{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TEB4SM5RTZRNQ4MCEXAZGEESIZ","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":"280ee425504098bfc5b57948c62d8130bfe0e4388e7810ce96158454558f9366","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T15:30:30Z","title_canon_sha256":"d788e3670e701c597fc19a6d527cae5fa0895f5b97311a33b97f92c8d4f87788"},"schema_version":"1.0","source":{"id":"2606.15862","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.15862","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.15862v2","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.15862","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"TEB4SM5RTZRN","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"TEB4SM5RTZRNQ4MC","created_at":"2026-06-19T16:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"TEB4SM5R","created_at":"2026-06-19T16:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:99515c33307df934211c5552eca40ea9e0ed6b53fe0a0fb3593ab4c5c0aef609","target":"graph","created_at":"2026-06-19T16:12:56Z","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/2606.15862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jingtong Wu, Jun Wang, Linghua Zhang, Zhisong Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T15:30:30Z","title":"RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.15862","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":"sha256:21826505ea2260f8b1de4600021240286ae8f3df6c99017bfcff8d6eb24db7d2","target":"record","created_at":"2026-06-19T16:12:56Z","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":"280ee425504098bfc5b57948c62d8130bfe0e4388e7810ce96158454558f9366","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T15:30:30Z","title_canon_sha256":"d788e3670e701c597fc19a6d527cae5fa0895f5b97311a33b97f92c8d4f87788"},"schema_version":"1.0","source":{"id":"2606.15862","kind":"arxiv","version":2}},"canonical_sha256":"9903c933b19e62d8718225c1931092464069129c6fc47c69e084b6e74674bef8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9903c933b19e62d8718225c1931092464069129c6fc47c69e084b6e74674bef8","first_computed_at":"2026-06-19T16:12:56.139117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:56.139117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/g0LiedzW8Iu2fB4CEq869/YFY1MEwfpgfv1gR2iituF71v8XV0vPXVgL+Fau4mTmBpillA5OGId8rlCzP6Ag==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:56.139532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.15862","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21826505ea2260f8b1de4600021240286ae8f3df6c99017bfcff8d6eb24db7d2","sha256:99515c33307df934211c5552eca40ea9e0ed6b53fe0a0fb3593ab4c5c0aef609"],"state_sha256":"4361010ed0add6e334519b451cb4bff39810d24cd53fee309fde66e8bbb70e84"}