{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YAKOOMKQMAF3P42NKNURR3QGDB","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":"55735cb78f5c28734948c51d2498ea05df572e45d4bc46187bd949abdd41dd0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-13T05:22:30Z","title_canon_sha256":"fdd6517907e122894bb9f55f888c31dfbfd5569a6ea887f98306dbcc817bb6e7"},"schema_version":"1.0","source":{"id":"2306.07542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07542","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07542v1","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07542","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"YAKOOMKQMAF3","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"YAKOOMKQMAF3P42N","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"YAKOOMKQ","created_at":"2026-07-05T06:20:06Z"}],"graph_snapshots":[{"event_id":"sha256:7764505a8c6d1b63a7c5e5d6351915ed6ad2f912fdb3f827f731d234e95746b6","target":"graph","created_at":"2026-07-05T06:20:06Z","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/2306.07542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn within a shared environment. This paradigm is applicable to various industrial scenarios such as autonomous driving, quantitative trading, and inventory management. However, applying MARL to these real-world scenarios is impeded by many challenges such as scaling up, complex agent interactions, and non-stationary dynamics. To incentivize the research of MARL on these challenges, we develop MABIM (Multi-Agent Benchmark for Inventory Management) which is a multi-echelon, multi-commodity inventory management ","authors_text":"Chuheng Zhang, Jiang Bian, Lei Song, Li Zhao, Wei Jiang, Xianliang Yang, Zhihao Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-13T05:22:30Z","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07542","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:a3e2105be73b44d6550c10d7a461235579f0e1e80387a6935c259b275acc3dc7","target":"record","created_at":"2026-07-05T06:20:06Z","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":"55735cb78f5c28734948c51d2498ea05df572e45d4bc46187bd949abdd41dd0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-13T05:22:30Z","title_canon_sha256":"fdd6517907e122894bb9f55f888c31dfbfd5569a6ea887f98306dbcc817bb6e7"},"schema_version":"1.0","source":{"id":"2306.07542","kind":"arxiv","version":1}},"canonical_sha256":"c014e73150600bb7f34d536918ee06187a788ebee4a861eec5feea81f832e8a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c014e73150600bb7f34d536918ee06187a788ebee4a861eec5feea81f832e8a2","first_computed_at":"2026-07-05T06:20:06.045832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:06.045832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PbhXyewSJ3iqBcNJJa6DVJ/tptrqGvORRjjgsw8PIsujVoMdpeVfXhZJ/PLC2RXIZhsj8KtkrxJG5446S5MNAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:06.046234Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3e2105be73b44d6550c10d7a461235579f0e1e80387a6935c259b275acc3dc7","sha256:7764505a8c6d1b63a7c5e5d6351915ed6ad2f912fdb3f827f731d234e95746b6"],"state_sha256":"836f99705892beecf7f72ffcec43aa2b46aac9d3adf09442a810036ee05363b5"}