{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RYSESQI4T5MFXK7GVAJPOWWDE6","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":"ca7eb514f5f01c465717e4b74981c14057a0d16a4a506a13a688ff695a6106e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T15:53:37Z","title_canon_sha256":"2222255ad5f10733ca9d2920718e8dd726e2bccddfaf67e1ae4a9608768c43fc"},"schema_version":"1.0","source":{"id":"2204.00888","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00888","created_at":"2026-07-05T04:47:41Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00888v3","created_at":"2026-07-05T04:47:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00888","created_at":"2026-07-05T04:47:41Z"},{"alias_kind":"pith_short_12","alias_value":"RYSESQI4T5MF","created_at":"2026-07-05T04:47:41Z"},{"alias_kind":"pith_short_16","alias_value":"RYSESQI4T5MFXK7G","created_at":"2026-07-05T04:47:41Z"},{"alias_kind":"pith_short_8","alias_value":"RYSESQI4","created_at":"2026-07-05T04:47:41Z"}],"graph_snapshots":[{"event_id":"sha256:abc132f0a5a298e87bacfa9ad53a4077e576c9966d8c3860ab001932cde86cf5","target":"graph","created_at":"2026-07-05T04:47:41Z","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/2204.00888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent prevalence of reinforcement learning (RL), there have been tremendous interests in utilizing RL for ads allocation in recommendation platforms (e.g., e-commerce and news feed sites). To achieve better allocation, the input of recent RL-based ads allocation methods is upgraded from point-wise single item to list-wise item arrangement. However, this also results in a high-dimensional space of state-action pairs, making it difficult to learn list-wise representations with good generalization ability. This further hinders the exploration of RL agents and causes poor sample efficien","authors_text":"Chuheng Zhang, Dong Wang, Guogang Liao, Xiaowen Shi, Xiaoxu Wu, Xingxing Wang, Yongkang Wang, Ze Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T15:53:37Z","title":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00888","kind":"arxiv","version":3},"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:fdd5e649857f75d0f2829bc798d33ce5e048866996d968a0dd19b43cb74e90ec","target":"record","created_at":"2026-07-05T04:47:41Z","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":"ca7eb514f5f01c465717e4b74981c14057a0d16a4a506a13a688ff695a6106e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-02T15:53:37Z","title_canon_sha256":"2222255ad5f10733ca9d2920718e8dd726e2bccddfaf67e1ae4a9608768c43fc"},"schema_version":"1.0","source":{"id":"2204.00888","kind":"arxiv","version":3}},"canonical_sha256":"8e2449411c9f585babe6a812f75ac32792a9618c3bfcc561a8f74acdac23488f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e2449411c9f585babe6a812f75ac32792a9618c3bfcc561a8f74acdac23488f","first_computed_at":"2026-07-05T04:47:41.440970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:47:41.440970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mbi8tpmzXk+IGMUCEsWj2YlVbZcG5xTUEwAHuhLJakj4WFwlGNRr9KkHYChUGhFoVItLvhS67Ioc73RYhA2ZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:47:41.441472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00888","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdd5e649857f75d0f2829bc798d33ce5e048866996d968a0dd19b43cb74e90ec","sha256:abc132f0a5a298e87bacfa9ad53a4077e576c9966d8c3860ab001932cde86cf5"],"state_sha256":"02199deac4242b9fe025a77d852f7505deaddab8d8d213855f35c463f9339334"}