{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZX5GPWUT6GZ24ZDCCBMFIQQW7M","short_pith_number":"pith:ZX5GPWUT","schema_version":"1.0","canonical_sha256":"cdfa67da93f1b3ae64621058544216fb08b6a0e4d4d29026074822a500e4b065","source":{"kind":"arxiv","id":"2406.01285","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Buchholz, Jan Malte Lichtenberg, Pola Schw\\\"obel","submitted_at":"2024-06-03T12:53:37Z","abstract_excerpt":"The issue of popularity bias -- where popular items are disproportionately recommended, overshadowing less popular but potentially relevant items -- remains a significant challenge in recommender systems. Recent advancements have seen the integration of general-purpose Large Language Models (LLMs) into the architecture of such systems. This integration raises concerns that it might exacerbate popularity bias, given that the LLM's training data is likely dominated by popular items. However, it simultaneously presents a novel opportunity to address the bias via prompt tuning. Our study explores "},"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":"2406.01285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-03T12:53:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"602d91e3d7aaa560a3d68ac1a90711cf4610b4d0dfe3e11da49f7e5d3c91e03d","abstract_canon_sha256":"d0b7bd9b3509dbe24f86a702156c191f5d8a3ed2956a63222a8075777c9a98d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:37.907030Z","signature_b64":"zVntD5k5M9JrisiPCEfLu6w3mghT/0dnJUbOhVUFohaUpYEJ4V8Ll9QxY0OcYXMShNiSVmt4la02cz+yCrW6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdfa67da93f1b3ae64621058544216fb08b6a0e4d4d29026074822a500e4b065","last_reissued_at":"2026-07-05T08:26:37.906659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:37.906659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexander Buchholz, Jan Malte Lichtenberg, Pola Schw\\\"obel","submitted_at":"2024-06-03T12:53:37Z","abstract_excerpt":"The issue of popularity bias -- where popular items are disproportionately recommended, overshadowing less popular but potentially relevant items -- remains a significant challenge in recommender systems. Recent advancements have seen the integration of general-purpose Large Language Models (LLMs) into the architecture of such systems. This integration raises concerns that it might exacerbate popularity bias, given that the LLM's training data is likely dominated by popular items. However, it simultaneously presents a novel opportunity to address the bias via prompt tuning. Our study explores "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01285","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/2406.01285/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":"2406.01285","created_at":"2026-07-05T08:26:37.906729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01285v1","created_at":"2026-07-05T08:26:37.906729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01285","created_at":"2026-07-05T08:26:37.906729+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZX5GPWUT6GZ2","created_at":"2026-07-05T08:26:37.906729+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZX5GPWUT6GZ24ZDC","created_at":"2026-07-05T08:26:37.906729+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZX5GPWUT","created_at":"2026-07-05T08:26:37.906729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17443","citing_title":"Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10907","citing_title":"From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27439","citing_title":"Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recommendation: A 37,000-Run Audit","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30207","citing_title":"Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00540","citing_title":"Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19128","citing_title":"GraphRAG-IRL: Personalized Recommendation with Graph-Grounded Inverse Reinforcement Learning and LLM Re-ranking","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M","json":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M.json","graph_json":"https://pith.science/api/pith-number/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/graph.json","events_json":"https://pith.science/api/pith-number/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/events.json","paper":"https://pith.science/paper/ZX5GPWUT"},"agent_actions":{"view_html":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M","download_json":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M.json","view_paper":"https://pith.science/paper/ZX5GPWUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01285&json=true","fetch_graph":"https://pith.science/api/pith-number/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/graph.json","fetch_events":"https://pith.science/api/pith-number/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/action/storage_attestation","attest_author":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/action/author_attestation","sign_citation":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/action/citation_signature","submit_replication":"https://pith.science/pith/ZX5GPWUT6GZ24ZDCCBMFIQQW7M/action/replication_record"}},"created_at":"2026-07-05T08:26:37.906729+00:00","updated_at":"2026-07-05T08:26:37.906729+00:00"}