{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7OYKVYCAVFQPRDOUHN5SFX2Y7O","short_pith_number":"pith:7OYKVYCA","schema_version":"1.0","canonical_sha256":"fbb0aae040a960f88dd43b7b22df58fbbff412325ba0edd05fbe0e341909a7fa","source":{"kind":"arxiv","id":"2503.22610","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.HC","authors_text":"Anders S{\\o}gaard, Antonia Karamolegkou, Danae Sanchez Villegas, Daniel Hershcovich, Georgios Pantazopoulos, Malvina Nikandrou, Phillip Rust, Ruchira Dhar","submitted_at":"2025-03-28T16:54:25Z","abstract_excerpt":"This paper explores the effectiveness of Multimodal Large Language models (MLLMs) as assistive technologies for visually impaired individuals. We conduct a user survey to identify adoption patterns and key challenges users face with such technologies. Despite a high adoption rate of these models, our findings highlight concerns related to contextual understanding, cultural sensitivity, and complex scene understanding, particularly for individuals who may rely solely on them for visual interpretation. Informed by these results, we collate five user-centred tasks with image and video inputs, inc"},"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":"2503.22610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-28T16:54:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY","cs.LG"],"title_canon_sha256":"65c38ad81806353798a1288bfc57f2dd238a33b11cf2f7ad4e85d8356dc62cc6","abstract_canon_sha256":"6db69855d4a84a8bff04c473463c5c84b1cd0f3a8a96ecbdfd8d4ea919e542b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:07.686532Z","signature_b64":"FtuMeAOkzkiM0PFpG2EIOQ+henb0MKhcM7ne3kOKYlvcqMwdrEHJdwD4JG3eMewh264TUwV5bHe33QzGW/ypDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb0aae040a960f88dd43b7b22df58fbbff412325ba0edd05fbe0e341909a7fa","last_reissued_at":"2026-07-05T10:41:07.686006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:07.686006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY","cs.LG"],"primary_cat":"cs.HC","authors_text":"Anders S{\\o}gaard, Antonia Karamolegkou, Danae Sanchez Villegas, Daniel Hershcovich, Georgios Pantazopoulos, Malvina Nikandrou, Phillip Rust, Ruchira Dhar","submitted_at":"2025-03-28T16:54:25Z","abstract_excerpt":"This paper explores the effectiveness of Multimodal Large Language models (MLLMs) as assistive technologies for visually impaired individuals. We conduct a user survey to identify adoption patterns and key challenges users face with such technologies. Despite a high adoption rate of these models, our findings highlight concerns related to contextual understanding, cultural sensitivity, and complex scene understanding, particularly for individuals who may rely solely on them for visual interpretation. Informed by these results, we collate five user-centred tasks with image and video inputs, inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22610","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/2503.22610/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":"2503.22610","created_at":"2026-07-05T10:41:07.686066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22610v1","created_at":"2026-07-05T10:41:07.686066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22610","created_at":"2026-07-05T10:41:07.686066+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OYKVYCAVFQP","created_at":"2026-07-05T10:41:07.686066+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OYKVYCAVFQPRDOU","created_at":"2026-07-05T10:41:07.686066+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OYKVYCA","created_at":"2026-07-05T10:41:07.686066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25084","citing_title":"Are We There Yet? Exploring the Capabilities of MLLMs in Assistive AI Applications","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O","json":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O.json","graph_json":"https://pith.science/api/pith-number/7OYKVYCAVFQPRDOUHN5SFX2Y7O/graph.json","events_json":"https://pith.science/api/pith-number/7OYKVYCAVFQPRDOUHN5SFX2Y7O/events.json","paper":"https://pith.science/paper/7OYKVYCA"},"agent_actions":{"view_html":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O","download_json":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O.json","view_paper":"https://pith.science/paper/7OYKVYCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22610&json=true","fetch_graph":"https://pith.science/api/pith-number/7OYKVYCAVFQPRDOUHN5SFX2Y7O/graph.json","fetch_events":"https://pith.science/api/pith-number/7OYKVYCAVFQPRDOUHN5SFX2Y7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O/action/storage_attestation","attest_author":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O/action/author_attestation","sign_citation":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O/action/citation_signature","submit_replication":"https://pith.science/pith/7OYKVYCAVFQPRDOUHN5SFX2Y7O/action/replication_record"}},"created_at":"2026-07-05T10:41:07.686066+00:00","updated_at":"2026-07-05T10:41:07.686066+00:00"}