{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","short_pith_number":"pith:AQ7X7DDA","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"},"canonical_sha256":"043f7f8c6049de8fc7092675988f82fe31d179a1a494c32cbada3b36244305c6","source":{"kind":"arxiv","id":"2602.04802","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04802","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04802v2","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04802","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"AQ7X7DDAJHPI","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_16","alias_value":"AQ7X7DDAJHPI7RYJ","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_8","alias_value":"AQ7X7DDA","created_at":"2026-05-20T00:03:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","target":"record","payload":{"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"},"canonical_sha256":"043f7f8c6049de8fc7092675988f82fe31d179a1a494c32cbada3b36244305c6","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"},"source_kind":"arxiv","source_id":"2602.04802","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKSG72yN0LGRbFauvg7SS7anyD/hK+aqQ0oZBZmR/kujMeGLNSzRE5P2hoU8bfEyN2ipDTRMY8YjsxlHS5J2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:40:25.601015Z"},"content_sha256":"f513f2bd888509d213dd74cd1254d0b83c0f7fde347eb88332502d49c7168bc6","schema_version":"1.0","event_id":"sha256:f513f2bd888509d213dd74cd1254d0b83c0f7fde347eb88332502d49c7168bc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQHojQ6wY3VDkSX4DyR/L4d1Z0pO1jBQWddZhW/LIPpb/IcUhRFmk9dmsWmTvwWPiedLLfEtPFj6TWYLBy91Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:40:25.601732Z"},"content_sha256":"83c80aea5be2d33793609bc601e8b8e4d10a2df7408d4066dc857ac2af5e45d9","schema_version":"1.0","event_id":"sha256:83c80aea5be2d33793609bc601e8b8e4d10a2df7408d4066dc857ac2af5e45d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/bundle.json","state_url":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T19:40:25Z","links":{"resolver":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","bundle":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/bundle.json","state":"https://pith.science/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AQ7X7DDAJHPI7RYJEZ2ZRD4C7Y","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56faab36cd5362bd5370562ed50ce17b0c3ad897116b7de85bcbcdd5116a4c31","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T17:48:55Z","title_canon_sha256":"f6571c3eecc1637dc5f1af641b9554b1ea5c4ded8c399267cb72f574bc581164"},"schema_version":"1.0","source":{"id":"2602.04802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04802","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04802v2","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04802","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_12","alias_value":"AQ7X7DDAJHPI","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_16","alias_value":"AQ7X7DDAJHPI7RYJ","created_at":"2026-05-20T00:03:04Z"},{"alias_kind":"pith_short_8","alias_value":"AQ7X7DDA","created_at":"2026-05-20T00:03:04Z"}],"graph_snapshots":[{"event_id":"sha256:83c80aea5be2d33793609bc601e8b8e4d10a2df7408d4066dc857ac2af5e45d9","target":"graph","created_at":"2026-05-20T00:03:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.04802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haiwen Diao, Huchuan Lu, Juntong Feng, Qing'an Liu, Xinzhe Han, Yue Zhu, Yuhao Wang, Yujie Cheng, Yunzhi Zhuge","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T17:48:55Z","title":"VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04802","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f513f2bd888509d213dd74cd1254d0b83c0f7fde347eb88332502d49c7168bc6","target":"record","created_at":"2026-05-20T00:03:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56faab36cd5362bd5370562ed50ce17b0c3ad897116b7de85bcbcdd5116a4c31","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-04T17:48:55Z","title_canon_sha256":"f6571c3eecc1637dc5f1af641b9554b1ea5c4ded8c399267cb72f574bc581164"},"schema_version":"1.0","source":{"id":"2602.04802","kind":"arxiv","version":2}},"canonical_sha256":"043f7f8c6049de8fc7092675988f82fe31d179a1a494c32cbada3b36244305c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"043f7f8c6049de8fc7092675988f82fe31d179a1a494c32cbada3b36244305c6","first_computed_at":"2026-05-20T00:03:04.643626Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:04.643626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ac575JANYmn0tnxZRG2I1CnkUptQgzWCeZ2w4yAtuXvhF11vrC9GVaUtr5evzvxP03+eaQbw4KzpQ4p31VejBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:04.644544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f513f2bd888509d213dd74cd1254d0b83c0f7fde347eb88332502d49c7168bc6","sha256:83c80aea5be2d33793609bc601e8b8e4d10a2df7408d4066dc857ac2af5e45d9"],"state_sha256":"e94e3be204a6f61cb0da4223756efaca94db5d9ebf3e00da489cdf1970f84360"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bzv+uku5Ny14yzeYrHSfe0sjg85MxaRqLiw/SkIawu7icMP4ZLifk02m6sX4ugtwHepFOsd1hd+y31ErJOurCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:40:25.605629Z","bundle_sha256":"be17535fee5a1b008401ee6d850194242d039c258baf754a2c7df02d9902fb9e"}}