{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3J2J6P2HORTIYWD5IC6YURDMPB","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":"8f7bccc1bcd8fb39510870e812ee974c3ec78b2b24062b5f5ab4dea94ab3d8d0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-14T12:21:22Z","title_canon_sha256":"e6f48e85acb625e984122b2dd1495546c15931ddf85fbfd8b5fc5f565d751d3f"},"schema_version":"1.0","source":{"id":"2008.06319","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.06319","created_at":"2026-07-05T01:43:41Z"},{"alias_kind":"arxiv_version","alias_value":"2008.06319v2","created_at":"2026-07-05T01:43:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06319","created_at":"2026-07-05T01:43:41Z"},{"alias_kind":"pith_short_12","alias_value":"3J2J6P2HORTI","created_at":"2026-07-05T01:43:41Z"},{"alias_kind":"pith_short_16","alias_value":"3J2J6P2HORTIYWD5","created_at":"2026-07-05T01:43:41Z"},{"alias_kind":"pith_short_8","alias_value":"3J2J6P2H","created_at":"2026-07-05T01:43:41Z"}],"graph_snapshots":[{"event_id":"sha256:dba8379c75e3bffbaa226aa057a14878ce7564870b932549d246ad5c74a7115b","target":"graph","created_at":"2026-07-05T01:43:41Z","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/2008.06319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Christian D. Hubbs, Hector D. Perez, Ignacio E. Grossmann, John M. Wassick, Nikolaos V. Sahinidis, Owais Sarwar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-14T12:21:22Z","title":"OR-Gym: A Reinforcement Learning Library for Operations Research Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06319","kind":"arxiv","version":2},"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":"sha256:15df4f7277a4a2cc17be9b84d1dbeaff3eabfeb72f2cefd48c824ec671a5e4f5","target":"record","created_at":"2026-07-05T01:43:41Z","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":"8f7bccc1bcd8fb39510870e812ee974c3ec78b2b24062b5f5ab4dea94ab3d8d0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-08-14T12:21:22Z","title_canon_sha256":"e6f48e85acb625e984122b2dd1495546c15931ddf85fbfd8b5fc5f565d751d3f"},"schema_version":"1.0","source":{"id":"2008.06319","kind":"arxiv","version":2}},"canonical_sha256":"da749f3f4774668c587d40bd8a446c786e012f401ec9b2d60f4525ee992d3095","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da749f3f4774668c587d40bd8a446c786e012f401ec9b2d60f4525ee992d3095","first_computed_at":"2026-07-05T01:43:41.168277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:41.168277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1bca+b7oD0uYfgeQhUHuKrKYMXTzja/XmGLO8g3BxqDSXWCuTSDVtzROqrywkHnvmVnUy+AGBohXLy4FcCqAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:41.168712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.06319","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15df4f7277a4a2cc17be9b84d1dbeaff3eabfeb72f2cefd48c824ec671a5e4f5","sha256:dba8379c75e3bffbaa226aa057a14878ce7564870b932549d246ad5c74a7115b"],"state_sha256":"cffe2aa1cdce942d2c927d4e9de87327d857677e8de793ab95e2788e6cd9a9d9"}