{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7Y4ECRC2MBGU23T3SNZALX5YSH","short_pith_number":"pith:7Y4ECRC2","schema_version":"1.0","canonical_sha256":"fe3841445a604d4d6e7b937205dfb891e2e1f9b5d4311cb09334667b2b56afab","source":{"kind":"arxiv","id":"2302.03431","version":2},"attestation_state":"computed","paper":{"title":"Exploration and Regularization of the Latent Action Space in Recommendation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bowen Sun, Dong Zheng, Ji Jiang, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Xiangyu Zhao, Yongfeng Zhang, Yuhao Wang","submitted_at":"2023-02-07T12:34:31Z","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"},"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":"2302.03431","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.IR","submitted_at":"2023-02-07T12:34:31Z","cross_cats_sorted":[],"title_canon_sha256":"31f71663b11e19bd9942a8d01cc045bb9d0e6c3bde5e6d3e21e12436b30e7be4","abstract_canon_sha256":"5c794b06276e75669788c7dd3a93017a2b9493b0f67615238098ea5002e4d253"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:56.468915Z","signature_b64":"qYHfhvwTFXYKiaUEWmKDiIudnjVSvNU56dxNKSRkp0vAWLmayxymBW6GqPBiN/dwK1SFNPa3w3vSlSJlfeR/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe3841445a604d4d6e7b937205dfb891e2e1f9b5d4311cb09334667b2b56afab","last_reissued_at":"2026-07-05T05:39:56.468465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:56.468465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploration and Regularization of the Latent Action Space in Recommendation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bowen Sun, Dong Zheng, Ji Jiang, Kun Gai, Peng Jiang, Qingpeng Cai, Shuchang Liu, Xiangyu Zhao, Yongfeng Zhang, Yuhao Wang","submitted_at":"2023-02-07T12:34:31Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03431","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/2302.03431/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":"2302.03431","created_at":"2026-07-05T05:39:56.468528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03431v2","created_at":"2026-07-05T05:39:56.468528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03431","created_at":"2026-07-05T05:39:56.468528+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Y4ECRC2MBGU","created_at":"2026-07-05T05:39:56.468528+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Y4ECRC2MBGU23T3","created_at":"2026-07-05T05:39:56.468528+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Y4ECRC2","created_at":"2026-07-05T05:39:56.468528+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/7Y4ECRC2MBGU23T3SNZALX5YSH","json":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH.json","graph_json":"https://pith.science/api/pith-number/7Y4ECRC2MBGU23T3SNZALX5YSH/graph.json","events_json":"https://pith.science/api/pith-number/7Y4ECRC2MBGU23T3SNZALX5YSH/events.json","paper":"https://pith.science/paper/7Y4ECRC2"},"agent_actions":{"view_html":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH","download_json":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH.json","view_paper":"https://pith.science/paper/7Y4ECRC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03431&json=true","fetch_graph":"https://pith.science/api/pith-number/7Y4ECRC2MBGU23T3SNZALX5YSH/graph.json","fetch_events":"https://pith.science/api/pith-number/7Y4ECRC2MBGU23T3SNZALX5YSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH/action/storage_attestation","attest_author":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH/action/author_attestation","sign_citation":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH/action/citation_signature","submit_replication":"https://pith.science/pith/7Y4ECRC2MBGU23T3SNZALX5YSH/action/replication_record"}},"created_at":"2026-07-05T05:39:56.468528+00:00","updated_at":"2026-07-05T05:39:56.468528+00:00"}