{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QD33QCM5HI73UKCEI5THFRE2BH","short_pith_number":"pith:QD33QCM5","schema_version":"1.0","canonical_sha256":"80f7b8099d3a3fba2844476672c49a09e2609ecdd9a7bb81c17e79b68005e458","source":{"kind":"arxiv","id":"2410.06967","version":1},"attestation_state":"computed","paper":{"title":"$\\texttt{ModSCAN}$: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Xinyue Shen, Yang Zhang, Yugeng Liu, Yukun Jiang, Zheng Li","submitted_at":"2024-10-09T15:07:05Z","abstract_excerpt":"Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored. In this study, we present a pioneering measurement framework, $\\texttt{ModSCAN}$, to $\\underline{SCAN}$ the stereotypical bias within LVLMs from both vision and language $\\underline{Mod}$alities. $\\texttt{ModSCAN}$ examines stereotypical biases with respect to two typical stereotypical attributes (gender and race) across three kinds of scenarios: occupations, descriptors, and persona traits. Our findings suggest that 1) t"},"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":"2410.06967","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-10-09T15:07:05Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"dcf42fc2f2a167b556dee3d0ab4920519e7a64098e3d717a834bce1eb1e2802c","abstract_canon_sha256":"1fc9e6d7c0d711df26c1d34dd144d908e760f4aa2cc2abe9912eeba965d1d782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:09.088066Z","signature_b64":"2btMScp5s2uXmosYTTF4XnVX5MJnLPWZJGJBeXPOP+nETZ7ujx1Iz0PdRf0os2m+7UMoIqi7hc8GzgpKg8kdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f7b8099d3a3fba2844476672c49a09e2609ecdd9a7bb81c17e79b68005e458","last_reissued_at":"2026-07-05T09:18:09.087644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:09.087644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\texttt{ModSCAN}$: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Xinyue Shen, Yang Zhang, Yugeng Liu, Yukun Jiang, Zheng Li","submitted_at":"2024-10-09T15:07:05Z","abstract_excerpt":"Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored. In this study, we present a pioneering measurement framework, $\\texttt{ModSCAN}$, to $\\underline{SCAN}$ the stereotypical bias within LVLMs from both vision and language $\\underline{Mod}$alities. $\\texttt{ModSCAN}$ examines stereotypical biases with respect to two typical stereotypical attributes (gender and race) across three kinds of scenarios: occupations, descriptors, and persona traits. Our findings suggest that 1) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06967","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/2410.06967/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":"2410.06967","created_at":"2026-07-05T09:18:09.087704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06967v1","created_at":"2026-07-05T09:18:09.087704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06967","created_at":"2026-07-05T09:18:09.087704+00:00"},{"alias_kind":"pith_short_12","alias_value":"QD33QCM5HI73","created_at":"2026-07-05T09:18:09.087704+00:00"},{"alias_kind":"pith_short_16","alias_value":"QD33QCM5HI73UKCE","created_at":"2026-07-05T09:18:09.087704+00:00"},{"alias_kind":"pith_short_8","alias_value":"QD33QCM5","created_at":"2026-07-05T09:18:09.087704+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/QD33QCM5HI73UKCEI5THFRE2BH","json":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH.json","graph_json":"https://pith.science/api/pith-number/QD33QCM5HI73UKCEI5THFRE2BH/graph.json","events_json":"https://pith.science/api/pith-number/QD33QCM5HI73UKCEI5THFRE2BH/events.json","paper":"https://pith.science/paper/QD33QCM5"},"agent_actions":{"view_html":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH","download_json":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH.json","view_paper":"https://pith.science/paper/QD33QCM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06967&json=true","fetch_graph":"https://pith.science/api/pith-number/QD33QCM5HI73UKCEI5THFRE2BH/graph.json","fetch_events":"https://pith.science/api/pith-number/QD33QCM5HI73UKCEI5THFRE2BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH/action/storage_attestation","attest_author":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH/action/author_attestation","sign_citation":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH/action/citation_signature","submit_replication":"https://pith.science/pith/QD33QCM5HI73UKCEI5THFRE2BH/action/replication_record"}},"created_at":"2026-07-05T09:18:09.087704+00:00","updated_at":"2026-07-05T09:18:09.087704+00:00"}