{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QSMK7UNZIOE3UXFJOAGPQCNHVP","short_pith_number":"pith:QSMK7UNZ","schema_version":"1.0","canonical_sha256":"8498afd1b94389ba5ca9700cf809a7abd472215575e01048c75cb6bbac66ab21","source":{"kind":"arxiv","id":"2507.22040","version":1},"attestation_state":"computed","paper":{"title":"Structure-Informed Deep Reinforcement Learning for Inventory Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Akhil Bagaria, Alvaro Maggiar, Carson Eisenach, Dean Foster, Dominique Perrault-Joncas, Omer Gottesman, Sohrab Andaz","submitted_at":"2025-07-29T17:41:45Z","abstract_excerpt":"This paper investigates the application of Deep Reinforcement Learning (DRL) to classical inventory management problems, with a focus on practical implementation considerations. We apply a DRL algorithm based on DirectBackprop to several fundamental inventory management scenarios including multi-period systems with lost sales (with and without lead times), perishable inventory management, dual sourcing, and joint inventory procurement and removal. The DRL approach learns policies across products using only historical information that would be available in practice, avoiding unrealistic assumpt"},"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":"2507.22040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T17:41:45Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"c90236bec701fcc2e01d60db22d78096d6160afe8ef5a6c94689095cdde463c7","abstract_canon_sha256":"58c89905f64a99e32c587f97a5851f8e97d59ee0afb5e17be5b52b77e1096a5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:12.070374Z","signature_b64":"7ViUU2yNjqHI7ZQqcNAPBG5wzsK6P/kpru3CeaEA5PZ01zmRpXdm+3OjZl7oQ28Agi1fL1aS5KDpwIeAtPHSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8498afd1b94389ba5ca9700cf809a7abd472215575e01048c75cb6bbac66ab21","last_reissued_at":"2026-07-05T11:45:12.069957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:12.069957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Informed Deep Reinforcement Learning for Inventory Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Akhil Bagaria, Alvaro Maggiar, Carson Eisenach, Dean Foster, Dominique Perrault-Joncas, Omer Gottesman, Sohrab Andaz","submitted_at":"2025-07-29T17:41:45Z","abstract_excerpt":"This paper investigates the application of Deep Reinforcement Learning (DRL) to classical inventory management problems, with a focus on practical implementation considerations. We apply a DRL algorithm based on DirectBackprop to several fundamental inventory management scenarios including multi-period systems with lost sales (with and without lead times), perishable inventory management, dual sourcing, and joint inventory procurement and removal. The DRL approach learns policies across products using only historical information that would be available in practice, avoiding unrealistic assumpt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22040","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/2507.22040/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":"2507.22040","created_at":"2026-07-05T11:45:12.070010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22040v1","created_at":"2026-07-05T11:45:12.070010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22040","created_at":"2026-07-05T11:45:12.070010+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSMK7UNZIOE3","created_at":"2026-07-05T11:45:12.070010+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSMK7UNZIOE3UXFJ","created_at":"2026-07-05T11:45:12.070010+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSMK7UNZ","created_at":"2026-07-05T11:45:12.070010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP","json":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP.json","graph_json":"https://pith.science/api/pith-number/QSMK7UNZIOE3UXFJOAGPQCNHVP/graph.json","events_json":"https://pith.science/api/pith-number/QSMK7UNZIOE3UXFJOAGPQCNHVP/events.json","paper":"https://pith.science/paper/QSMK7UNZ"},"agent_actions":{"view_html":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP","download_json":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP.json","view_paper":"https://pith.science/paper/QSMK7UNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22040&json=true","fetch_graph":"https://pith.science/api/pith-number/QSMK7UNZIOE3UXFJOAGPQCNHVP/graph.json","fetch_events":"https://pith.science/api/pith-number/QSMK7UNZIOE3UXFJOAGPQCNHVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP/action/storage_attestation","attest_author":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP/action/author_attestation","sign_citation":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP/action/citation_signature","submit_replication":"https://pith.science/pith/QSMK7UNZIOE3UXFJOAGPQCNHVP/action/replication_record"}},"created_at":"2026-07-05T11:45:12.070010+00:00","updated_at":"2026-07-05T11:45:12.070010+00:00"}