{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BGLWE2B7XOTELXMPXRWY3EFULJ","short_pith_number":"pith:BGLWE2B7","schema_version":"1.0","canonical_sha256":"099762683fbba645dd8fbc6d8d90b45a4574897d0f0a99ac12a220367d17f25b","source":{"kind":"arxiv","id":"2205.13248","version":1},"attestation_state":"computed","paper":{"title":"Constrained Reinforcement Learning for Short Video Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Dong Zheng, Guangwei Ding, Jie Zheng, Peng Jiang, Pinghua Gong, Qingpeng Cai, Ruohan Zhan","submitted_at":"2022-05-26T09:36:20Z","abstract_excerpt":"The wide popularity of short videos on social media poses new opportunities and challenges to optimize recommender systems on the video-sharing platforms. Users provide complex and multi-faceted responses towards recommendations, including watch time and various types of interactions with videos. As a result, established recommendation algorithms that concern a single objective are not adequate to meet this new demand of optimizing comprehensive user experiences. In this paper, we formulate the problem of short video recommendation as a constrained Markov Decision Process (MDP), where platform"},"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":"2205.13248","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-26T09:36:20Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3ae9a1e629842b2b858250f39620864f59610d6d03e77d7ad75935d004456aff","abstract_canon_sha256":"66b72107d7e0b25e296afc908dc36096d0329c307a54b30f26d5c65a997c34c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:41.277352Z","signature_b64":"Rx1XR4h8Sk3h6qhmJgO9/eNpljIu7ko5LsjUA7cXVXnXrWluau6H8e0FToT2dmsTTJt2JGqJg0SYSF04yl7YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"099762683fbba645dd8fbc6d8d90b45a4574897d0f0a99ac12a220367d17f25b","last_reissued_at":"2026-07-05T04:26:41.276941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:41.276941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Reinforcement Learning for Short Video Recommendation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Dong Zheng, Guangwei Ding, Jie Zheng, Peng Jiang, Pinghua Gong, Qingpeng Cai, Ruohan Zhan","submitted_at":"2022-05-26T09:36:20Z","abstract_excerpt":"The wide popularity of short videos on social media poses new opportunities and challenges to optimize recommender systems on the video-sharing platforms. Users provide complex and multi-faceted responses towards recommendations, including watch time and various types of interactions with videos. As a result, established recommendation algorithms that concern a single objective are not adequate to meet this new demand of optimizing comprehensive user experiences. In this paper, we formulate the problem of short video recommendation as a constrained Markov Decision Process (MDP), where platform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13248","kind":"arxiv","version":1},"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/2205.13248/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":"2205.13248","created_at":"2026-07-05T04:26:41.276997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13248v1","created_at":"2026-07-05T04:26:41.276997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13248","created_at":"2026-07-05T04:26:41.276997+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGLWE2B7XOTE","created_at":"2026-07-05T04:26:41.276997+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGLWE2B7XOTELXMP","created_at":"2026-07-05T04:26:41.276997+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGLWE2B7","created_at":"2026-07-05T04:26:41.276997+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/BGLWE2B7XOTELXMPXRWY3EFULJ","json":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ.json","graph_json":"https://pith.science/api/pith-number/BGLWE2B7XOTELXMPXRWY3EFULJ/graph.json","events_json":"https://pith.science/api/pith-number/BGLWE2B7XOTELXMPXRWY3EFULJ/events.json","paper":"https://pith.science/paper/BGLWE2B7"},"agent_actions":{"view_html":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ","download_json":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ.json","view_paper":"https://pith.science/paper/BGLWE2B7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13248&json=true","fetch_graph":"https://pith.science/api/pith-number/BGLWE2B7XOTELXMPXRWY3EFULJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BGLWE2B7XOTELXMPXRWY3EFULJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ/action/storage_attestation","attest_author":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ/action/author_attestation","sign_citation":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ/action/citation_signature","submit_replication":"https://pith.science/pith/BGLWE2B7XOTELXMPXRWY3EFULJ/action/replication_record"}},"created_at":"2026-07-05T04:26:41.276997+00:00","updated_at":"2026-07-05T04:26:41.276997+00:00"}