{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3J2J6P2HORTIYWD5IC6YURDMPB","short_pith_number":"pith:3J2J6P2H","schema_version":"1.0","canonical_sha256":"da749f3f4774668c587d40bd8a446c786e012f401ec9b2d60f4525ee992d3095","source":{"kind":"arxiv","id":"2008.06319","version":2},"attestation_state":"computed","paper":{"title":"OR-Gym: A Reinforcement Learning Library for Operations Research Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian D. Hubbs, Hector D. Perez, Ignacio E. Grossmann, John M. Wassick, Nikolaos V. Sahinidis, Owais Sarwar","submitted_at":"2020-08-14T12:21:22Z","abstract_excerpt":"Reinforcement learning (RL) has been widely applied to game-playing and surpassed the best human-level performance in many domains, yet there are few use-cases in industrial or commercial settings. We introduce OR-Gym, an open-source library for developing reinforcement learning algorithms to address operations research problems. In this paper, we apply reinforcement learning to the knapsack, multi-dimensional bin packing, multi-echelon supply chain, and multi-period asset allocation model problems, as well as benchmark the RL solutions against MILP and heuristic models. These problems are use"},"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":"2008.06319","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-14T12:21:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e6f48e85acb625e984122b2dd1495546c15931ddf85fbfd8b5fc5f565d751d3f","abstract_canon_sha256":"8f7bccc1bcd8fb39510870e812ee974c3ec78b2b24062b5f5ab4dea94ab3d8d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:41.168712Z","signature_b64":"1bca+b7oD0uYfgeQhUHuKrKYMXTzja/XmGLO8g3BxqDSXWCuTSDVtzROqrywkHnvmVnUy+AGBohXLy4FcCqAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da749f3f4774668c587d40bd8a446c786e012f401ec9b2d60f4525ee992d3095","last_reissued_at":"2026-07-05T01:43:41.168277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:41.168277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OR-Gym: A Reinforcement Learning Library for Operations Research Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian D. Hubbs, Hector D. Perez, Ignacio E. Grossmann, John M. Wassick, Nikolaos V. Sahinidis, Owais Sarwar","submitted_at":"2020-08-14T12:21:22Z","abstract_excerpt":"Reinforcement learning (RL) has been widely applied to game-playing and surpassed the best human-level performance in many domains, yet there are few use-cases in industrial or commercial settings. We introduce OR-Gym, an open-source library for developing reinforcement learning algorithms to address operations research problems. In this paper, we apply reinforcement learning to the knapsack, multi-dimensional bin packing, multi-echelon supply chain, and multi-period asset allocation model problems, as well as benchmark the RL solutions against MILP and heuristic models. These problems are use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06319","kind":"arxiv","version":2},"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/2008.06319/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":"2008.06319","created_at":"2026-07-05T01:43:41.168343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06319v2","created_at":"2026-07-05T01:43:41.168343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06319","created_at":"2026-07-05T01:43:41.168343+00:00"},{"alias_kind":"pith_short_12","alias_value":"3J2J6P2HORTI","created_at":"2026-07-05T01:43:41.168343+00:00"},{"alias_kind":"pith_short_16","alias_value":"3J2J6P2HORTIYWD5","created_at":"2026-07-05T01:43:41.168343+00:00"},{"alias_kind":"pith_short_8","alias_value":"3J2J6P2H","created_at":"2026-07-05T01:43:41.168343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28706","citing_title":"Robust Markov Decision Processes on Continuous State Spaces","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05261","citing_title":"ICNN-enhanced 2SP: Leveraging input convex neural networks for solving two-stage stochastic programming","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12768","citing_title":"ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11355","citing_title":"gym-invmgmt: An Open Benchmarking Framework for Inventory Management Methods","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06516","citing_title":"Learning to Cut: Reinforcement Learning for Benders Decomposition","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB","json":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB.json","graph_json":"https://pith.science/api/pith-number/3J2J6P2HORTIYWD5IC6YURDMPB/graph.json","events_json":"https://pith.science/api/pith-number/3J2J6P2HORTIYWD5IC6YURDMPB/events.json","paper":"https://pith.science/paper/3J2J6P2H"},"agent_actions":{"view_html":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB","download_json":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB.json","view_paper":"https://pith.science/paper/3J2J6P2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06319&json=true","fetch_graph":"https://pith.science/api/pith-number/3J2J6P2HORTIYWD5IC6YURDMPB/graph.json","fetch_events":"https://pith.science/api/pith-number/3J2J6P2HORTIYWD5IC6YURDMPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB/action/storage_attestation","attest_author":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB/action/author_attestation","sign_citation":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB/action/citation_signature","submit_replication":"https://pith.science/pith/3J2J6P2HORTIYWD5IC6YURDMPB/action/replication_record"}},"created_at":"2026-07-05T01:43:41.168343+00:00","updated_at":"2026-07-05T01:43:41.168343+00:00"}