{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I2CU5E2QGHTUBY5YZKU7NC4ON2","short_pith_number":"pith:I2CU5E2Q","schema_version":"1.0","canonical_sha256":"46854e935031e740e3b8caa9f68b8e6e965dc7e5b3cd350598b2f14f95e52287","source":{"kind":"arxiv","id":"2402.01735","version":2},"attestation_state":"computed","paper":{"title":"VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Hillming Li, Jing Li, Rong Xiang, Yilin Zhang, Yi Zhao","submitted_at":"2024-01-29T08:28:32Z","abstract_excerpt":"Visually Impaired Assistance (VIA) aims to automatically help the visually impaired (VI) handle daily activities. The advancement of VIA primarily depends on developments in Computer Vision (CV) and Natural Language Processing (NLP), both of which exhibit cutting-edge paradigms with large models (LMs). Furthermore, LMs have shown exceptional multimodal abilities to tackle challenging physically-grounded tasks such as embodied robots. To investigate the potential and limitations of state-of-the-art (SOTA) LMs' capabilities in VIA applications, we present an extensive study for the task of VIA w"},"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":"2402.01735","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T08:28:32Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"cac2b08704defccccbcb1118cbef08e1d2300f9e3a75279a36b1c121f9d56b06","abstract_canon_sha256":"fa61821172d3b8838af05b4d748d62d15be5fc29e4ee73a82306069cfd8ba943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:35.356903Z","signature_b64":"fcRWwsdF9D15u5nrZznmSQ8yi0VPNLnPwrGpo/W0qTnW3rRaPslQOrQ/LYBJDdl5KLOoU7PBUkMgz1jkjpVBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46854e935031e740e3b8caa9f68b8e6e965dc7e5b3cd350598b2f14f95e52287","last_reissued_at":"2026-07-05T07:43:35.356400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:35.356400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VIALM: A Survey and Benchmark of Visually Impaired Assistance with Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Hillming Li, Jing Li, Rong Xiang, Yilin Zhang, Yi Zhao","submitted_at":"2024-01-29T08:28:32Z","abstract_excerpt":"Visually Impaired Assistance (VIA) aims to automatically help the visually impaired (VI) handle daily activities. The advancement of VIA primarily depends on developments in Computer Vision (CV) and Natural Language Processing (NLP), both of which exhibit cutting-edge paradigms with large models (LMs). Furthermore, LMs have shown exceptional multimodal abilities to tackle challenging physically-grounded tasks such as embodied robots. To investigate the potential and limitations of state-of-the-art (SOTA) LMs' capabilities in VIA applications, we present an extensive study for the task of VIA w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01735","kind":"arxiv","version":2},"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/2402.01735/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":"2402.01735","created_at":"2026-07-05T07:43:35.356458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01735v2","created_at":"2026-07-05T07:43:35.356458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01735","created_at":"2026-07-05T07:43:35.356458+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2CU5E2QGHTU","created_at":"2026-07-05T07:43:35.356458+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2CU5E2QGHTUBY5Y","created_at":"2026-07-05T07:43:35.356458+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2CU5E2Q","created_at":"2026-07-05T07:43:35.356458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.12844","citing_title":"GuideDog: A Real-World Egocentric Multimodal Dataset for Blind and Low-Vision Accessibility-Aware Guidance","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11782","citing_title":"Urban Risk-Aware Navigation via VQA-Based Event Maps for People with Low Vision","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2","json":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2.json","graph_json":"https://pith.science/api/pith-number/I2CU5E2QGHTUBY5YZKU7NC4ON2/graph.json","events_json":"https://pith.science/api/pith-number/I2CU5E2QGHTUBY5YZKU7NC4ON2/events.json","paper":"https://pith.science/paper/I2CU5E2Q"},"agent_actions":{"view_html":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2","download_json":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2.json","view_paper":"https://pith.science/paper/I2CU5E2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01735&json=true","fetch_graph":"https://pith.science/api/pith-number/I2CU5E2QGHTUBY5YZKU7NC4ON2/graph.json","fetch_events":"https://pith.science/api/pith-number/I2CU5E2QGHTUBY5YZKU7NC4ON2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2/action/storage_attestation","attest_author":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2/action/author_attestation","sign_citation":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2/action/citation_signature","submit_replication":"https://pith.science/pith/I2CU5E2QGHTUBY5YZKU7NC4ON2/action/replication_record"}},"created_at":"2026-07-05T07:43:35.356458+00:00","updated_at":"2026-07-05T07:43:35.356458+00:00"}