{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KWAEOJIZTXHSIPX2VBVZQI7T4K","short_pith_number":"pith:KWAEOJIZ","schema_version":"1.0","canonical_sha256":"55804725199dcf243efaa86b9823f3e2a39c01f0dc32273d1e166ca08df7b390","source":{"kind":"arxiv","id":"2311.14084","version":4},"attestation_state":"computed","paper":{"title":"Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.IR","authors_text":"Danyang Hou, Huawei Shen, Jingcheng Deng, Jun Xu, Liang Pang, Shicheng Xu, Xueqi Cheng","submitted_at":"2023-11-23T16:22:58Z","abstract_excerpt":"With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source bias in text retrieval for web search. Specifically, neural retrieval models tend to rank generated texts higher than human-written texts. In this paper, we extend the study of this bias to cross-modal retrieval. Firstly, we successfully construct a suitable benchmark to explore the existence of the bias. Subsequent extensive experiments on this benchmark reveal that AI-generated images introduce an invisible releva"},"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":"2311.14084","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-11-23T16:22:58Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"9e00a3fb4078e7bdbabc77331911da79628494926b6637ad87bfab485428b19b","abstract_canon_sha256":"75f10eb9f0e28693cee2e41f5937242b689633392a47a818ad81246aa0b33641"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:13.907035Z","signature_b64":"4ntNGtG6uH75Xur7uw/5/c+1O78uBpKaYqeCuHyrzYEbwqZkDCcIuBGWSRApw9f3hJ7bEi6zUWjBZz4+FHuNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55804725199dcf243efaa86b9823f3e2a39c01f0dc32273d1e166ca08df7b390","last_reissued_at":"2026-07-05T08:23:13.906587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:13.906587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invisible Relevance Bias: Text-Image Retrieval Models Prefer AI-Generated Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.IR","authors_text":"Danyang Hou, Huawei Shen, Jingcheng Deng, Jun Xu, Liang Pang, Shicheng Xu, Xueqi Cheng","submitted_at":"2023-11-23T16:22:58Z","abstract_excerpt":"With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source bias in text retrieval for web search. Specifically, neural retrieval models tend to rank generated texts higher than human-written texts. In this paper, we extend the study of this bias to cross-modal retrieval. Firstly, we successfully construct a suitable benchmark to explore the existence of the bias. Subsequent extensive experiments on this benchmark reveal that AI-generated images introduce an invisible releva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14084","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/2311.14084/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":"2311.14084","created_at":"2026-07-05T08:23:13.906643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14084v4","created_at":"2026-07-05T08:23:13.906643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14084","created_at":"2026-07-05T08:23:13.906643+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWAEOJIZTXHS","created_at":"2026-07-05T08:23:13.906643+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWAEOJIZTXHSIPX2","created_at":"2026-07-05T08:23:13.906643+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWAEOJIZ","created_at":"2026-07-05T08:23:13.906643+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/KWAEOJIZTXHSIPX2VBVZQI7T4K","json":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K.json","graph_json":"https://pith.science/api/pith-number/KWAEOJIZTXHSIPX2VBVZQI7T4K/graph.json","events_json":"https://pith.science/api/pith-number/KWAEOJIZTXHSIPX2VBVZQI7T4K/events.json","paper":"https://pith.science/paper/KWAEOJIZ"},"agent_actions":{"view_html":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K","download_json":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K.json","view_paper":"https://pith.science/paper/KWAEOJIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14084&json=true","fetch_graph":"https://pith.science/api/pith-number/KWAEOJIZTXHSIPX2VBVZQI7T4K/graph.json","fetch_events":"https://pith.science/api/pith-number/KWAEOJIZTXHSIPX2VBVZQI7T4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K/action/storage_attestation","attest_author":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K/action/author_attestation","sign_citation":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K/action/citation_signature","submit_replication":"https://pith.science/pith/KWAEOJIZTXHSIPX2VBVZQI7T4K/action/replication_record"}},"created_at":"2026-07-05T08:23:13.906643+00:00","updated_at":"2026-07-05T08:23:13.906643+00:00"}