{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AAN4PY4BWBR6VUCKH4HDGOCT4A","short_pith_number":"pith:AAN4PY4B","schema_version":"1.0","canonical_sha256":"001bc7e381b063ead04a3f0e333853e0388ce62656407f0a96cfd79052cde962","source":{"kind":"arxiv","id":"2405.13362","version":4},"attestation_state":"computed","paper":{"title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Danial Ebrat, Eli Paradalis, Luis Rueda","submitted_at":"2024-05-22T05:43:15Z","abstract_excerpt":"Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever changing nature of user preferences in real-world scenarios. Meanwhile, generative AI techniques have emerged as powerful tools for creating synthetic data, including user profiles and behaviors. Recognizing this potential, we introduce Lusifer, an LLM-based simulation environment designed to generate dynamic, realistic user feedback for RL-based recommender training. In Lusifer, user profiles are incrementally updated at each interaction step, with Large Language Models (LLMs) pr"},"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":"2405.13362","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-05-22T05:43:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"da2788bc9305a837f47302218623a1081ace1deda64280fe5246c3dc65a563c8","abstract_canon_sha256":"434877e4f14ab743da7faa2026a65c9896fea760d87d013029c1cb2ec17d3f53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:59.293572Z","signature_b64":"xGoyHm8c5rI+AwMUkQTxmx7LDnB37ICe8Q/yQWYCYe5Zuh74Nb7jvgzmLQeGe4Kpqb+oYre/4TJ9lh4redGqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"001bc7e381b063ead04a3f0e333853e0388ce62656407f0a96cfd79052cde962","last_reissued_at":"2026-07-05T12:06:59.292377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:59.292377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Danial Ebrat, Eli Paradalis, Luis Rueda","submitted_at":"2024-05-22T05:43:15Z","abstract_excerpt":"Reinforcement learning (RL) recommender systems often rely on static datasets that fail to capture the fluid, ever changing nature of user preferences in real-world scenarios. Meanwhile, generative AI techniques have emerged as powerful tools for creating synthetic data, including user profiles and behaviors. Recognizing this potential, we introduce Lusifer, an LLM-based simulation environment designed to generate dynamic, realistic user feedback for RL-based recommender training. In Lusifer, user profiles are incrementally updated at each interaction step, with Large Language Models (LLMs) pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13362","kind":"arxiv","version":4},"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/2405.13362/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":"2405.13362","created_at":"2026-07-05T12:06:59.292513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13362v4","created_at":"2026-07-05T12:06:59.292513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13362","created_at":"2026-07-05T12:06:59.292513+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAN4PY4BWBR6","created_at":"2026-07-05T12:06:59.292513+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAN4PY4BWBR6VUCK","created_at":"2026-07-05T12:06:59.292513+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAN4PY4B","created_at":"2026-07-05T12:06:59.292513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A","json":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A.json","graph_json":"https://pith.science/api/pith-number/AAN4PY4BWBR6VUCKH4HDGOCT4A/graph.json","events_json":"https://pith.science/api/pith-number/AAN4PY4BWBR6VUCKH4HDGOCT4A/events.json","paper":"https://pith.science/paper/AAN4PY4B"},"agent_actions":{"view_html":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A","download_json":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A.json","view_paper":"https://pith.science/paper/AAN4PY4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13362&json=true","fetch_graph":"https://pith.science/api/pith-number/AAN4PY4BWBR6VUCKH4HDGOCT4A/graph.json","fetch_events":"https://pith.science/api/pith-number/AAN4PY4BWBR6VUCKH4HDGOCT4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A/action/storage_attestation","attest_author":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A/action/author_attestation","sign_citation":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A/action/citation_signature","submit_replication":"https://pith.science/pith/AAN4PY4BWBR6VUCKH4HDGOCT4A/action/replication_record"}},"created_at":"2026-07-05T12:06:59.292513+00:00","updated_at":"2026-07-05T12:06:59.292513+00:00"}