{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2LZS4JWIIVY4UVOERENT2Q2KQF","short_pith_number":"pith:2LZS4JWI","schema_version":"1.0","canonical_sha256":"d2f32e26c84571ca55c4891b3d434a815147ab607e26653d9d40018e387d1aad","source":{"kind":"arxiv","id":"2006.04037","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Hardik Meisheri, Harshad Khadilkar, Nazneen N Sultana, Somjit Nath, Vinita Baniwal","submitted_at":"2020-06-07T04:02:59Z","abstract_excerpt":"This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. The problem description and solution are both adapted from a real-world business solution. The novelty of this problem with respect to supply chain literature is (i) we consider concurrent inventory management of a large number (50 to 1000) of products with shared capacity, (ii) we consider a multi-node supply chain consisting of a warehouse which supplies three stores, (iii) the warehouse, stores, and transportation from warehouse to stores have finite capacities, (iv) w"},"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":"2006.04037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-07T04:02:59Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"71e8e72881058a225bad15cdea0e7f83d93c9d5c43cb224527be93525993ba69","abstract_canon_sha256":"6ea70321319fba27b9bb69752e51811c604af747e268fcdf33b5b9a10592f822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:35.286170Z","signature_b64":"lpgqZWNOmYPvUAF0vbDERkUWgt2P7X2SkcyU5zO6XCva6AJHFpmteAjIJIKBptpi7PVywq32G0zvxzFvlFoJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2f32e26c84571ca55c4891b3d434a815147ab607e26653d9d40018e387d1aad","last_reissued_at":"2026-07-05T01:08:35.285590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:35.285590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Multi-Product Multi-Node Inventory Management in Supply Chains","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaraman Ravindran, Hardik Meisheri, Harshad Khadilkar, Nazneen N Sultana, Somjit Nath, Vinita Baniwal","submitted_at":"2020-06-07T04:02:59Z","abstract_excerpt":"This paper describes the application of reinforcement learning (RL) to multi-product inventory management in supply chains. The problem description and solution are both adapted from a real-world business solution. The novelty of this problem with respect to supply chain literature is (i) we consider concurrent inventory management of a large number (50 to 1000) of products with shared capacity, (ii) we consider a multi-node supply chain consisting of a warehouse which supplies three stores, (iii) the warehouse, stores, and transportation from warehouse to stores have finite capacities, (iv) w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04037","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/2006.04037/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":"2006.04037","created_at":"2026-07-05T01:08:35.285662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04037v1","created_at":"2026-07-05T01:08:35.285662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04037","created_at":"2026-07-05T01:08:35.285662+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LZS4JWIIVY4","created_at":"2026-07-05T01:08:35.285662+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LZS4JWIIVY4UVOE","created_at":"2026-07-05T01:08:35.285662+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LZS4JWI","created_at":"2026-07-05T01:08:35.285662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09417","citing_title":"A Survey of Reinforcement Learning for Optimization in Automation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF","json":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF.json","graph_json":"https://pith.science/api/pith-number/2LZS4JWIIVY4UVOERENT2Q2KQF/graph.json","events_json":"https://pith.science/api/pith-number/2LZS4JWIIVY4UVOERENT2Q2KQF/events.json","paper":"https://pith.science/paper/2LZS4JWI"},"agent_actions":{"view_html":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF","download_json":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF.json","view_paper":"https://pith.science/paper/2LZS4JWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04037&json=true","fetch_graph":"https://pith.science/api/pith-number/2LZS4JWIIVY4UVOERENT2Q2KQF/graph.json","fetch_events":"https://pith.science/api/pith-number/2LZS4JWIIVY4UVOERENT2Q2KQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF/action/storage_attestation","attest_author":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF/action/author_attestation","sign_citation":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF/action/citation_signature","submit_replication":"https://pith.science/pith/2LZS4JWIIVY4UVOERENT2Q2KQF/action/replication_record"}},"created_at":"2026-07-05T01:08:35.285662+00:00","updated_at":"2026-07-05T01:08:35.285662+00:00"}