{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:POTENRNHV77G53XHBVZHHJXWCY","short_pith_number":"pith:POTENRNH","canonical_record":{"source":{"id":"2309.02669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-06T02:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"1f072b5db66d2ef2c4049e853fe6b7da3528a5dd99d9a028488b893df77259bd","abstract_canon_sha256":"7c0b522d8c247918c820906c123c527a6c7824b9339c37e296fde106fa3bf3ea"},"schema_version":"1.0"},"canonical_sha256":"7ba646c5a7affe6eeee70d7273a6f6163e8bddea4bb50324c4d80cc9405af1e1","source":{"kind":"arxiv","id":"2309.02669","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02669","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02669v1","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02669","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"POTENRNHV77G","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"POTENRNHV77G53XH","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"POTENRNH","created_at":"2026-07-05T06:48:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:POTENRNHV77G53XHBVZHHJXWCY","target":"record","payload":{"canonical_record":{"source":{"id":"2309.02669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-06T02:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"1f072b5db66d2ef2c4049e853fe6b7da3528a5dd99d9a028488b893df77259bd","abstract_canon_sha256":"7c0b522d8c247918c820906c123c527a6c7824b9339c37e296fde106fa3bf3ea"},"schema_version":"1.0"},"canonical_sha256":"7ba646c5a7affe6eeee70d7273a6f6163e8bddea4bb50324c4d80cc9405af1e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:15.742892Z","signature_b64":"vzlXHUZtMS//qcOZnbLT/JkbmbIy5No1hqBrVT7jmblu6xRF7joFRgBq+CTV1OCBfeIU8j1gvWYeKsNSkAtfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ba646c5a7affe6eeee70d7273a6f6163e8bddea4bb50324c4d80cc9405af1e1","last_reissued_at":"2026-07-05T06:48:15.742461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:15.742461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.02669","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":"2026-07-05T06:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9tGzzSJci18uSJzvw1b/hNB36Bxp7iPqgGBKacUxAoiVdVKNujfW/Aq9katQyRMR+57pEalC8Ocip261lDrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:51:17.938237Z"},"content_sha256":"ffab77c35574839411843c8f2e93db60cdfdab5fba725aa0755b26107696f18d","schema_version":"1.0","event_id":"sha256:ffab77c35574839411843c8f2e93db60cdfdab5fba725aa0755b26107696f18d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:POTENRNHV77G53XHBVZHHJXWCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Guannan Zhang, Jinjie Gu, Jiyan Jiang, Lihong Gu, Li Yu, Shiji Zhou, Tianchi Cai, Wenpeng Zhang, Xiaodong Zeng, Xierui Song","submitted_at":"2023-09-06T02:35:46Z","abstract_excerpt":"We study the budget allocation problem in online marketing campaigns that utilize previously collected offline data. We first discuss the long-term effect of optimizing marketing budget allocation decisions in the offline setting. To overcome the challenge, we propose a novel game-theoretic offline value-based reinforcement learning method using mixed policies. The proposed method reduces the need to store infinitely many policies in previous methods to only constantly many policies, which achieves nearly optimal policy efficiency, making it practical and favorable for industrial usage. We fur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02669","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/2309.02669/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":"2026-07-05T06:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANMI8mFR/5wHT4WquqH/vRPzYk7DPjnEayCS4muXNTzlSBdtyZeJCgr6Kz9Btgh/TTqnbkz+mOfI4nqmTvyvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:51:17.939168Z"},"content_sha256":"92310bd9aa933117a0001da9d38ae573991b1a1381f1652f52b5f23b7d4818fe","schema_version":"1.0","event_id":"sha256:92310bd9aa933117a0001da9d38ae573991b1a1381f1652f52b5f23b7d4818fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POTENRNHV77G53XHBVZHHJXWCY/bundle.json","state_url":"https://pith.science/pith/POTENRNHV77G53XHBVZHHJXWCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POTENRNHV77G53XHBVZHHJXWCY/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":"2026-08-03T19:51:17Z","links":{"resolver":"https://pith.science/pith/POTENRNHV77G53XHBVZHHJXWCY","bundle":"https://pith.science/pith/POTENRNHV77G53XHBVZHHJXWCY/bundle.json","state":"https://pith.science/pith/POTENRNHV77G53XHBVZHHJXWCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POTENRNHV77G53XHBVZHHJXWCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:POTENRNHV77G53XHBVZHHJXWCY","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":"7c0b522d8c247918c820906c123c527a6c7824b9339c37e296fde106fa3bf3ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-06T02:35:46Z","title_canon_sha256":"1f072b5db66d2ef2c4049e853fe6b7da3528a5dd99d9a028488b893df77259bd"},"schema_version":"1.0","source":{"id":"2309.02669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02669","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02669v1","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02669","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"POTENRNHV77G","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"POTENRNHV77G53XH","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"POTENRNH","created_at":"2026-07-05T06:48:15Z"}],"graph_snapshots":[{"event_id":"sha256:92310bd9aa933117a0001da9d38ae573991b1a1381f1652f52b5f23b7d4818fe","target":"graph","created_at":"2026-07-05T06:48:15Z","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/2309.02669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the budget allocation problem in online marketing campaigns that utilize previously collected offline data. We first discuss the long-term effect of optimizing marketing budget allocation decisions in the offline setting. To overcome the challenge, we propose a novel game-theoretic offline value-based reinforcement learning method using mixed policies. The proposed method reduces the need to store infinitely many policies in previous methods to only constantly many policies, which achieves nearly optimal policy efficiency, making it practical and favorable for industrial usage. We fur","authors_text":"Guannan Zhang, Jinjie Gu, Jiyan Jiang, Lihong Gu, Li Yu, Shiji Zhou, Tianchi Cai, Wenpeng Zhang, Xiaodong Zeng, Xierui Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-06T02:35:46Z","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02669","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:ffab77c35574839411843c8f2e93db60cdfdab5fba725aa0755b26107696f18d","target":"record","created_at":"2026-07-05T06:48:15Z","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":"7c0b522d8c247918c820906c123c527a6c7824b9339c37e296fde106fa3bf3ea","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-06T02:35:46Z","title_canon_sha256":"1f072b5db66d2ef2c4049e853fe6b7da3528a5dd99d9a028488b893df77259bd"},"schema_version":"1.0","source":{"id":"2309.02669","kind":"arxiv","version":1}},"canonical_sha256":"7ba646c5a7affe6eeee70d7273a6f6163e8bddea4bb50324c4d80cc9405af1e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ba646c5a7affe6eeee70d7273a6f6163e8bddea4bb50324c4d80cc9405af1e1","first_computed_at":"2026-07-05T06:48:15.742461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:15.742461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vzlXHUZtMS//qcOZnbLT/JkbmbIy5No1hqBrVT7jmblu6xRF7joFRgBq+CTV1OCBfeIU8j1gvWYeKsNSkAtfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:15.742892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffab77c35574839411843c8f2e93db60cdfdab5fba725aa0755b26107696f18d","sha256:92310bd9aa933117a0001da9d38ae573991b1a1381f1652f52b5f23b7d4818fe"],"state_sha256":"a66d3e1cf89b334376652b33785b096fc94e508b40a672e9592d7b5f43d867e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/StGXSuWrSib8WdZR1qCdxNo2X0kvl7WOp+/F6XVB3UHT9FaZ262LNtELGKmJppZHOmsLO+wjiO9PanZCNizAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:51:17.943932Z","bundle_sha256":"72abfecc9a1095ce2b8c09352edd4dba65574651af5d05a1b9c14f9bbb757c08"}}