{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TCOJ3D52FH7VEL3UKYJUALHV22","short_pith_number":"pith:TCOJ3D52","schema_version":"1.0","canonical_sha256":"989c9d8fba29ff522f745613402cf5d6b6c0d1be042e756277fe3738af3954bc","source":{"kind":"arxiv","id":"1805.10000","version":1},"attestation_state":"computed","paper":{"title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"An-xiang Zeng, Jing-Cheng Shi, Qing Da, Shi-Yong Chen, Yang Yu","submitted_at":"2018-05-25T06:39:31Z","abstract_excerpt":"Applying reinforcement learning in physical-world tasks is extremely challenging. It is commonly infeasible to sample a large number of trials, as required by current reinforcement learning methods, in a physical environment. This paper reports our project on using reinforcement learning for better commodity search in Taobao, one of the largest online retail platforms and meanwhile a physical environment with a high sampling cost. Instead of training reinforcement learning in Taobao directly, we present our approach: first we build Virtual Taobao, a simulator learned from historical customer b"},"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":"1805.10000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-05-25T06:39:31Z","cross_cats_sorted":[],"title_canon_sha256":"4bc3f9cbab79106105da466ceb4b92e2fbf989835c90bb54cd5a2b4e53a0bec5","abstract_canon_sha256":"5fe7316fc6c43f1c7052e929fe72d34add86c7df6fc3b86a0a0d500dfebbe02b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:58.526748Z","signature_b64":"jIWdNPXb582Yjh4Ak31k5NHGieyshcoWupQz2Y5Xx4LI/opb1B8r8GO0Xk+h5QNvLRTD7iw6RFtck76TT8/mCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"989c9d8fba29ff522f745613402cf5d6b6c0d1be042e756277fe3738af3954bc","last_reissued_at":"2026-05-18T00:14:58.526170Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:58.526170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"An-xiang Zeng, Jing-Cheng Shi, Qing Da, Shi-Yong Chen, Yang Yu","submitted_at":"2018-05-25T06:39:31Z","abstract_excerpt":"Applying reinforcement learning in physical-world tasks is extremely challenging. It is commonly infeasible to sample a large number of trials, as required by current reinforcement learning methods, in a physical environment. This paper reports our project on using reinforcement learning for better commodity search in Taobao, one of the largest online retail platforms and meanwhile a physical environment with a high sampling cost. Instead of training reinforcement learning in Taobao directly, we present our approach: first we build Virtual Taobao, a simulator learned from historical customer b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10000","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.10000","created_at":"2026-05-18T00:14:58.526277+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10000v1","created_at":"2026-05-18T00:14:58.526277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10000","created_at":"2026-05-18T00:14:58.526277+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCOJ3D52FH7V","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCOJ3D52FH7VEL3U","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCOJ3D52","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18756","citing_title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22","json":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22.json","graph_json":"https://pith.science/api/pith-number/TCOJ3D52FH7VEL3UKYJUALHV22/graph.json","events_json":"https://pith.science/api/pith-number/TCOJ3D52FH7VEL3UKYJUALHV22/events.json","paper":"https://pith.science/paper/TCOJ3D52"},"agent_actions":{"view_html":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22","download_json":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22.json","view_paper":"https://pith.science/paper/TCOJ3D52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10000&json=true","fetch_graph":"https://pith.science/api/pith-number/TCOJ3D52FH7VEL3UKYJUALHV22/graph.json","fetch_events":"https://pith.science/api/pith-number/TCOJ3D52FH7VEL3UKYJUALHV22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22/action/storage_attestation","attest_author":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22/action/author_attestation","sign_citation":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22/action/citation_signature","submit_replication":"https://pith.science/pith/TCOJ3D52FH7VEL3UKYJUALHV22/action/replication_record"}},"created_at":"2026-05-18T00:14:58.526277+00:00","updated_at":"2026-05-18T00:14:58.526277+00:00"}