{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JPDN7FIC7FAIWK3DSFWHOEZ47V","short_pith_number":"pith:JPDN7FIC","schema_version":"1.0","canonical_sha256":"4bc6df9502f9408b2b63916c77133cfd7f06a8ca02ca401fe9a29ab04fdb212b","source":{"kind":"arxiv","id":"2210.07006","version":1},"attestation_state":"computed","paper":{"title":"Sustainable Online Reinforcement Learning for Auto-bidding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Zheng, Chuan Yu, Jian Xu, Mingzhou Xie, Rongquan Bai, Yusen Huo, Zhiyu Mou","submitted_at":"2022-10-13T13:17:20Z","abstract_excerpt":"Recently, auto-bidding technique has become an essential tool to increase the revenue of advertisers. Facing the complex and ever-changing bidding environments in the real-world advertising system (RAS), state-of-the-art auto-bidding policies usually leverage reinforcement learning (RL) algorithms to generate real-time bids on behalf of the advertisers. Due to safety concerns, it was believed that the RL training process can only be carried out in an offline virtual advertising system (VAS) that is built based on the historical data generated in the RAS. In this paper, we argue that there exis"},"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":"2210.07006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-13T13:17:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4b47897ff046db58f08be9416e58de5258a21daf5e826cd5ed4cad6c16e8513","abstract_canon_sha256":"28c8570217de73d93ae5754350bf8145405453f80b3e06898275fb851f91d37d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:23.670792Z","signature_b64":"d/l3oPaetM4/FESvjCaR5Gcv2HbuQ6TK1M0r3u+AP+Pm6M+wRbpFmZkSvytZGbtblBfnyJkxc6GHrQPW8DQdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc6df9502f9408b2b63916c77133cfd7f06a8ca02ca401fe9a29ab04fdb212b","last_reissued_at":"2026-07-05T05:06:23.670215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:23.670215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sustainable Online Reinforcement Learning for Auto-bidding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Zheng, Chuan Yu, Jian Xu, Mingzhou Xie, Rongquan Bai, Yusen Huo, Zhiyu Mou","submitted_at":"2022-10-13T13:17:20Z","abstract_excerpt":"Recently, auto-bidding technique has become an essential tool to increase the revenue of advertisers. Facing the complex and ever-changing bidding environments in the real-world advertising system (RAS), state-of-the-art auto-bidding policies usually leverage reinforcement learning (RL) algorithms to generate real-time bids on behalf of the advertisers. Due to safety concerns, it was believed that the RL training process can only be carried out in an offline virtual advertising system (VAS) that is built based on the historical data generated in the RAS. In this paper, we argue that there exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07006","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/2210.07006/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":"2210.07006","created_at":"2026-07-05T05:06:23.670288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07006v1","created_at":"2026-07-05T05:06:23.670288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07006","created_at":"2026-07-05T05:06:23.670288+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPDN7FIC7FAI","created_at":"2026-07-05T05:06:23.670288+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPDN7FIC7FAIWK3D","created_at":"2026-07-05T05:06:23.670288+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPDN7FIC","created_at":"2026-07-05T05:06:23.670288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V","json":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V.json","graph_json":"https://pith.science/api/pith-number/JPDN7FIC7FAIWK3DSFWHOEZ47V/graph.json","events_json":"https://pith.science/api/pith-number/JPDN7FIC7FAIWK3DSFWHOEZ47V/events.json","paper":"https://pith.science/paper/JPDN7FIC"},"agent_actions":{"view_html":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V","download_json":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V.json","view_paper":"https://pith.science/paper/JPDN7FIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07006&json=true","fetch_graph":"https://pith.science/api/pith-number/JPDN7FIC7FAIWK3DSFWHOEZ47V/graph.json","fetch_events":"https://pith.science/api/pith-number/JPDN7FIC7FAIWK3DSFWHOEZ47V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V/action/storage_attestation","attest_author":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V/action/author_attestation","sign_citation":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V/action/citation_signature","submit_replication":"https://pith.science/pith/JPDN7FIC7FAIWK3DSFWHOEZ47V/action/replication_record"}},"created_at":"2026-07-05T05:06:23.670288+00:00","updated_at":"2026-07-05T05:06:23.670288+00:00"}