at":"2025-05-24T08:43:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18595","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/2505.18595/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":"2505.18595","created_at":"2026-07-05T11:09:16.272713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18595v1","created_at":"2026-07-05T11:09:16.272713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18595","created_at":"2026-07-05T11:09:16.272713+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRVXPR5GUQQQ","created_at":"2026-07-05T11:09:16.272713+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRVXPR5GUQQQXCKJ","created_at":"2026-07-05T11:09:16.272713+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRVXPR5G","created_at":"2026-07-05T11:09:16.272713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.14159","citing_title":"MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC","json":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC.json","graph_json":"https://pith.science/api/pith-number/HRVXPR5GUQQQXCKJTBEHHIBPQC/graph.json","events_json":"https://pith.science/api/pith-number/HRVXPR5GUQQQXCKJTBEHHIBPQC/events.json","paper":"https://pith.science/paper/HRVXPR5G"},"agent_actions":{"view_html":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC","download_json":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC.json","view_paper":"https://pith.science/paper/HRVXPR5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18595&json=true","fetch_graph":"https://pith.science/api/pith-number/HRVXPR5GUQQQXCKJTBEHHIBPQC/graph.json","fetch_events":"https://pith.science/api/pith-number/HRVXPR5GUQQQXCKJTBEHHIBPQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC/action/storage_attestation","attest_author":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC/action/author_attestation","sign_citation":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC/action/citation_signature","submit_replication":"https://pith.science/pith/HRVXPR5GUQQQXCKJTBEHHIBPQC/action/replication_record"}},"created_at":"2026-07-05T11:09:16.272713+00:00","updated_at":"2026-07-05T11:09:16.272713+00:00"}