{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKADHJYFBAOJ37GDW7G4Y2SAZB","short_pith_number":"pith:ZKADHJYF","schema_version":"1.0","canonical_sha256":"ca8033a705081c9dfcc3b7cdcc6a40c87597da2358889d6cdc617f97e26217bd","source":{"kind":"arxiv","id":"2402.15102","version":2},"attestation_state":"computed","paper":{"title":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.IR"],"primary_cat":"cs.LG","authors_text":"Chuan Yu, Fan Wu, Haoming Li, Jian Xu, Shuai Dou, Yusen Huo, Zhenzhe Zheng, Zhilin Zhang","submitted_at":"2024-02-23T05:20:23Z","abstract_excerpt":"In online advertising, advertisers participate in ad auctions to acquire ad opportunities, often by utilizing auto-bidding tools provided by demand-side platforms (DSPs). The current auto-bidding algorithms typically employ reinforcement learning (RL). However, due to safety concerns, most RL-based auto-bidding policies are trained in simulation, leading to a performance degradation when deployed in online environments. To narrow this gap, we can deploy multiple auto-bidding agents in parallel to collect a large interaction dataset. Offline RL algorithms can then be utilized to train a new pol"},"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":"2402.15102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T05:20:23Z","cross_cats_sorted":["cs.AI","cs.GT","cs.IR"],"title_canon_sha256":"742b076f0a0e4ec61c718b3537a9e6393b147a28f5e90a84876621c1288903e9","abstract_canon_sha256":"a4c3070ee9205c424b6d2a6a3a19300fcd7587a57d9010216fc9aaa4bd57defe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:11.032549Z","signature_b64":"UEotG+OsvQgKEb9FQ6dNQieGqlnMuvwQ0JKLLLVAwD5KUXmsk+mytK6GZ5x4CVV3XVcYtqs+nbabZshm+rH/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca8033a705081c9dfcc3b7cdcc6a40c87597da2358889d6cdc617f97e26217bd","last_reissued_at":"2026-07-05T08:05:11.032117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:11.032117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.IR"],"primary_cat":"cs.LG","authors_text":"Chuan Yu, Fan Wu, Haoming Li, Jian Xu, Shuai Dou, Yusen Huo, Zhenzhe Zheng, Zhilin Zhang","submitted_at":"2024-02-23T05:20:23Z","abstract_excerpt":"In online advertising, advertisers participate in ad auctions to acquire ad opportunities, often by utilizing auto-bidding tools provided by demand-side platforms (DSPs). The current auto-bidding algorithms typically employ reinforcement learning (RL). However, due to safety concerns, most RL-based auto-bidding policies are trained in simulation, leading to a performance degradation when deployed in online environments. To narrow this gap, we can deploy multiple auto-bidding agents in parallel to collect a large interaction dataset. Offline RL algorithms can then be utilized to train a new pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15102","kind":"arxiv","version":2},"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/2402.15102/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":"2402.15102","created_at":"2026-07-05T08:05:11.032172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15102v2","created_at":"2026-07-05T08:05:11.032172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15102","created_at":"2026-07-05T08:05:11.032172+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKADHJYFBAOJ","created_at":"2026-07-05T08:05:11.032172+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKADHJYFBAOJ37GD","created_at":"2026-07-05T08:05:11.032172+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKADHJYF","created_at":"2026-07-05T08:05:11.032172+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/ZKADHJYFBAOJ37GDW7G4Y2SAZB","json":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB.json","graph_json":"https://pith.science/api/pith-number/ZKADHJYFBAOJ37GDW7G4Y2SAZB/graph.json","events_json":"https://pith.science/api/pith-number/ZKADHJYFBAOJ37GDW7G4Y2SAZB/events.json","paper":"https://pith.science/paper/ZKADHJYF"},"agent_actions":{"view_html":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB","download_json":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB.json","view_paper":"https://pith.science/paper/ZKADHJYF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15102&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKADHJYFBAOJ37GDW7G4Y2SAZB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKADHJYFBAOJ37GDW7G4Y2SAZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB/action/storage_attestation","attest_author":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB/action/author_attestation","sign_citation":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB/action/citation_signature","submit_replication":"https://pith.science/pith/ZKADHJYFBAOJ37GDW7G4Y2SAZB/action/replication_record"}},"created_at":"2026-07-05T08:05:11.032172+00:00","updated_at":"2026-07-05T08:05:11.032172+00:00"}