{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LQ5PZ32XYCWKVIPE57PTB2EAWI","short_pith_number":"pith:LQ5PZ32X","schema_version":"1.0","canonical_sha256":"5c3afcef57c0acaaa1e4efdf30e880b231562bfb07b13f3795087421c3d96973","source":{"kind":"arxiv","id":"1912.02572","version":3},"attestation_state":"computed","paper":{"title":"Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning: A Field Experiment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaxi Liu, Xiaoqing Wang, Xingyu Wu, Yidong Zhang, Yuming Deng","submitted_at":"2019-12-05T13:41:03Z","abstract_excerpt":"In this paper we present an end-to-end framework for addressing the problem of dynamic pricing (DP) on E-commerce platform using methods based on deep reinforcement learning (DRL). By using four groups of different business data to represent the states of each time period, we model the dynamic pricing problem as a Markov Decision Process (MDP). Compared with the state-of-the-art DRL-based dynamic pricing algorithms, our approaches make the following three contributions. First, we extend the discrete set problem to the continuous price set. Second, instead of using revenue as the reward functio"},"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":"1912.02572","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-05T13:41:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b2d16327d836e05995f84a049dd03bb6129383c11b0b33a07b57fba88aec5d48","abstract_canon_sha256":"2db8b0b35fd047bbf7df26db5efbc66290eed631d64e91f588fc35557a6374e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:54.337981Z","signature_b64":"3N1ew4AWCIEna3YdcWmDu36qkFQPpz7FTuK9+jhp+vATBTWYmbPIAEmsm4uiAjJetoXc+L9mgyFvB7BGIvjiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3afcef57c0acaaa1e4efdf30e880b231562bfb07b13f3795087421c3d96973","last_reissued_at":"2026-07-05T03:09:54.337499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:54.337499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Pricing on E-commerce Platform with Deep Reinforcement Learning: A Field Experiment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaxi Liu, Xiaoqing Wang, Xingyu Wu, Yidong Zhang, Yuming Deng","submitted_at":"2019-12-05T13:41:03Z","abstract_excerpt":"In this paper we present an end-to-end framework for addressing the problem of dynamic pricing (DP) on E-commerce platform using methods based on deep reinforcement learning (DRL). By using four groups of different business data to represent the states of each time period, we model the dynamic pricing problem as a Markov Decision Process (MDP). Compared with the state-of-the-art DRL-based dynamic pricing algorithms, our approaches make the following three contributions. First, we extend the discrete set problem to the continuous price set. Second, instead of using revenue as the reward functio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02572","kind":"arxiv","version":3},"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/1912.02572/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":"1912.02572","created_at":"2026-07-05T03:09:54.337565+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.02572v3","created_at":"2026-07-05T03:09:54.337565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02572","created_at":"2026-07-05T03:09:54.337565+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ5PZ32XYCWK","created_at":"2026-07-05T03:09:54.337565+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ5PZ32XYCWKVIPE","created_at":"2026-07-05T03:09:54.337565+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ5PZ32X","created_at":"2026-07-05T03:09:54.337565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26787","citing_title":"AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22855","citing_title":"PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI","json":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI.json","graph_json":"https://pith.science/api/pith-number/LQ5PZ32XYCWKVIPE57PTB2EAWI/graph.json","events_json":"https://pith.science/api/pith-number/LQ5PZ32XYCWKVIPE57PTB2EAWI/events.json","paper":"https://pith.science/paper/LQ5PZ32X"},"agent_actions":{"view_html":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI","download_json":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI.json","view_paper":"https://pith.science/paper/LQ5PZ32X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.02572&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ5PZ32XYCWKVIPE57PTB2EAWI/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ5PZ32XYCWKVIPE57PTB2EAWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI/action/storage_attestation","attest_author":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI/action/author_attestation","sign_citation":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI/action/citation_signature","submit_replication":"https://pith.science/pith/LQ5PZ32XYCWKVIPE57PTB2EAWI/action/replication_record"}},"created_at":"2026-07-05T03:09:54.337565+00:00","updated_at":"2026-07-05T03:09:54.337565+00:00"}