{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R4BMIJDQDXZE3ES3J4YQVW22H2","short_pith_number":"pith:R4BMIJDQ","schema_version":"1.0","canonical_sha256":"8f02c424701df24d925b4f310adb5a3e9244c7f4a3db6e8b7c928aca919632bd","source":{"kind":"arxiv","id":"2205.15455","version":2},"attestation_state":"computed","paper":{"title":"A Simulation Environment and Reinforcement Learning Method for Waste Reduction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Maarten de Rijke, Mozhdeh Ariannezhad, Paul Groth, Sami Jullien","submitted_at":"2022-05-30T22:48:57Z","abstract_excerpt":"In retail (e.g., grocery stores, apparel shops, online retailers), inventory managers have to balance short-term risk (no items to sell) with long-term-risk (over ordering leading to product waste). This balancing task is made especially hard due to the lack of information about future customer purchases. In this paper, we study the problem of restocking a grocery store's inventory with perishable items over time, from a distributional point of view. The objective is to maximize sales while minimizing waste, with uncertainty about the actual consumption by costumers. This problem is of a high "},"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":"2205.15455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T22:48:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"beaec224f8d5d44d2f8173ea7077f01ec466dc10e84cd94b3dd7644767d52cf3","abstract_canon_sha256":"5d961b8303294758c00330fd0af480d85ddd208d45a22b45a994bb78b7628d7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:04.160232Z","signature_b64":"Rk+nC7b3gDbNSBSQWKmFiIvLbin1PN4T5Lm2Gig13EvEr1fHINl/bhUYWbRxjS/lCLK7WtsV6Li/u6JRl6UECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f02c424701df24d925b4f310adb5a3e9244c7f4a3db6e8b7c928aca919632bd","last_reissued_at":"2026-07-05T06:14:04.159800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:04.159800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simulation Environment and Reinforcement Learning Method for Waste Reduction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Maarten de Rijke, Mozhdeh Ariannezhad, Paul Groth, Sami Jullien","submitted_at":"2022-05-30T22:48:57Z","abstract_excerpt":"In retail (e.g., grocery stores, apparel shops, online retailers), inventory managers have to balance short-term risk (no items to sell) with long-term-risk (over ordering leading to product waste). This balancing task is made especially hard due to the lack of information about future customer purchases. In this paper, we study the problem of restocking a grocery store's inventory with perishable items over time, from a distributional point of view. The objective is to maximize sales while minimizing waste, with uncertainty about the actual consumption by costumers. This problem is of a high "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15455","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/2205.15455/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":"2205.15455","created_at":"2026-07-05T06:14:04.159857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15455v2","created_at":"2026-07-05T06:14:04.159857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15455","created_at":"2026-07-05T06:14:04.159857+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4BMIJDQDXZE","created_at":"2026-07-05T06:14:04.159857+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4BMIJDQDXZE3ES3","created_at":"2026-07-05T06:14:04.159857+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4BMIJDQ","created_at":"2026-07-05T06:14:04.159857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04167","citing_title":"Smart Transportation Without Neurons -- Fair Metro Network Expansion with Tabular Reinforcement Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2","json":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2.json","graph_json":"https://pith.science/api/pith-number/R4BMIJDQDXZE3ES3J4YQVW22H2/graph.json","events_json":"https://pith.science/api/pith-number/R4BMIJDQDXZE3ES3J4YQVW22H2/events.json","paper":"https://pith.science/paper/R4BMIJDQ"},"agent_actions":{"view_html":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2","download_json":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2.json","view_paper":"https://pith.science/paper/R4BMIJDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15455&json=true","fetch_graph":"https://pith.science/api/pith-number/R4BMIJDQDXZE3ES3J4YQVW22H2/graph.json","fetch_events":"https://pith.science/api/pith-number/R4BMIJDQDXZE3ES3J4YQVW22H2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2/action/storage_attestation","attest_author":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2/action/author_attestation","sign_citation":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2/action/citation_signature","submit_replication":"https://pith.science/pith/R4BMIJDQDXZE3ES3J4YQVW22H2/action/replication_record"}},"created_at":"2026-07-05T06:14:04.159857+00:00","updated_at":"2026-07-05T06:14:04.159857+00:00"}