{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3TSI63BZCJ3IYX2ONAG56WUQOE","short_pith_number":"pith:3TSI63BZ","schema_version":"1.0","canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","source":{"kind":"arxiv","id":"2012.02476","version":1},"attestation_state":"computed","paper":{"title":"Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Li Li, Rui Chen, Tong Xu, Yanan Wang, Yong Ge","submitted_at":"2020-12-04T08:58:35Z","abstract_excerpt":"Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a meta-level model-based reinforcement learning approach for fast user adaptation. In our approach, we learn to infer each"},"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":"2012.02476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T08:58:35Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9a04cbb4dfb7dd1b1e0cea19634f1f87ad75a86e6079637eae5a66fa5cd6fe55","abstract_canon_sha256":"307d3b2291603c8eb6247f1bc2645e64aea5cc84088efdd23ddc80723754d72b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:59.995928Z","signature_b64":"UT+bcYAiYEAfPrFOMrKFBLqD37Vg1gbnzWpJ7NN5nLqbrCiK53/uHyOP+S2p1J7wpDNTC11nE68BHjiYurTcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dce48f6c3912768c5f4e680ddf5a90711bc145611744fa0990aca686b2a531fc","last_reissued_at":"2026-07-05T01:56:59.995481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:59.995481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Meta-level Model-based Reinforcement Learning Approach for Cold-Start Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Li Li, Rui Chen, Tong Xu, Yanan Wang, Yong Ge","submitted_at":"2020-12-04T08:58:35Z","abstract_excerpt":"Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn a robust recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this paper, we address the cold-start challenge in the RL-based recommender systems by proposing a meta-level model-based reinforcement learning approach for fast user adaptation. In our approach, we learn to infer each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02476","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/2012.02476/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":"2012.02476","created_at":"2026-07-05T01:56:59.995536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02476v1","created_at":"2026-07-05T01:56:59.995536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02476","created_at":"2026-07-05T01:56:59.995536+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TSI63BZCJ3I","created_at":"2026-07-05T01:56:59.995536+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TSI63BZCJ3IYX2O","created_at":"2026-07-05T01:56:59.995536+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TSI63BZ","created_at":"2026-07-05T01:56:59.995536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.08109","citing_title":"Data-driven inventory management for new products: An adjusted Dyna-$Q$ approach with transfer learning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE","json":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE.json","graph_json":"https://pith.science/api/pith-number/3TSI63BZCJ3IYX2ONAG56WUQOE/graph.json","events_json":"https://pith.science/api/pith-number/3TSI63BZCJ3IYX2ONAG56WUQOE/events.json","paper":"https://pith.science/paper/3TSI63BZ"},"agent_actions":{"view_html":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE","download_json":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE.json","view_paper":"https://pith.science/paper/3TSI63BZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02476&json=true","fetch_graph":"https://pith.science/api/pith-number/3TSI63BZCJ3IYX2ONAG56WUQOE/graph.json","fetch_events":"https://pith.science/api/pith-number/3TSI63BZCJ3IYX2ONAG56WUQOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/action/storage_attestation","attest_author":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/action/author_attestation","sign_citation":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/action/citation_signature","submit_replication":"https://pith.science/pith/3TSI63BZCJ3IYX2ONAG56WUQOE/action/replication_record"}},"created_at":"2026-07-05T01:56:59.995536+00:00","updated_at":"2026-07-05T01:56:59.995536+00:00"}