{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CL34BT735BH4K4HAJBU242EO4S","short_pith_number":"pith:CL34BT73","schema_version":"1.0","canonical_sha256":"12f7c0cffbe84fc570e04869ae688ee48e20364580a6a4483466a7fa941e0845","source":{"kind":"arxiv","id":"2507.04294","version":1},"attestation_state":"computed","paper":{"title":"BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chaochao Chen, Jiaming Zhang, Li Zhang, Xiaohua Feng, Yiqun Xu, Yuyuan Li, Zhifei Ren","submitted_at":"2025-07-06T08:39:26Z","abstract_excerpt":"Large Language Model-enhanced Recommender Systems (LLM-enhanced RSs) have emerged as a powerful approach to improving recommendation quality by leveraging LLMs to generate item representations. Despite these advancements, the integration of LLMs raises severe fairness concerns. Existing studies reveal that LLM-based RSs exhibit greater unfairness than traditional RSs, yet fairness issues in LLM-enhanced RSs remain largely unexplored. In this paper, our empirical study reveals that while LLM-enhanced RSs improve fairness across item groups, a significant fairness gap persists. Further enhanceme"},"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":"2507.04294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-07-06T08:39:26Z","cross_cats_sorted":[],"title_canon_sha256":"7eff094ea9897a1fdeebb3fcf426afc069958795a79cf16986bf7cb92f4dc2f6","abstract_canon_sha256":"7d184a64d8c61fc1340dac676e13928e5ef96daaa0c1dcd89300e60b4167a3d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:45.316619Z","signature_b64":"DSlBpAMBxPrsGW8CmVV+Uk7mjMF2TO+YMVEXooCHDsUcExseuT3REgI+36Ebl9+XcBsN9fLbmghi4CCMl9iHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12f7c0cffbe84fc570e04869ae688ee48e20364580a6a4483466a7fa941e0845","last_reissued_at":"2026-07-05T11:32:45.316102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:45.316102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chaochao Chen, Jiaming Zhang, Li Zhang, Xiaohua Feng, Yiqun Xu, Yuyuan Li, Zhifei Ren","submitted_at":"2025-07-06T08:39:26Z","abstract_excerpt":"Large Language Model-enhanced Recommender Systems (LLM-enhanced RSs) have emerged as a powerful approach to improving recommendation quality by leveraging LLMs to generate item representations. Despite these advancements, the integration of LLMs raises severe fairness concerns. Existing studies reveal that LLM-based RSs exhibit greater unfairness than traditional RSs, yet fairness issues in LLM-enhanced RSs remain largely unexplored. In this paper, our empirical study reveals that while LLM-enhanced RSs improve fairness across item groups, a significant fairness gap persists. Further enhanceme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04294","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/2507.04294/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":"2507.04294","created_at":"2026-07-05T11:32:45.316165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04294v1","created_at":"2026-07-05T11:32:45.316165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04294","created_at":"2026-07-05T11:32:45.316165+00:00"},{"alias_kind":"pith_short_12","alias_value":"CL34BT735BH4","created_at":"2026-07-05T11:32:45.316165+00:00"},{"alias_kind":"pith_short_16","alias_value":"CL34BT735BH4K4HA","created_at":"2026-07-05T11:32:45.316165+00:00"},{"alias_kind":"pith_short_8","alias_value":"CL34BT73","created_at":"2026-07-05T11:32:45.316165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":295,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22549","citing_title":"ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S","json":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S.json","graph_json":"https://pith.science/api/pith-number/CL34BT735BH4K4HAJBU242EO4S/graph.json","events_json":"https://pith.science/api/pith-number/CL34BT735BH4K4HAJBU242EO4S/events.json","paper":"https://pith.science/paper/CL34BT73"},"agent_actions":{"view_html":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S","download_json":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S.json","view_paper":"https://pith.science/paper/CL34BT73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04294&json=true","fetch_graph":"https://pith.science/api/pith-number/CL34BT735BH4K4HAJBU242EO4S/graph.json","fetch_events":"https://pith.science/api/pith-number/CL34BT735BH4K4HAJBU242EO4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S/action/storage_attestation","attest_author":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S/action/author_attestation","sign_citation":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S/action/citation_signature","submit_replication":"https://pith.science/pith/CL34BT735BH4K4HAJBU242EO4S/action/replication_record"}},"created_at":"2026-07-05T11:32:45.316165+00:00","updated_at":"2026-07-05T11:32:45.316165+00:00"}