{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GEQ2E5EQV3SRJRMHJXCDQ4ILWW","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":"774bb4319b5412a451dd25ca706b9b3cadc498f0bd2d13a41e5e68728715b0c0","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T06:53:53Z","title_canon_sha256":"2900b2f7b39940ab345fda1cfe92e8a273628f9b0ac2b2848cf880234bba3eeb"},"schema_version":"1.0","source":{"id":"2110.05032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05032","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05032v1","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05032","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"GEQ2E5EQV3SR","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"GEQ2E5EQV3SRJRMH","created_at":"2026-07-05T03:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"GEQ2E5EQ","created_at":"2026-07-05T03:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:fd01f37cadd0875c000692a5ff8e22f9ccbbd77bc9dee52d1f9aa3d5b9e04b0a","target":"graph","created_at":"2026-07-05T03:21:23Z","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/2110.05032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time bidding (RTB) has become a critical way of online advertising. In RTB, an advertiser can participate in bidding ad impressions to display its advertisements. The advertiser determines every impression's bidding price according to its bidding strategy. Therefore, a good bidding strategy can help advertisers improve cost efficiency. This paper focuses on optimizing a single advertiser's bidding strategy using reinforcement learning (RL) in RTB. Unfortunately, it is challenging to optimize the bidding strategy through RL at the granularity of impression due to the highly dynamic nature ","authors_text":"Jinyu Liu, Mengjuan Liu, Xuyun Nie, Yuchen Ge, Zhengning Hu","cross_cats":["cs.AI","cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T06:53:53Z","title":"Bid Optimization using Maximum Entropy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05032","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":"sha256:8cc3bde166af5a075d761003fe78719d00d3c2d1c9cd1ed2dc503b61627e6b11","target":"record","created_at":"2026-07-05T03:21:23Z","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":"774bb4319b5412a451dd25ca706b9b3cadc498f0bd2d13a41e5e68728715b0c0","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-11T06:53:53Z","title_canon_sha256":"2900b2f7b39940ab345fda1cfe92e8a273628f9b0ac2b2848cf880234bba3eeb"},"schema_version":"1.0","source":{"id":"2110.05032","kind":"arxiv","version":1}},"canonical_sha256":"3121a27490aee514c5874dc438710bb5ba33d7405e09891655c8e1c06f0c1110","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3121a27490aee514c5874dc438710bb5ba33d7405e09891655c8e1c06f0c1110","first_computed_at":"2026-07-05T03:21:23.958165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:23.958165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TBPpQdKPgtVH2Z31leLZA8h4Hizc8SVZ+3Q3jZwtAJtDMdb27Ii0VfPnTO4f4RXg1PL32GOCmlUJMtSOVVCsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:23.958594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cc3bde166af5a075d761003fe78719d00d3c2d1c9cd1ed2dc503b61627e6b11","sha256:fd01f37cadd0875c000692a5ff8e22f9ccbbd77bc9dee52d1f9aa3d5b9e04b0a"],"state_sha256":"356fe53729bb4c6a6f80b12251935881a57945cf38ba1988397c396f12628c18"}