{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHB5BAZ2XAX3O2ULLGWX3H7GPA","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":"6c0df7d9fff60c4e583434a93b2ef0e101dc5894b4f7ed4576f1c23ea810d937","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:55:24Z","title_canon_sha256":"302962ea1b3fda239348b8e101b2a266c0e2a9553d3a6a1555e9eecda1d445ac"},"schema_version":"1.0","source":{"id":"2607.02494","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02494","created_at":"2026-07-03T01:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02494v1","created_at":"2026-07-03T01:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02494","created_at":"2026-07-03T01:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"OHB5BAZ2XAX3","created_at":"2026-07-03T01:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"OHB5BAZ2XAX3O2UL","created_at":"2026-07-03T01:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"OHB5BAZ2","created_at":"2026-07-03T01:18:00Z"}],"graph_snapshots":[{"event_id":"sha256:378f3b9fdef70b941b5059d3cf3ea6c0c74e3ae0d938a70b24d89ceac8cd563f","target":"graph","created_at":"2026-07-03T01:18:00Z","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/2607.02494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language Models (LVLMs). Despite their widespread adoption, CLIP models exhibit a critical yet underexplored failure mode: irrelevant text appearing within images confounds visual representations, biasing them toward lexical meaning rather than true visual semantics. This robustness issue, commonly described as a Typographic Attack (TA), exposes a vulnerability that poses a significant risk to safety-critical applications such as autonomous driving. To achieve","authors_text":"Aidong Zhang, Bohan Liu, Guangzhi Xiong, Sanchit Sinha, Wenqian Ye, Zhenghao He","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:55:24Z","title":"Towards Robustness against Typographic Attack with Training-free Concept Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02494","kind":"arxiv","version":1},"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":"sha256:3c4cd79cbafd670a2242b9de4da44d1b11f903722402682795e87b49f8cfd497","target":"record","created_at":"2026-07-03T01:18:00Z","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":"6c0df7d9fff60c4e583434a93b2ef0e101dc5894b4f7ed4576f1c23ea810d937","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T17:55:24Z","title_canon_sha256":"302962ea1b3fda239348b8e101b2a266c0e2a9553d3a6a1555e9eecda1d445ac"},"schema_version":"1.0","source":{"id":"2607.02494","kind":"arxiv","version":1}},"canonical_sha256":"71c3d0833ab82fb76a8b59ad7d9fe6780149b3824bce705f9648a0d41c0b50df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71c3d0833ab82fb76a8b59ad7d9fe6780149b3824bce705f9648a0d41c0b50df","first_computed_at":"2026-07-03T01:18:00.863519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:18:00.863519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8ajjRnmyTvDaKlz5/kTT7kN4EzF9qtGFEE1cscrsfY5kBrr91ycx0dKIhhgKS60nUFW9Jin/IbbBM8gnJYEmCA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:18:00.863912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02494","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c4cd79cbafd670a2242b9de4da44d1b11f903722402682795e87b49f8cfd497","sha256:378f3b9fdef70b941b5059d3cf3ea6c0c74e3ae0d938a70b24d89ceac8cd563f"],"state_sha256":"399c4c091414e66e9c123a2b1caa43aa39cfe4ae19106c40c9c06572401c40f0"}