{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7OXDXAJACXT2WVRO3JPU7NXG4G","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":"9aeaece083b6e88c8f86f29ad4d503e9fecfa59ac21b9452af4f0f1f32323542","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T15:23:53Z","title_canon_sha256":"ec8070128c2abbe38bc5a7c220ba684eef6d666ce5d4bb13794a1b2d8f939975"},"schema_version":"1.0","source":{"id":"2012.06052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.06052","created_at":"2026-07-05T01:58:47Z"},{"alias_kind":"arxiv_version","alias_value":"2012.06052v1","created_at":"2026-07-05T01:58:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06052","created_at":"2026-07-05T01:58:47Z"},{"alias_kind":"pith_short_12","alias_value":"7OXDXAJACXT2","created_at":"2026-07-05T01:58:47Z"},{"alias_kind":"pith_short_16","alias_value":"7OXDXAJACXT2WVRO","created_at":"2026-07-05T01:58:47Z"},{"alias_kind":"pith_short_8","alias_value":"7OXDXAJA","created_at":"2026-07-05T01:58:47Z"}],"graph_snapshots":[{"event_id":"sha256:7985b8caf31cf8441ef398b86c5109f6acb93b66e9e259399a8e9c902d611445","target":"graph","created_at":"2026-07-05T01:58:47Z","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/2012.06052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the continuous development of machine learning technology, major e-commerce platforms have launched recommendation systems based on it to serve a large number of customers with different needs more efficiently. Compared with traditional supervised learning, reinforcement learning can better capture the user's state transition in the decision-making process, and consider a series of user actions, not just the static characteristics of the user at a certain moment. In theory, it will have a long-term perspective, producing a more effective recommendation. The special requirements of reinfor","authors_text":"Jingtian Ge, Kenglun Chang, Rong Tao, Yang Yu, Zhenhao Gu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T15:23:53Z","title":"Interactive Search Based on Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06052","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":"sha256:4995af1a76911ed595936a1be76a09817992906e0db9e21374d22138ac88da64","target":"record","created_at":"2026-07-05T01:58:47Z","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":"9aeaece083b6e88c8f86f29ad4d503e9fecfa59ac21b9452af4f0f1f32323542","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-09T15:23:53Z","title_canon_sha256":"ec8070128c2abbe38bc5a7c220ba684eef6d666ce5d4bb13794a1b2d8f939975"},"schema_version":"1.0","source":{"id":"2012.06052","kind":"arxiv","version":1}},"canonical_sha256":"fbae3b812015e7ab562eda5f4fb6e6e1a5adef455525c40fc05f14651e786912","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbae3b812015e7ab562eda5f4fb6e6e1a5adef455525c40fc05f14651e786912","first_computed_at":"2026-07-05T01:58:47.039346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:47.039346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PXuRkgI4C0TpLPXkNK9+owZPOcIXwAW9VdNdX5E/G0jJycWUVge6RvHtJACKFAgQRyDfosgi+vYwgM8dDEZMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:47.039775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.06052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4995af1a76911ed595936a1be76a09817992906e0db9e21374d22138ac88da64","sha256:7985b8caf31cf8441ef398b86c5109f6acb93b66e9e259399a8e9c902d611445"],"state_sha256":"d055d07f56a59ef3472f6b7ea30a4addf1a8756092cc3e3f5c431bd9dd808029"}