{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z7LZIMICBTKMZGK5TYFSQALFSJ","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":"3d8a7271187b00e5043138a39d2d9c092e99c90a5f91720a2f989b487d777347","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T17:57:03Z","title_canon_sha256":"c7f3a5c523654bdc3031cc1e98abf3364046c43c8af16ed8e9e524c29bd0d80d"},"schema_version":"1.0","source":{"id":"2607.09657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09657","created_at":"2026-07-13T01:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09657v1","created_at":"2026-07-13T01:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09657","created_at":"2026-07-13T01:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"Z7LZIMICBTKM","created_at":"2026-07-13T01:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"Z7LZIMICBTKMZGK5","created_at":"2026-07-13T01:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"Z7LZIMIC","created_at":"2026-07-13T01:20:28Z"}],"graph_snapshots":[{"event_id":"sha256:a23fdf1b733cd15cd827780079b10b35519de559a194c08ab021d8f9e5635a31","target":"graph","created_at":"2026-07-13T01:20:28Z","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/2607.09657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual representations, where figures, typeset equations, and page layouts carry rich information that cannot be faithfully or completely captured by text alone. Yet current pretraining approaches discard these visual cues by converting visually rich sources, such as documents and web pages, into plain text for learning language intelligence. This paper challenges the default assumption that language models must be trained","authors_text":"Bin Liu, Demin Song, Gaoang Wang, Haian Huang, Haijun Lv, Haiteng Zhao, Haochen Ye, Kai Chen, Kuikun Liu, Qipeng Guo, Tianyang Lin, Wenwei Zhang, Yiming Zhang, Yunhua Zhou, Yuzhe Gu, Zhonghan Zhao","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T17:57:03Z","title":"Scalable Visual Pretraining for Language Intelligence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09657","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":"sha256:0fafa3a2d4db8c648afc4a028b1bc2b079e2991a77e4ccd20e8001d28168dc16","target":"record","created_at":"2026-07-13T01:20:28Z","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":"3d8a7271187b00e5043138a39d2d9c092e99c90a5f91720a2f989b487d777347","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T17:57:03Z","title_canon_sha256":"c7f3a5c523654bdc3031cc1e98abf3364046c43c8af16ed8e9e524c29bd0d80d"},"schema_version":"1.0","source":{"id":"2607.09657","kind":"arxiv","version":1}},"canonical_sha256":"cfd79431020cd4cc995d9e0b2801659250bd15339b1a47c5d29b45efb5178e50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfd79431020cd4cc995d9e0b2801659250bd15339b1a47c5d29b45efb5178e50","first_computed_at":"2026-07-13T01:20:28.406996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:20:28.406996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H7swTtHW7Wqv+WVfjkHnrl9B/9KxtvUO5HCjyUgrXqi9RbTKKDmvNDCi1CEdLCA0RsW/85p3iSW68LHQdpK2DQ==","signature_status":"signed_v1","signed_at":"2026-07-13T01:20:28.408382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fafa3a2d4db8c648afc4a028b1bc2b079e2991a77e4ccd20e8001d28168dc16","sha256:a23fdf1b733cd15cd827780079b10b35519de559a194c08ab021d8f9e5635a31"],"state_sha256":"e29ddbc7a5053abfd74a03266f97e312cab8daff2a29d92e27532b88137b4e6e"}