{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZKADHJYFBAOJ37GDW7G4Y2SAZB","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":"a4c3070ee9205c424b6d2a6a3a19300fcd7587a57d9010216fc9aaa4bd57defe","cross_cats_sorted":["cs.AI","cs.GT","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T05:20:23Z","title_canon_sha256":"742b076f0a0e4ec61c718b3537a9e6393b147a28f5e90a84876621c1288903e9"},"schema_version":"1.0","source":{"id":"2402.15102","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15102","created_at":"2026-07-05T08:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15102v2","created_at":"2026-07-05T08:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15102","created_at":"2026-07-05T08:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZKADHJYFBAOJ","created_at":"2026-07-05T08:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"ZKADHJYFBAOJ37GD","created_at":"2026-07-05T08:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"ZKADHJYF","created_at":"2026-07-05T08:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:16b08cb1406c5baab5e03821a113213bea54ba92cc24c128120007193eb1ebe0","target":"graph","created_at":"2026-07-05T08:05:11Z","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/2402.15102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chuan Yu, Fan Wu, Haoming Li, Jian Xu, Shuai Dou, Yusen Huo, Zhenzhe Zheng, Zhilin Zhang","cross_cats":["cs.AI","cs.GT","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T05:20:23Z","title":"Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15102","kind":"arxiv","version":2},"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":"sha256:64377565117915ae64e5742bf2ff695420ff2561a3a93e88a9a5d0917724f4bf","target":"record","created_at":"2026-07-05T08:05:11Z","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":"a4c3070ee9205c424b6d2a6a3a19300fcd7587a57d9010216fc9aaa4bd57defe","cross_cats_sorted":["cs.AI","cs.GT","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T05:20:23Z","title_canon_sha256":"742b076f0a0e4ec61c718b3537a9e6393b147a28f5e90a84876621c1288903e9"},"schema_version":"1.0","source":{"id":"2402.15102","kind":"arxiv","version":2}},"canonical_sha256":"ca8033a705081c9dfcc3b7cdcc6a40c87597da2358889d6cdc617f97e26217bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca8033a705081c9dfcc3b7cdcc6a40c87597da2358889d6cdc617f97e26217bd","first_computed_at":"2026-07-05T08:05:11.032117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:11.032117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UEotG+OsvQgKEb9FQ6dNQieGqlnMuvwQ0JKLLLVAwD5KUXmsk+mytK6GZ5x4CVV3XVcYtqs+nbabZshm+rH/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:11.032549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15102","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64377565117915ae64e5742bf2ff695420ff2561a3a93e88a9a5d0917724f4bf","sha256:16b08cb1406c5baab5e03821a113213bea54ba92cc24c128120007193eb1ebe0"],"state_sha256":"c35bcf5d0efc19d03be0ea750874980ea9832e8b8f783a355afd30012ee6c55e"}