{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7Y4ECRC2MBGU23T3SNZALX5YSH","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":"5c794b06276e75669788c7dd3a93017a2b9493b0f67615238098ea5002e4d253","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T12:34:31Z","title_canon_sha256":"31f71663b11e19bd9942a8d01cc045bb9d0e6c3bde5e6d3e21e12436b30e7be4"},"schema_version":"1.0","source":{"id":"2302.03431","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.03431","created_at":"2026-07-05T05:39:56Z"},{"alias_kind":"arxiv_version","alias_value":"2302.03431v2","created_at":"2026-07-05T05:39:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03431","created_at":"2026-07-05T05:39:56Z"},{"alias_kind":"pith_short_12","alias_value":"7Y4ECRC2MBGU","created_at":"2026-07-05T05:39:56Z"},{"alias_kind":"pith_short_16","alias_value":"7Y4ECRC2MBGU23T3","created_at":"2026-07-05T05:39:56Z"},{"alias_kind":"pith_short_8","alias_value":"7Y4ECRC2","created_at":"2026-07-05T05:39:56Z"}],"graph_snapshots":[{"event_id":"sha256:5248528590c78a1286d9a57c5104da0b1300eda932a3fc4549d8ccf7444705cf","target":"graph","created_at":"2026-07-05T05:39:56Z","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/2302.03431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recommender systems, reinforcement learning solutions have effectively boosted recommendation performance because of their ability to capture long-term user-system interaction. However, the action space of the recommendation policy is a list of items, which could be extremely large with a dynamic candidate item pool. To overcome this challenge, we propose a hyper-actor and critic learning framework where the policy decomposes the item list generation process into a hyper-action inference step and an effect-action selection step. The first step maps the given state space into a vectorized hy","authors_text":"Bowen Sun, Dong Zheng, Ji Jiang, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Xiangyu Zhao, Yongfeng Zhang, Yuhao Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T12:34:31Z","title":"Exploration and Regularization of the Latent Action Space in Recommendation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03431","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:abe201d20f978b856640c6da60fde123731cccd4c58490673a179443015139da","target":"record","created_at":"2026-07-05T05:39:56Z","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":"5c794b06276e75669788c7dd3a93017a2b9493b0f67615238098ea5002e4d253","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T12:34:31Z","title_canon_sha256":"31f71663b11e19bd9942a8d01cc045bb9d0e6c3bde5e6d3e21e12436b30e7be4"},"schema_version":"1.0","source":{"id":"2302.03431","kind":"arxiv","version":2}},"canonical_sha256":"fe3841445a604d4d6e7b937205dfb891e2e1f9b5d4311cb09334667b2b56afab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe3841445a604d4d6e7b937205dfb891e2e1f9b5d4311cb09334667b2b56afab","first_computed_at":"2026-07-05T05:39:56.468465Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:39:56.468465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qYHfhvwTFXYKiaUEWmKDiIudnjVSvNU56dxNKSRkp0vAWLmayxymBW6GqPBiN/dwK1SFNPa3w3vSlSJlfeR/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:39:56.468915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.03431","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abe201d20f978b856640c6da60fde123731cccd4c58490673a179443015139da","sha256:5248528590c78a1286d9a57c5104da0b1300eda932a3fc4549d8ccf7444705cf"],"state_sha256":"ef6a47e859723a3fe30328a1583c3acea6e9758e13d4b32f0fc5f71e3446f350"}