{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TEB4SM5RTZRNQ4MCEXAZGEESIZ","short_pith_number":"pith:TEB4SM5R","schema_version":"1.0","canonical_sha256":"9903c933b19e62d8718225c1931092464069129c6fc47c69e084b6e74674bef8","source":{"kind":"arxiv","id":"2606.15862","version":2},"attestation_state":"computed","paper":{"title":"RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingtong Wu, Jun Wang, Linghua Zhang, Zhisong Zhang","submitted_at":"2026-06-14T15:30:30Z","abstract_excerpt":"Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, cus"},"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":"2606.15862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T15:30:30Z","cross_cats_sorted":[],"title_canon_sha256":"d788e3670e701c597fc19a6d527cae5fa0895f5b97311a33b97f92c8d4f87788","abstract_canon_sha256":"280ee425504098bfc5b57948c62d8130bfe0e4388e7810ce96158454558f9366"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:56.139532Z","signature_b64":"0/g0LiedzW8Iu2fB4CEq869/YFY1MEwfpgfv1gR2iituF71v8XV0vPXVgL+Fau4mTmBpillA5OGId8rlCzP6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9903c933b19e62d8718225c1931092464069129c6fc47c69e084b6e74674bef8","last_reissued_at":"2026-06-19T16:12:56.139117Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:56.139117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jingtong Wu, Jun Wang, Linghua Zhang, Zhisong Zhang","submitted_at":"2026-06-14T15:30:30Z","abstract_excerpt":"Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for evaluating tool-using LLM agents in single-store supermarket operation. RetailBench models retail management as a partially observable decision process and is designed to support thousand-day-scale simulations. In this environment, agents must manage pricing, replenishment, supplier selection, shelf assortment, inventory aging, cus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.15862","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/2606.15862/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":"2606.15862","created_at":"2026-06-19T16:12:56.139187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.15862v2","created_at":"2026-06-19T16:12:56.139187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.15862","created_at":"2026-06-19T16:12:56.139187+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEB4SM5RTZRN","created_at":"2026-06-19T16:12:56.139187+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEB4SM5RTZRNQ4MC","created_at":"2026-06-19T16:12:56.139187+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEB4SM5R","created_at":"2026-06-19T16:12:56.139187+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/TEB4SM5RTZRNQ4MCEXAZGEESIZ","json":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ.json","graph_json":"https://pith.science/api/pith-number/TEB4SM5RTZRNQ4MCEXAZGEESIZ/graph.json","events_json":"https://pith.science/api/pith-number/TEB4SM5RTZRNQ4MCEXAZGEESIZ/events.json","paper":"https://pith.science/paper/TEB4SM5R"},"agent_actions":{"view_html":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ","download_json":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ.json","view_paper":"https://pith.science/paper/TEB4SM5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.15862&json=true","fetch_graph":"https://pith.science/api/pith-number/TEB4SM5RTZRNQ4MCEXAZGEESIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TEB4SM5RTZRNQ4MCEXAZGEESIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ/action/storage_attestation","attest_author":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ/action/author_attestation","sign_citation":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ/action/citation_signature","submit_replication":"https://pith.science/pith/TEB4SM5RTZRNQ4MCEXAZGEESIZ/action/replication_record"}},"created_at":"2026-06-19T16:12:56.139187+00:00","updated_at":"2026-06-19T16:12:56.139187+00:00"}