{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","short_pith_number":"pith:AQ7X7DDA","schema_version":"1.0","canonical_sha256":"043f7f8c6049de8fc7092675988f82fe31d179a1a494c32cbada3b36244305c6","source":{"kind":"arxiv","id":"2602.04802","version":2},"attestation_state":"computed","paper":{"title":"VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Diao, Huchuan Lu, Juntong Feng, Qing'an Liu, Xinzhe Han, Yue Zhu, Yuhao Wang, Yujie Cheng, Yunzhi Zhuge","submitted_at":"2026-02-04T17:48:55Z","abstract_excerpt":"Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also frequently appears as visualized text embedded in images, raising the question of whether current VLMs handle such input requests comparably. We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and visualized-text questions un"},"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":"2602.04802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T17:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"f6571c3eecc1637dc5f1af641b9554b1ea5c4ded8c399267cb72f574bc581164","abstract_canon_sha256":"56faab36cd5362bd5370562ed50ce17b0c3ad897116b7de85bcbcdd5116a4c31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:04.644544Z","signature_b64":"ac575JANYmn0tnxZRG2I1CnkUptQgzWCeZ2w4yAtuXvhF11vrC9GVaUtr5evzvxP03+eaQbw4KzpQ4p31VejBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"043f7f8c6049de8fc7092675988f82fe31d179a1a494c32cbada3b36244305c6","last_reissued_at":"2026-05-20T00:03:04.643626Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:04.643626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiwen Diao, Huchuan Lu, Juntong Feng, Qing'an Liu, Xinzhe Han, Yue Zhu, Yuhao Wang, Yujie Cheng, Yunzhi Zhuge","submitted_at":"2026-02-04T17:48:55Z","abstract_excerpt":"Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also frequently appears as visualized text embedded in images, raising the question of whether current VLMs handle such input requests comparably. We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and visualized-text questions un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04802","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/2602.04802/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":"2602.04802","created_at":"2026-05-20T00:03:04.643771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04802v2","created_at":"2026-05-20T00:03:04.643771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04802","created_at":"2026-05-20T00:03:04.643771+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQ7X7DDAJHPI","created_at":"2026-05-20T00:03:04.643771+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQ7X7DDAJHPI7RYJ","created_at":"2026-05-20T00:03:04.643771+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQ7X7DDA","created_at":"2026-05-20T00:03:04.643771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.25231","citing_title":"DRAGON: A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","json":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y.json","graph_json":"https://pith.science/api/pith-number/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/graph.json","events_json":"https://pith.science/api/pith-number/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/events.json","paper":"https://pith.science/paper/AQ7X7DDA"},"agent_actions":{"view_html":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","download_json":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y.json","view_paper":"https://pith.science/paper/AQ7X7DDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04802&json=true","fetch_graph":"https://pith.science/api/pith-number/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/graph.json","fetch_events":"https://pith.science/api/pith-number/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/action/storage_attestation","attest_author":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/action/author_attestation","sign_citation":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/action/citation_signature","submit_replication":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/action/replication_record"}},"created_at":"2026-05-20T00:03:04.643771+00:00","updated_at":"2026-05-20T00:03:04.643771+00:00"}