{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WLRRSSWHL45UJQXINKBU5LAKJF","short_pith_number":"pith:WLRRSSWH","schema_version":"1.0","canonical_sha256":"b2e3194ac75f3b44c2e86a834eac0a4977de7839eca4f009814972262dbdca71","source":{"kind":"arxiv","id":"2501.05591","version":1},"attestation_state":"computed","paper":{"title":"Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qi Xu, Shuang Yang, Tao Liu, Wei Shi, Zhigang Hua","submitted_at":"2025-01-09T21:53:03Z","abstract_excerpt":"Session-level dynamic ad load optimization aims to personalize the density and types of delivered advertisements in real time during a user's online session by dynamically balancing user experience quality and ad monetization. Traditional causal learning-based approaches struggle with key technical challenges, especially in handling confounding bias and distribution shifts. In this paper, we develop an offline deep Q-network (DQN)-based framework that effectively mitigates confounding bias in dynamic systems and demonstrates more than 80% offline gains compared to the best causal learning-base"},"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":"2501.05591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T21:53:03Z","cross_cats_sorted":[],"title_canon_sha256":"500b26e65c89f5ad8ca2fbee674a945d1903f81a540fbe7407b6dc7dc954ac4f","abstract_canon_sha256":"b5e2e27fc12f73293f2cb4703eb45cbeb3cd004e27b3b7029794657a009e943c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:25.695870Z","signature_b64":"lvcPBfNxvpTRoRZ0LUdjB0JmwVrQNocSBlBK08sSR0FF9N3KJoyGJzcyGxWB7Zgh675/r9j8pxHTze0+UNCeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e3194ac75f3b44c2e86a834eac0a4977de7839eca4f009814972262dbdca71","last_reissued_at":"2026-07-05T09:59:25.695393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:25.695393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qi Xu, Shuang Yang, Tao Liu, Wei Shi, Zhigang Hua","submitted_at":"2025-01-09T21:53:03Z","abstract_excerpt":"Session-level dynamic ad load optimization aims to personalize the density and types of delivered advertisements in real time during a user's online session by dynamically balancing user experience quality and ad monetization. Traditional causal learning-based approaches struggle with key technical challenges, especially in handling confounding bias and distribution shifts. In this paper, we develop an offline deep Q-network (DQN)-based framework that effectively mitigates confounding bias in dynamic systems and demonstrates more than 80% offline gains compared to the best causal learning-base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05591","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.05591/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":"2501.05591","created_at":"2026-07-05T09:59:25.695451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05591v1","created_at":"2026-07-05T09:59:25.695451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05591","created_at":"2026-07-05T09:59:25.695451+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLRRSSWHL45U","created_at":"2026-07-05T09:59:25.695451+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLRRSSWHL45UJQXI","created_at":"2026-07-05T09:59:25.695451+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLRRSSWH","created_at":"2026-07-05T09:59:25.695451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23090","citing_title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF","json":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF.json","graph_json":"https://pith.science/api/pith-number/WLRRSSWHL45UJQXINKBU5LAKJF/graph.json","events_json":"https://pith.science/api/pith-number/WLRRSSWHL45UJQXINKBU5LAKJF/events.json","paper":"https://pith.science/paper/WLRRSSWH"},"agent_actions":{"view_html":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF","download_json":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF.json","view_paper":"https://pith.science/paper/WLRRSSWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05591&json=true","fetch_graph":"https://pith.science/api/pith-number/WLRRSSWHL45UJQXINKBU5LAKJF/graph.json","fetch_events":"https://pith.science/api/pith-number/WLRRSSWHL45UJQXINKBU5LAKJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/action/storage_attestation","attest_author":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/action/author_attestation","sign_citation":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/action/citation_signature","submit_replication":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/action/replication_record"}},"created_at":"2026-07-05T09:59:25.695451+00:00","updated_at":"2026-07-05T09:59:25.695451+00:00"}