{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DAQ55NJ2K4F5OWRV7VM7Y25LIH","short_pith_number":"pith:DAQ55NJ2","schema_version":"1.0","canonical_sha256":"1821deb53a570bd75a35fd59fc6bab41e8c85130451b4a9c1d241c15b45eefec","source":{"kind":"arxiv","id":"2407.06177","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language Models under Cultural and Inclusive Considerations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.CV","authors_text":"Anders S{\\o}gaard, Antonia Karamolegkou, Daniel Hershcovich, Phillip Rust, Ruixiang Cui, Yong Cao","submitted_at":"2024-07-08T17:50:00Z","abstract_excerpt":"Large vision-language models (VLMs) can assist visually impaired people by describing images from their daily lives. Current evaluation datasets may not reflect diverse cultural user backgrounds or the situational context of this use case. To address this problem, we create a survey to determine caption preferences and propose a culture-centric evaluation benchmark by filtering VizWiz, an existing dataset with images taken by people who are blind. We then evaluate several VLMs, investigating their reliability as visual assistants in a culturally diverse setting. While our results for state-of-"},"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":"2407.06177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T17:50:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"649f94fa662892b592ac6cfbae98653deed21ee38c79c92ce19384d52d98b3a4","abstract_canon_sha256":"959de69d1c543fe420e4166bdc638a399d6f4558da4f9e4b4da19f7d63b0edd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:24.676486Z","signature_b64":"e3tnxm7VkqIhEEtXHuybNFZ6r/1zcIuDruLFBg9bTuJGxYEbXi3yE+SLRpciUcUzfL4jqsXJN5sC5+rYSwvcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1821deb53a570bd75a35fd59fc6bab41e8c85130451b4a9c1d241c15b45eefec","last_reissued_at":"2026-07-05T08:41:24.676049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:24.676049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Models under Cultural and Inclusive Considerations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.CV","authors_text":"Anders S{\\o}gaard, Antonia Karamolegkou, Daniel Hershcovich, Phillip Rust, Ruixiang Cui, Yong Cao","submitted_at":"2024-07-08T17:50:00Z","abstract_excerpt":"Large vision-language models (VLMs) can assist visually impaired people by describing images from their daily lives. Current evaluation datasets may not reflect diverse cultural user backgrounds or the situational context of this use case. To address this problem, we create a survey to determine caption preferences and propose a culture-centric evaluation benchmark by filtering VizWiz, an existing dataset with images taken by people who are blind. We then evaluate several VLMs, investigating their reliability as visual assistants in a culturally diverse setting. While our results for state-of-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06177","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/2407.06177/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":"2407.06177","created_at":"2026-07-05T08:41:24.676106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06177v1","created_at":"2026-07-05T08:41:24.676106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06177","created_at":"2026-07-05T08:41:24.676106+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAQ55NJ2K4F5","created_at":"2026-07-05T08:41:24.676106+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAQ55NJ2K4F5OWRV","created_at":"2026-07-05T08:41:24.676106+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAQ55NJ2","created_at":"2026-07-05T08:41:24.676106+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/DAQ55NJ2K4F5OWRV7VM7Y25LIH","json":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH.json","graph_json":"https://pith.science/api/pith-number/DAQ55NJ2K4F5OWRV7VM7Y25LIH/graph.json","events_json":"https://pith.science/api/pith-number/DAQ55NJ2K4F5OWRV7VM7Y25LIH/events.json","paper":"https://pith.science/paper/DAQ55NJ2"},"agent_actions":{"view_html":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH","download_json":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH.json","view_paper":"https://pith.science/paper/DAQ55NJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06177&json=true","fetch_graph":"https://pith.science/api/pith-number/DAQ55NJ2K4F5OWRV7VM7Y25LIH/graph.json","fetch_events":"https://pith.science/api/pith-number/DAQ55NJ2K4F5OWRV7VM7Y25LIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH/action/storage_attestation","attest_author":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH/action/author_attestation","sign_citation":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH/action/citation_signature","submit_replication":"https://pith.science/pith/DAQ55NJ2K4F5OWRV7VM7Y25LIH/action/replication_record"}},"created_at":"2026-07-05T08:41:24.676106+00:00","updated_at":"2026-07-05T08:41:24.676106+00:00"}