{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:25C7H22O4WSAKGQLER3VK7VROY","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":"c4d54d44c76522cb6361bc3423b7f61e4829c1ec41d8bf200ddfce7c21cac821","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T04:57:51Z","title_canon_sha256":"a3492896508a81b41f0b28a5042f7c3326100dbf2873b763827ad7262f7de74d"},"schema_version":"1.0","source":{"id":"2606.12898","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12898","created_at":"2026-06-12T01:09:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12898v1","created_at":"2026-06-12T01:09:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12898","created_at":"2026-06-12T01:09:31Z"},{"alias_kind":"pith_short_12","alias_value":"25C7H22O4WSA","created_at":"2026-06-12T01:09:31Z"},{"alias_kind":"pith_short_16","alias_value":"25C7H22O4WSAKGQL","created_at":"2026-06-12T01:09:31Z"},{"alias_kind":"pith_short_8","alias_value":"25C7H22O","created_at":"2026-06-12T01:09:31Z"}],"graph_snapshots":[{"event_id":"sha256:c57bc105a6e0fba4343e217572db4c9cdab09aa449da277bdf8507db4b258200","target":"graph","created_at":"2026-06-12T01:09:31Z","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/2606.12898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Text Comprehension (VTC) renders text into images for a vision-language model (VLM) to read, sidestepping LLM context-window limits and powering applications from long-page OCR to multi-page memory QA. Yet existing VTC pipelines treat rendering and layout as a fixed, content-agnostic preprocessing step and offer little mechanistic understanding of how VLMs internally process visualized text. Through a focused empirical study on VTC QA tasks, we reveal that VLMs exhibit a localization-without-utilization regime: evidence-localizing attention emerges sharply in the middle-to-late layers a","authors_text":"Hui Liu, Kai Guo, Qirui Wang, Shenglai Zeng, Xianxuan Long, Xinnan Dai","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T04:57:51Z","title":"Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12898","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":"sha256:56f76c1304921af9db26404c80256ff2d6bfbae379a702604d1b44c9c7b086f6","target":"record","created_at":"2026-06-12T01:09:31Z","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":"c4d54d44c76522cb6361bc3423b7f61e4829c1ec41d8bf200ddfce7c21cac821","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-11T04:57:51Z","title_canon_sha256":"a3492896508a81b41f0b28a5042f7c3326100dbf2873b763827ad7262f7de74d"},"schema_version":"1.0","source":{"id":"2606.12898","kind":"arxiv","version":1}},"canonical_sha256":"d745f3eb4ee5a4051a0b2477557eb176294b7090b1ff147e1eb68b2e09f2f3b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d745f3eb4ee5a4051a0b2477557eb176294b7090b1ff147e1eb68b2e09f2f3b3","first_computed_at":"2026-06-12T01:09:31.798994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:31.798994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q8TxzVMtlKpl3uhYHPBA8xCtx7puqBQ7JIhiF4TsEa3zDCpb4PMD3Ha5uU2QzKME6L/Udjm1LSweXTeD8UpnCQ==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:31.799482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12898","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56f76c1304921af9db26404c80256ff2d6bfbae379a702604d1b44c9c7b086f6","sha256:c57bc105a6e0fba4343e217572db4c9cdab09aa449da277bdf8507db4b258200"],"state_sha256":"16a4133a2d686a3f671342d6801d82b2f9ef8d31560101e878863739e840cbe2"}