{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ATTN5XDI7LPPPSEAQHBHBNYWMF","short_pith_number":"pith:ATTN5XDI","schema_version":"1.0","canonical_sha256":"04e6dedc68fadef7c88081c270b716615b02120780e628c30cf3abc6e34decff","source":{"kind":"arxiv","id":"2310.20501","version":3},"attestation_state":"computed","paper":{"title":"Neural Retrievers are Biased Towards LLM-Generated Content","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Gang Wang, Jun Xu, Liang Pang, Sunhao Dai, Weihao Liu, Xiaolin Hu, Xiao Zhang, Yong Liu, Yuqi Zhou","submitted_at":"2023-10-31T14:42:23Z","abstract_excerpt":"Recently, the emergence of large language models (LLMs) has revolutionized the paradigm of information retrieval (IR) applications, especially in web search, by generating vast amounts of human-like texts on the Internet. As a result, IR systems in the LLM era are facing a new challenge: the indexed documents are now not only written by human beings but also automatically generated by the LLMs. How these LLM-generated documents influence the IR systems is a pressing and still unexplored question. In this work, we conduct a quantitative evaluation of IR models in scenarios where both human-writ"},"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":"2310.20501","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2023-10-31T14:42:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"67dc0af2a133e877671dddfa47107c7b92a6111cb554414606bbcd2178778aba","abstract_canon_sha256":"2177c4962c6ef2743eb0150e85954a66cc1c78a235b8a7b474d53553df433f77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:25.379719Z","signature_b64":"H7k5Y6Hio+zvitVhaF5Z9pH3A9sHqptsyjGBCB05SVcb3YlE17UmYC77G0XRIOOq2GrZYMd4FBlpEn8TPn0uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e6dedc68fadef7c88081c270b716615b02120780e628c30cf3abc6e34decff","last_reissued_at":"2026-07-05T08:50:25.379260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:25.379260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Retrievers are Biased Towards LLM-Generated Content","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Gang Wang, Jun Xu, Liang Pang, Sunhao Dai, Weihao Liu, Xiaolin Hu, Xiao Zhang, Yong Liu, Yuqi Zhou","submitted_at":"2023-10-31T14:42:23Z","abstract_excerpt":"Recently, the emergence of large language models (LLMs) has revolutionized the paradigm of information retrieval (IR) applications, especially in web search, by generating vast amounts of human-like texts on the Internet. As a result, IR systems in the LLM era are facing a new challenge: the indexed documents are now not only written by human beings but also automatically generated by the LLMs. How these LLM-generated documents influence the IR systems is a pressing and still unexplored question. In this work, we conduct a quantitative evaluation of IR models in scenarios where both human-writ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20501","kind":"arxiv","version":3},"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/2310.20501/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":"2310.20501","created_at":"2026-07-05T08:50:25.379325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20501v3","created_at":"2026-07-05T08:50:25.379325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20501","created_at":"2026-07-05T08:50:25.379325+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATTN5XDI7LPP","created_at":"2026-07-05T08:50:25.379325+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATTN5XDI7LPPPSEA","created_at":"2026-07-05T08:50:25.379325+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATTN5XDI","created_at":"2026-07-05T08:50:25.379325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF","json":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF.json","graph_json":"https://pith.science/api/pith-number/ATTN5XDI7LPPPSEAQHBHBNYWMF/graph.json","events_json":"https://pith.science/api/pith-number/ATTN5XDI7LPPPSEAQHBHBNYWMF/events.json","paper":"https://pith.science/paper/ATTN5XDI"},"agent_actions":{"view_html":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF","download_json":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF.json","view_paper":"https://pith.science/paper/ATTN5XDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20501&json=true","fetch_graph":"https://pith.science/api/pith-number/ATTN5XDI7LPPPSEAQHBHBNYWMF/graph.json","fetch_events":"https://pith.science/api/pith-number/ATTN5XDI7LPPPSEAQHBHBNYWMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF/action/storage_attestation","attest_author":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF/action/author_attestation","sign_citation":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF/action/citation_signature","submit_replication":"https://pith.science/pith/ATTN5XDI7LPPPSEAQHBHBNYWMF/action/replication_record"}},"created_at":"2026-07-05T08:50:25.379325+00:00","updated_at":"2026-07-05T08:50:25.379325+00:00"}