{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q3L5CUG3SUBML66BR6F7LIU5CX","short_pith_number":"pith:Q3L5CUG3","schema_version":"1.0","canonical_sha256":"86d7d150db9502c5fbc18f8bf5a29d15d11d08f5078ba1a1ca6eadb1eb188a84","source":{"kind":"arxiv","id":"2507.02698","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning for Dynamic Pricing in Supply Chains: Benchmarking Strategic Agent Behaviours under Realistically Simulated Market Conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.EM"],"primary_cat":"cs.LG","authors_text":"Marijn van Rijswijk, Seyed Sahand Mohammadi Ziabari, Thomas Hazenberg, Yao Ma","submitted_at":"2025-07-03T15:07:37Z","abstract_excerpt":"This study investigates how Multi-Agent Reinforcement Learning (MARL) can improve dynamic pricing strategies in supply chains, particularly in contexts where traditional ERP systems rely on static, rule-based approaches that overlook strategic interactions among market actors. While recent research has applied reinforcement learning to pricing, most implementations remain single-agent and fail to model the interdependent nature of real-world supply chains. This study addresses that gap by evaluating the performance of three MARL algorithms: MADDPG, MADQN, and QMIX against static rule-based bas"},"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":"2507.02698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T15:07:37Z","cross_cats_sorted":["econ.EM"],"title_canon_sha256":"4b1b07a6e9d041272115b30a022db7bee6eceab1ae18eda277c180433432333e","abstract_canon_sha256":"479f32bb6d99e54b500f34a1076395597ed4b36bfc404b54bcc201a69a37af88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:33.333293Z","signature_b64":"TSUnzZsf17UUS8U5xVOUw6HvhhOZ0frPRIKoDMqJnpMxkXe8LP0XKb7DGKJPeerMtG1z98P2ZapuqZj7FvkDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86d7d150db9502c5fbc18f8bf5a29d15d11d08f5078ba1a1ca6eadb1eb188a84","last_reissued_at":"2026-07-05T11:31:33.332863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:33.332863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning for Dynamic Pricing in Supply Chains: Benchmarking Strategic Agent Behaviours under Realistically Simulated Market Conditions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.EM"],"primary_cat":"cs.LG","authors_text":"Marijn van Rijswijk, Seyed Sahand Mohammadi Ziabari, Thomas Hazenberg, Yao Ma","submitted_at":"2025-07-03T15:07:37Z","abstract_excerpt":"This study investigates how Multi-Agent Reinforcement Learning (MARL) can improve dynamic pricing strategies in supply chains, particularly in contexts where traditional ERP systems rely on static, rule-based approaches that overlook strategic interactions among market actors. While recent research has applied reinforcement learning to pricing, most implementations remain single-agent and fail to model the interdependent nature of real-world supply chains. This study addresses that gap by evaluating the performance of three MARL algorithms: MADDPG, MADQN, and QMIX against static rule-based bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02698","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/2507.02698/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":"2507.02698","created_at":"2026-07-05T11:31:33.332924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02698v1","created_at":"2026-07-05T11:31:33.332924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02698","created_at":"2026-07-05T11:31:33.332924+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3L5CUG3SUBM","created_at":"2026-07-05T11:31:33.332924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3L5CUG3SUBML66B","created_at":"2026-07-05T11:31:33.332924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3L5CUG3","created_at":"2026-07-05T11:31:33.332924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26787","citing_title":"AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX","json":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX.json","graph_json":"https://pith.science/api/pith-number/Q3L5CUG3SUBML66BR6F7LIU5CX/graph.json","events_json":"https://pith.science/api/pith-number/Q3L5CUG3SUBML66BR6F7LIU5CX/events.json","paper":"https://pith.science/paper/Q3L5CUG3"},"agent_actions":{"view_html":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX","download_json":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX.json","view_paper":"https://pith.science/paper/Q3L5CUG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02698&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3L5CUG3SUBML66BR6F7LIU5CX/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3L5CUG3SUBML66BR6F7LIU5CX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX/action/storage_attestation","attest_author":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX/action/author_attestation","sign_citation":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX/action/citation_signature","submit_replication":"https://pith.science/pith/Q3L5CUG3SUBML66BR6F7LIU5CX/action/replication_record"}},"created_at":"2026-07-05T11:31:33.332924+00:00","updated_at":"2026-07-05T11:31:33.332924+00:00"}