{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G2LEPIFCJEDPUOZBHDWCBGSBHI","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":"e5e2d9612b47fd99d80a18e8202bc5197fae44f3d3324086cf0efed8deecebe7","cross_cats_sorted":["cs.LG","econ.EM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-16T23:27:21Z","title_canon_sha256":"a4133f79ee291c80ac97a2c6fb474c3aea760242ccb791f5cfab259ba4e90dc9"},"schema_version":"1.0","source":{"id":"2405.10469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10469","created_at":"2026-07-05T08:20:00Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10469v1","created_at":"2026-07-05T08:20:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10469","created_at":"2026-07-05T08:20:00Z"},{"alias_kind":"pith_short_12","alias_value":"G2LEPIFCJEDP","created_at":"2026-07-05T08:20:00Z"},{"alias_kind":"pith_short_16","alias_value":"G2LEPIFCJEDPUOZB","created_at":"2026-07-05T08:20:00Z"},{"alias_kind":"pith_short_8","alias_value":"G2LEPIFC","created_at":"2026-07-05T08:20:00Z"}],"graph_snapshots":[{"event_id":"sha256:37bdd0096aef5b6c3ed78208e4f0e01fa183934a9ad0e0d5bfe04aec015eb79b","target":"graph","created_at":"2026-07-05T08:20:00Z","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/2405.10469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of open benchmarking platforms could greatly accelerate the adoption of AI agents in retail. This paper presents comprehensive simulations of customer shopping behaviors for the purpose of benchmarking reinforcement learning (RL) agents that optimize coupon targeting. The difficulty of this learning problem is largely driven by the sparsity of customer purchase events. We trained agents using offline batch data comprising summarized customer purchase histories to help mitigate this effect. Our experiments revealed that contextual bandit and deep RL methods that are less prone t","authors_text":"Joshua Mabry, Sriram Narayanamoorthy, Yu Xia, Zhengyuan Zhou","cross_cats":["cs.LG","econ.EM","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-16T23:27:21Z","title":"Simulation-Based Benchmarking of Reinforcement Learning Agents for Personalized Retail Promotions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10469","kind":"arxiv","version":1},"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":"sha256:688a032520fc12d68c46e82156ca1337d89f02001fb1c38f201ad4ae5fb85c29","target":"record","created_at":"2026-07-05T08:20:00Z","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":"e5e2d9612b47fd99d80a18e8202bc5197fae44f3d3324086cf0efed8deecebe7","cross_cats_sorted":["cs.LG","econ.EM","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-16T23:27:21Z","title_canon_sha256":"a4133f79ee291c80ac97a2c6fb474c3aea760242ccb791f5cfab259ba4e90dc9"},"schema_version":"1.0","source":{"id":"2405.10469","kind":"arxiv","version":1}},"canonical_sha256":"369647a0a24906fa3b2138ec209a413a04f7e22956c39e7cfb5b3690b55cf7b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"369647a0a24906fa3b2138ec209a413a04f7e22956c39e7cfb5b3690b55cf7b0","first_computed_at":"2026-07-05T08:20:00.498083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:00.498083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKHwQkfm9Cyg1gQkfH/1gl1S8+h3BdR6vM8WNCXo3UXtoDSEWAA8Pwnyc1cHikmihnrnvCaKF6Ge4vsXPgLzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:00.498457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:688a032520fc12d68c46e82156ca1337d89f02001fb1c38f201ad4ae5fb85c29","sha256:37bdd0096aef5b6c3ed78208e4f0e01fa183934a9ad0e0d5bfe04aec015eb79b"],"state_sha256":"f49061fc14a4b823a6522c4929cf06fe905c9ad5676512734c0e4978d9b69df9"}