{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDIIHZKZQGWBTBZMUWIOI6JCCM","short_pith_number":"pith:MDIIHZKZ","schema_version":"1.0","canonical_sha256":"60d083e55981ac19872ca590e4792213159dc548fd53f2673fa02479db422f43","source":{"kind":"arxiv","id":"2404.02508","version":1},"attestation_state":"computed","paper":{"title":"VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bufang Yang, Kaiwei Liu, Lixing He, Zhenyu Yan","submitted_at":"2024-04-03T06:53:27Z","abstract_excerpt":"Individuals with visual impairments, encompassing both partial and total difficulties in visual perception, are referred to as visually impaired (VI) people. An estimated 2.2 billion individuals worldwide are affected by visual impairments. Recent advancements in multi-modal large language models (MLLMs) have showcased their extraordinary capabilities across various domains. It is desirable to help VI individuals with MLLMs' great capabilities of visual understanding and reasoning. However, it is challenging for VI people to use MLLMs due to the difficulties in capturing the desirable images 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":"2404.02508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-03T06:53:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"33e9b44a228d024a4d98b62e8204e98bf471094535e02e2e8e07e35083e2251d","abstract_canon_sha256":"91f00d7ef8a09589277a5074c5fef3f39fff0c746e3ae727e255cae6acf469d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:57.421272Z","signature_b64":"Y7nn90FTJ9lL54QUTS8+psfzKUL8VBSsG5UV0f/KgkGq5nDP/d2bpNEy/RFP663KX+B7m8qx0meft0TulH9OAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60d083e55981ac19872ca590e4792213159dc548fd53f2673fa02479db422f43","last_reissued_at":"2026-07-05T08:03:57.420752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:57.420752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bufang Yang, Kaiwei Liu, Lixing He, Zhenyu Yan","submitted_at":"2024-04-03T06:53:27Z","abstract_excerpt":"Individuals with visual impairments, encompassing both partial and total difficulties in visual perception, are referred to as visually impaired (VI) people. An estimated 2.2 billion individuals worldwide are affected by visual impairments. Recent advancements in multi-modal large language models (MLLMs) have showcased their extraordinary capabilities across various domains. It is desirable to help VI individuals with MLLMs' great capabilities of visual understanding and reasoning. However, it is challenging for VI people to use MLLMs due to the difficulties in capturing the desirable images t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02508","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/2404.02508/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":"2404.02508","created_at":"2026-07-05T08:03:57.420820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02508v1","created_at":"2026-07-05T08:03:57.420820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02508","created_at":"2026-07-05T08:03:57.420820+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDIIHZKZQGWB","created_at":"2026-07-05T08:03:57.420820+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDIIHZKZQGWBTBZM","created_at":"2026-07-05T08:03:57.420820+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDIIHZKZ","created_at":"2026-07-05T08:03:57.420820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":157,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM","json":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM.json","graph_json":"https://pith.science/api/pith-number/MDIIHZKZQGWBTBZMUWIOI6JCCM/graph.json","events_json":"https://pith.science/api/pith-number/MDIIHZKZQGWBTBZMUWIOI6JCCM/events.json","paper":"https://pith.science/paper/MDIIHZKZ"},"agent_actions":{"view_html":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM","download_json":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM.json","view_paper":"https://pith.science/paper/MDIIHZKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02508&json=true","fetch_graph":"https://pith.science/api/pith-number/MDIIHZKZQGWBTBZMUWIOI6JCCM/graph.json","fetch_events":"https://pith.science/api/pith-number/MDIIHZKZQGWBTBZMUWIOI6JCCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM/action/storage_attestation","attest_author":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM/action/author_attestation","sign_citation":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM/action/citation_signature","submit_replication":"https://pith.science/pith/MDIIHZKZQGWBTBZMUWIOI6JCCM/action/replication_record"}},"created_at":"2026-07-05T08:03:57.420820+00:00","updated_at":"2026-07-05T08:03:57.420820+00:00"}