{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WLRRSSWHL45UJQXINKBU5LAKJF","short_pith_number":"pith:WLRRSSWH","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"},"canonical_sha256":"b2e3194ac75f3b44c2e86a834eac0a4977de7839eca4f009814972262dbdca71","source":{"kind":"arxiv","id":"2501.05591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05591","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05591v1","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05591","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"WLRRSSWHL45U","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"WLRRSSWHL45UJQXI","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"WLRRSSWH","created_at":"2026-07-05T09:59:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WLRRSSWHL45UJQXINKBU5LAKJF","target":"record","payload":{"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"},"canonical_sha256":"b2e3194ac75f3b44c2e86a834eac0a4977de7839eca4f009814972262dbdca71","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"},"source_kind":"arxiv","source_id":"2501.05591","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yep4VwoX5FWvKuWNT0rdotgAHcpWovVk71ppFKLd/voCecSAeMiH72sBfmN2m9RgjmiIM4PqHQCtrMVQfRx4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:39:54.322541Z"},"content_sha256":"864b60f3c00c85ac419d9099c762dcfcb62db727721e193f3c22c14518bdbbf0","schema_version":"1.0","event_id":"sha256:864b60f3c00c85ac419d9099c762dcfcb62db727721e193f3c22c14518bdbbf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WLRRSSWHL45UJQXINKBU5LAKJF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"63jkkSgeIMm02/NqnVUY2vEXGGC/a4yqC4y59thSzNMHWwvj9NacX5/DFIrPrdD8bJ/V1ftmPvmvmyhDoxvKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:39:54.323076Z"},"content_sha256":"167ceeac17b36f51b9138cdf5fb482a9511b7d79a64e271ef1acf008b6c07a35","schema_version":"1.0","event_id":"sha256:167ceeac17b36f51b9138cdf5fb482a9511b7d79a64e271ef1acf008b6c07a35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/bundle.json","state_url":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLRRSSWHL45UJQXINKBU5LAKJF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T15:39:54Z","links":{"resolver":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF","bundle":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/bundle.json","state":"https://pith.science/pith/WLRRSSWHL45UJQXINKBU5LAKJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLRRSSWHL45UJQXINKBU5LAKJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WLRRSSWHL45UJQXINKBU5LAKJF","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":"b5e2e27fc12f73293f2cb4703eb45cbeb3cd004e27b3b7029794657a009e943c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T21:53:03Z","title_canon_sha256":"500b26e65c89f5ad8ca2fbee674a945d1903f81a540fbe7407b6dc7dc954ac4f"},"schema_version":"1.0","source":{"id":"2501.05591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05591","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05591v1","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05591","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"WLRRSSWHL45U","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"WLRRSSWHL45UJQXI","created_at":"2026-07-05T09:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"WLRRSSWH","created_at":"2026-07-05T09:59:25Z"}],"graph_snapshots":[{"event_id":"sha256:167ceeac17b36f51b9138cdf5fb482a9511b7d79a64e271ef1acf008b6c07a35","target":"graph","created_at":"2026-07-05T09:59:25Z","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/2501.05591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Qi Xu, Shuang Yang, Tao Liu, Wei Shi, Zhigang Hua","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T21:53:03Z","title":"Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05591","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":"sha256:864b60f3c00c85ac419d9099c762dcfcb62db727721e193f3c22c14518bdbbf0","target":"record","created_at":"2026-07-05T09:59:25Z","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":"b5e2e27fc12f73293f2cb4703eb45cbeb3cd004e27b3b7029794657a009e943c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T21:53:03Z","title_canon_sha256":"500b26e65c89f5ad8ca2fbee674a945d1903f81a540fbe7407b6dc7dc954ac4f"},"schema_version":"1.0","source":{"id":"2501.05591","kind":"arxiv","version":1}},"canonical_sha256":"b2e3194ac75f3b44c2e86a834eac0a4977de7839eca4f009814972262dbdca71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2e3194ac75f3b44c2e86a834eac0a4977de7839eca4f009814972262dbdca71","first_computed_at":"2026-07-05T09:59:25.695393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:25.695393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvcPBfNxvpTRoRZ0LUdjB0JmwVrQNocSBlBK08sSR0FF9N3KJoyGJzcyGxWB7Zgh675/r9j8pxHTze0+UNCeAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:25.695870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:864b60f3c00c85ac419d9099c762dcfcb62db727721e193f3c22c14518bdbbf0","sha256:167ceeac17b36f51b9138cdf5fb482a9511b7d79a64e271ef1acf008b6c07a35"],"state_sha256":"845f65aeaf161b11ff9853f566ef38a80fe600e83ba173dba89fd8169cb2dcee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jqEGg5iAj4yUkYv6fOeW6Jopzi3xjEjtvN29GAiL7q597ehV6Ao5fGKnNHQEYtrlARHgwT18laLH9I1gvHk9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T15:39:54.326958Z","bundle_sha256":"8d5911761babf21405473147adbb0f5e792baf6efa28e06fb87149c420c72043"}}