{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4GNA52HTEALCEQ7TLS34BRTN7E","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":"ce6cc8b5c5c54d83105fea94b3b1e06736be01b8662384069e45e9b5d8285d86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-10T08:34:28Z","title_canon_sha256":"d310bd3701fcf3dd8722caaea57a57b25921bba2149a14a1fb486e15f97d2389"},"schema_version":"1.0","source":{"id":"2512.11899","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.11899","created_at":"2026-07-22T01:23:34Z"},{"alias_kind":"arxiv_version","alias_value":"2512.11899v2","created_at":"2026-07-22T01:23:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11899","created_at":"2026-07-22T01:23:34Z"},{"alias_kind":"pith_short_12","alias_value":"4GNA52HTEALC","created_at":"2026-07-22T01:23:34Z"},{"alias_kind":"pith_short_16","alias_value":"4GNA52HTEALCEQ7T","created_at":"2026-07-22T01:23:34Z"},{"alias_kind":"pith_short_8","alias_value":"4GNA52HT","created_at":"2026-07-22T01:23:34Z"}],"graph_snapshots":[{"event_id":"sha256:0044fad407ebe9b9c941752aa4edfd6a05b527c91211e825e01c731ddf6e9330","target":"graph","created_at":"2026-07-22T01:23:34Z","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/2512.11899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) are vulnerable to typographic attacks, where misleading text inserted into an image can override visual understanding. However, existing evaluation protocols and defenses are largely focused on object recognition and do not consider text-reading capability. This is a critical oversight: real-world scenarios often require both recognizing objects and reading scene text (e.g., recognizing pedestrians while reading traffic signs), where simply ignoring all text for robustness is unacceptable in practice. To address this gap, we introduce a novel task, Read-or-","authors_text":"Daiki Shiono, Futa Waseda, Kento Sasaki, Shojiro Yamabe, Tsubasa Takahashi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-10T08:34:28Z","title":"Read or Ignore? A Unified Benchmark for Typographic-Attack Robustness and Text Recognition in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11899","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:cd272d601aab397a7b7b3dea21e3e55439f4cad24c6452bde5709c6f13d58e76","target":"record","created_at":"2026-07-22T01:23:34Z","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":"ce6cc8b5c5c54d83105fea94b3b1e06736be01b8662384069e45e9b5d8285d86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-10T08:34:28Z","title_canon_sha256":"d310bd3701fcf3dd8722caaea57a57b25921bba2149a14a1fb486e15f97d2389"},"schema_version":"1.0","source":{"id":"2512.11899","kind":"arxiv","version":2}},"canonical_sha256":"e19a0ee8f320162243f35cb7c0c66df90a036add908f69b43c1af866b9c5a384","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e19a0ee8f320162243f35cb7c0c66df90a036add908f69b43c1af866b9c5a384","first_computed_at":"2026-07-22T01:23:34.209508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:34.209508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ARYlk5rZ4iPy7R0sKj228nj93lAe+bqmi766B5xuokrXUnJDwv+wkRMiIObqV+iqcpLnUPA7d75JT901vYNsAg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:34.210519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.11899","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd272d601aab397a7b7b3dea21e3e55439f4cad24c6452bde5709c6f13d58e76","sha256:0044fad407ebe9b9c941752aa4edfd6a05b527c91211e825e01c731ddf6e9330"],"state_sha256":"d5badd169cf2238ee36fdea2f88810e5eeb609bee5d008dbb9a9d6547b92694a"}