{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MC4Z3BRICZJOCTPTPUHKHRGDUH","short_pith_number":"pith:MC4Z3BRI","schema_version":"1.0","canonical_sha256":"60b99d86281652e14df37d0ea3c4c3a1ef839dd656b386d80a5226f3636b7ee6","source":{"kind":"arxiv","id":"2406.05255","version":1},"attestation_state":"computed","paper":{"title":"Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Besnik Fetahu, Davis Yoshida, Giuseppe Castellucci, Jason Choi, L\\\"utfi Kerem Senel, Nikhita Vedula, Shervin Malmasi, Zhiyu Chen","submitted_at":"2024-06-07T20:41:59Z","abstract_excerpt":"Recommender systems are widely used to suggest engaging content, and Large Language Models (LLMs) have given rise to generative recommenders. Such systems can directly generate items, including for open-set tasks like question suggestion. While the world knowledge of LLMs enable good recommendations, improving the generated content through user feedback is challenging as continuously fine-tuning LLMs is prohibitively expensive. We present a training-free approach for optimizing generative recommenders by connecting user feedback loops to LLM-based optimizers. We propose a generative explore-ex"},"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":"2406.05255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T20:41:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a395892767323ae1812919e22361d75705c32b4c4a23911366312eb20b21006c","abstract_canon_sha256":"9d2f6d0749ca792901ed011d0752c4da189d90c37f2f58805a7fd83758170764"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:03.143057Z","signature_b64":"RelEt6DN8gUWe+ISPafiC1eGmsIyhhFR7pjAX8bl0yzqb+pH2aUcquZiZpJVm6jCyP8NNKtCaeYiCJmCG5j0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60b99d86281652e14df37d0ea3c4c3a1ef839dd656b386d80a5226f3636b7ee6","last_reissued_at":"2026-07-05T08:29:03.142639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:03.142639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Besnik Fetahu, Davis Yoshida, Giuseppe Castellucci, Jason Choi, L\\\"utfi Kerem Senel, Nikhita Vedula, Shervin Malmasi, Zhiyu Chen","submitted_at":"2024-06-07T20:41:59Z","abstract_excerpt":"Recommender systems are widely used to suggest engaging content, and Large Language Models (LLMs) have given rise to generative recommenders. Such systems can directly generate items, including for open-set tasks like question suggestion. While the world knowledge of LLMs enable good recommendations, improving the generated content through user feedback is challenging as continuously fine-tuning LLMs is prohibitively expensive. We present a training-free approach for optimizing generative recommenders by connecting user feedback loops to LLM-based optimizers. We propose a generative explore-ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05255","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/2406.05255/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":"2406.05255","created_at":"2026-07-05T08:29:03.142698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05255v1","created_at":"2026-07-05T08:29:03.142698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05255","created_at":"2026-07-05T08:29:03.142698+00:00"},{"alias_kind":"pith_short_12","alias_value":"MC4Z3BRICZJO","created_at":"2026-07-05T08:29:03.142698+00:00"},{"alias_kind":"pith_short_16","alias_value":"MC4Z3BRICZJOCTPT","created_at":"2026-07-05T08:29:03.142698+00:00"},{"alias_kind":"pith_short_8","alias_value":"MC4Z3BRI","created_at":"2026-07-05T08:29:03.142698+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/MC4Z3BRICZJOCTPTPUHKHRGDUH","json":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH.json","graph_json":"https://pith.science/api/pith-number/MC4Z3BRICZJOCTPTPUHKHRGDUH/graph.json","events_json":"https://pith.science/api/pith-number/MC4Z3BRICZJOCTPTPUHKHRGDUH/events.json","paper":"https://pith.science/paper/MC4Z3BRI"},"agent_actions":{"view_html":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH","download_json":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH.json","view_paper":"https://pith.science/paper/MC4Z3BRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05255&json=true","fetch_graph":"https://pith.science/api/pith-number/MC4Z3BRICZJOCTPTPUHKHRGDUH/graph.json","fetch_events":"https://pith.science/api/pith-number/MC4Z3BRICZJOCTPTPUHKHRGDUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH/action/storage_attestation","attest_author":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH/action/author_attestation","sign_citation":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH/action/citation_signature","submit_replication":"https://pith.science/pith/MC4Z3BRICZJOCTPTPUHKHRGDUH/action/replication_record"}},"created_at":"2026-07-05T08:29:03.142698+00:00","updated_at":"2026-07-05T08:29:03.142698+00:00"}